阅读说明：本技术 使用人工智能的过程映射和监控 (Process mapping and monitoring using artificial intelligence ) 是由 R·K·H·帕拉卡什 S·戈努贡达 V·卡玛斯 S·娜拉 于 2020-02-14 设计创作，主要内容包括：本公开描述了一种用于信息的高级传递的系统。在一些实施例中,系统响应于报警而创建显示。在一些实施例中,所述显示上的信息是系统进行的属性映射和/或分析的函数。按照一些实施例,在确定显示什么内容期间,系统使用手动关联、统计分析、相关性、维护数据和/或历史数据中的一个或多个作为工具。在一些实施例中,系统在分析中结合过程模拟器、人工智能、机器学习和/或真实过程反馈中的一个或多个,使用这些工具中的一个或多个,以确定在紧急情况和/或异常事件期间向用户显示什么内容。(The present disclosure describes a system for advanced delivery of information. In some embodiments, the system creates a display in response to an alert. In some embodiments, the information on the display is a function of attribute mapping and/or analysis performed by the system. According to some embodiments, the system uses one or more of manual correlation, statistical analysis, correlation, maintenance data, and/or historical data as tools during the determination of what content to display. In some embodiments, the system uses one or more of these tools in conjunction with one or more of a process simulator, artificial intelligence, machine learning, and/or real process feedback in the analysis to determine what to display to the user during an emergency and/or abnormal event.)

1. A system for improving emergency information delivery, comprising:

at least one processor for executing a program code for the at least one processor,

at least one non-transitory processor-readable medium having instructions stored thereon, the instructions configured and arranged to:

reading asset data from a database;

comparing the asset data to one or more alarm limits;

displaying alarm information when the parameter of the primary asset exceeds the one or more alarm limits; and

secondary information to be displayed with the alert is determined.

2. The system of claim 1, wherein the first and second optical elements are selected from the group consisting of,

wherein the system selects secondary information to display based on one or more attributes of the primary asset.

3. The system of claim 1, wherein the first and second optical elements are selected from the group consisting of,

wherein the system selects secondary information to display based on one or more attributes of one or more secondary assets.

4. The system of claim 1, wherein the first and second optical elements are selected from the group consisting of,

wherein the system selects at least a portion of the secondary information to display based on one or more associations between one or more attributes of the primary asset and one or more attributes of the secondary asset; and

wherein the one or more associations comprise at least one of a correlation analysis and/or a manual association.

5. The system of claim 1, wherein the first and second optical elements are selected from the group consisting of,

wherein the system is configured and arranged to provide root cause analysis based on historical data; and

wherein the root cause analysis is as at least a part of the secondary information.

6. The system of claim 4, wherein the first and second sensors are arranged in a single package,

wherein the system is configured and arranged to identify anomalies in one or more secondary assets and display the anomalies as at least a portion of the secondary information.

7. The system of claim 4, wherein the first and second sensors are arranged in a single package,

wherein determining secondary information to display with the alert comprises creating a separate group;

wherein each separate group includes at least a different portion of the secondary information; and

wherein the system is configured and arranged to allow a user to select each of the separate groups to display the secondary information associated therewith.

8. A system for improving emergency information delivery, comprising:

at least one processor for executing a program code for the at least one processor,

at least one non-transitory processor-readable medium having instructions stored thereon, the instructions configured and arranged to:

reading asset data from a database;

comparing the asset data to one or more alarm limits;

generating an alarm when the parameter of the primary asset exceeds the one or more alarm limits;

determining information to be displayed with the alert; and

generating a display containing a visual representation of the alert and the information.

9. The system of claim 8, wherein the first and second sensors are arranged in a single package,

wherein the display includes a title, breadcrumbs, chart area, grid area, and time control.

10. The system of claim 9, wherein the first and second sensors are arranged in a single package,

wherein the breadcrumb comprises an asset hierarchy;

wherein each asset in the asset hierarchy is separated by a special marker;

wherein pressing the special flag will show a list of one or more sub-assets;

wherein selecting a sub-asset refreshes the breadcrumb to include a hierarchy of sub-assets;

wherein selecting a sub-asset updates the title, chart area, grid area, and time control with the sub-asset information.

11. The system of claim 8, wherein the first and second sensors are arranged in a single package,

wherein the information comprises primary information about the primary asset; and

wherein the information includes secondary information about the secondary asset.

12. The system of claim 11, wherein the first and second sensors are arranged in a single package,

wherein the secondary information includes at least one secondary asset alert.

13. The system of claim 11, wherein the first and second sensors are arranged in a single package,

wherein determining the information to display comprises the system using an attribute map having one or more associations that relate the primary asset to the secondary asset.

14. The system of claim 13, wherein the first and second sensors are arranged in a single package,

wherein the one or more associations comprise at least one of a correlation analysis and/or a manual association.

15. A system for improving emergency information delivery, comprising:

at least one processor for executing a program code for the at least one processor,

at least one non-transitory processor-readable medium having instructions stored thereon, the instructions configured and arranged to:

reading asset data from a database;

comparing the asset data to one or more alarm limits;

generating an alarm when the parameter of the primary asset exceeds the one or more alarm limits;

determining asset data information to be displayed in a plurality of portions;

determining an importance ranking for each of the plurality of portions;

generating a display containing the visual representation of the alert and the plurality of portions; and

it is determined which portion is retained on the display and which portion is hidden when the display is resized.

16. The system of claim 15, wherein the first and second sensors are arranged in a single package,

wherein determining an importance ranking for each of the plurality of portions is based at least in part on the analysis performed by the system; and

wherein the importance ranking and analysis can be different for different asset alerts.

17. The system of claim 15, wherein the first and second sensors are arranged in a single package,

wherein determining which portions to keep on the display and which portions to hide when resizing the display is based at least in part on an analysis performed by the system; and

where the determination of which portion to keep on the display and which portion to hide when resizing the display can be different for different asset alerts.

18. The system of claim 15, wherein the first and second sensors are arranged in a single package,

wherein determining which portion to keep on the display and which portion to hide when resizing the display comprises: the system displays at least one of a new graph and/or chart representing at least a portion of the asset data information in the retained portion.

19. The system of claim 15, wherein the first and second sensors are arranged in a single package,

wherein determining which portion to keep on the display and which portion to hide when resizing the display comprises: the system displays at least one of a new graph and/or chart representing at least a portion of the asset data information in the hidden portion.

20. The system of claim 15, wherein the first and second sensors are arranged in a single package,

wherein determining which portion to retain and which portion to hide on the display when resizing the display is based on one or more associations between one or more attributes of the primary asset and one or more attributes of the secondary asset; and

wherein the one or more associations comprise at least one of a correlation analysis and/or a manual association.

Background

In an emergency situation, the fast action is the difference between a hit-and-miss (near miss) and a disaster. In general, the alarm may appear to all suddenly appear in an unrelated manner. Prioritizing these alarms can be a time consuming task; the time taken to classify and display alarm data in a coherent manner may be the difference between success and failure.

In addition, some alarms only occur at remote locations and do not have a direct connection to an integrated monitoring system. In addition, some alarms are triggered manually by human intervention. One problem in the industry today is missing anomalies or product reviews due to distraction.

The current state of the art is that the user is responsible for building a display to provide reports on one or more assets. The reported asset information may include industrial system assets such as sensors and quality assurance measurement equipment, but may also include any other parameters that may be reported in a visual form, such as market trends or traffic patterns (traffic patterns). The prior art report visualization cannot accommodate different display types. For example, viewing the same information designed for the screen on a cell phone causes the graphics to become too small to understand.

The prior art also requires that all links between the asset information used in the report be made manually. For example, in the prior art, a graph representing the correlation between two attributes of the same or different assets needs to be manually created, saved, and selected for display. Typical prior art correlation graphs are obtained by manually selecting two sets of raw data and then plotting each set of data on a different axis to visually determine if a relationship exists (i.e., examining the display to determine if there is a slope change in the fit line). If a dependency graph does not exist in an emergency situation, valuable time must be spent creating the graph. Even if the graph does exist, it is likely to be stored in a user-specific folder, and searching for the graph or a report containing the graph may be futile, resulting in more time being wasted. For example, in the case of industries such as semiconductors, wasting an hour can result in millions of dollars of lost production capacity.

The prior art uses alarms to alert personnel when one or more asset parameters exceed alarm limits. These alarms are usually generated from the monitoring system in the form of flashing text, sometimes accompanied by set and exceeded values. In the prior art, the user must then log onto a computer, load the monitoring system, and then manually pull the "tags" associated with each alarm. These tags are then loaded into manually configured graphs and/or reports for visual analysis. Statistical analysis requires more graphs and reports to be manually set. In the case of alarms for measurement tools, there may be many different types of equipment (e.g. shredder, conveyor, oven, robot) between measurement nodes. In the prior art, the user had to determine what equipment is between nodes, which attributes are to be graphed, and attempt to determine what is the root cause of the anomaly and what actions to take to deal with.

Thus, there is a need for a system that automatically monitors the production environment and generates displays with items generated from relevant information from a large amount of asset data (e.g., tags) stored in a database so that timely action can be taken to prevent profit loss.

Disclosure of Invention

Some embodiments disclosed herein include a system for improving the delivery of emergency information. In some embodiments, the computer processor reads instructions stored on a non-transitory processor-readable medium (i.e., computer code stored on computer memory). In some embodiments, the instructions are configured and arranged to read asset data from a database. In some embodiments, the assets may include industrial system assets such as sensors and quality assurance measurement equipment. In some embodiments, the asset data may also include any other asset parameters that may be reported using pictures, graphs, tables, and/or links: monitors for market trends or traffic patterns are non-limiting examples of such assets. In some embodiments, the asset data is a digital representation of an analog or digital signal received from the asset. In some embodiments, one or more control limits and/or specification limits are associated with parameters of the asset data. In some embodiments, the parameter of the asset data is a sensor "tag" that communicates the sensor data to the system for storage in the database. In some embodiments, the database is a local database located in the field; in some embodiments, the database is a historian (historian) database that also includes a processor and a non-transitory computer-readable medium. In some embodiments, the system generates an alarm when one or more control limits and/or specification limits are exceeded.

In some embodiments, aspects of the system include novel ways of presenting relevant information associated with an alert. In some embodiments, the system is configured and arranged to read asset data from a database; comparing the asset data to one or more alarm limits; displaying alarm information when a parameter of the primary asset exceeds one or more alarm limits; and determining secondary information to be displayed in conjunction with the alert.

In some embodiments, reading the asset data includes reading the asset data not only from the tag of the alarming asset, but also from a tag associated with the asset. In some embodiments, the system includes instructions to perform a large-scale statistical analysis on some or all of the tag data to determine relationships between one or more assets (i.e., whether input/output of one asset is dependent on input/output of another asset). In some embodiments, the system uses the asset attributes to perform statistical analysis.

In some embodiments, the property of the asset may include a measured parameter (i.e., tag) of the asset, such as time, temperature, pressure, power, amperage, voltage, flow rate, and/or any measurement that may be communicated visually or by electrical signals. In some embodiments, the attributes of the asset may include the color, texture, age, material location, size, shape, mass, density, fault specification, or any other physical characteristic of the asset. In some embodiments, an attribute of an asset may be the impact of an input/output of the asset on upstream and/or downstream assets and/or processes. In some embodiments, any or all of the asset attributes are used in the statistical and/or presentation analysis of the system. In some embodiments, the system uses an attribute map that includes one or more associations between primary assets and secondary assets to determine which attributes should be included in the analysis, prediction, and/or information to be displayed. In some embodiments, the system uses attribute mapping to determine information to display in conjunction with an alarm.

In some embodiments, the statistical analysis may be performed by the system on-demand, continuously, intermittently, and/or in some combination thereof. In some embodiments, the statistical analysis is performed by selecting one or more inputs on a Graphical User Interface (GUI). In some embodiments, when a user selects a link and/or breadcrumbs, a statistical analysis is performed on the particular asset and/or the different levels of assets. In some embodiments, the system performs conventional known statistical analysis techniques and/or algorithms. In some embodiments, the system performs proprietary statistical analysis techniques and/or algorithms. In some embodiments, the system automatically generates one or more displays, including graphs, charts, tables, reports, root cause analysis, suggested action items, and/or countermeasures. As used herein, a reference to a system-generated item and/or information for display is also a reference to an icon, breadcrumb (breadcrumb) and/or link that results in a different display containing the item and/or information; generating the item and/or information on the current display; expand, highlight, and/or jump to a portion of the display having the item and/or information.

In some embodiments, the system uses the identified asset attribute dependencies to identify inputs to the process that may be the root cause of the alarm. For example, in some embodiments, multiple alarms are received from different areas of the plant: in response, the system performs a root cause analysis and determines that the parameters that are to be alerted at the downstream asset step are related to equipment parameters that have been determined by the system to be responsible for the product defect (i.e., upstream equipment and/or set point problems result in a defect output that is now the input to the downstream step, causing equipment failure, thereby causing an alert). Displays according to some embodiments shown herein are generated using relevant alert information. In some embodiments, valuable time is saved by the system prioritizing alarms for display in the order they need to be processed. In some embodiments, valuable time is saved by the system automatically providing one or more of the following: a report explaining the reason for the alarm occurrence; evidence and historical data supporting conclusions (i.e., past actions taken on similar events); a list of action items for how to most effectively solve the problem; historical asset data displayed as graphs (e.g., bar graphs, pie graphs, Pareto (Pareto) graphs) and/or reports; and/or maintenance reports.

In some embodiments, the system includes a cloud-based or cloud/live hybrid historian system, collectively referred to herein as a historian and/or historian database. In some embodiments, the use of a historian allows for the centralization of asset and/or process data obtained from multiple locations (e.g., industrial plants, fleet vehicles, business servers, and/or any data source). In some embodiments, centralization allows the system to use data from some and/or all of the multiple locations for one or more of the analyses discussed above and/or throughout the present disclosure. In some embodiments, this improves system accuracy by providing a larger data set for analysis. In some embodiments, the larger data set improves the accuracy of proprietary and/or conventional artificial intelligence, machine learning, and/or deep learning algorithms (collectively referred to herein as AI) used in conjunction with statistical analysis and related information determination as described above.

In some embodiments, AI is used in one, some, or all of the analyses and/or embodiments set forth in this disclosure. In some embodiments, the AI is used to determine the most relevant items to display, and/or the type of display (e.g., chart, graph, report, link, etc.) used to convey information. In some embodiments, algorithms that do not include an AI perform one or more of the actions described herein. In some embodiments, the system uses processor-readable instructions stored on a memory that, when read by a processor, implement one or more aspects of the system. Throughout this disclosure, use of phrases including "system," system determination, "" system execution, "" system generation, "" system display, "" system comparison, "and/or similar language includes use of AI and/or non-AI algorithms in performing the acts and/or steps performed by the" system.

In some embodiments, the system may automatically process and display user-specific items and/or information. In some embodiments, the system identifies a particular user by logging in identification, facial recognition, maintaining records, approvals, and/or any stored data that links the user to a particular role in the organization. In some embodiments, each particular user receives a customized alert display based on his/her role in the organization. In some embodiments, the system uses AI in conjunction with stored data to determine relevant items/information to display based on the persona of the individual. In some embodiments, the system performs analysis on the stored data using algorithms that do not include AI to determine relevant items/information to display based on the persona of the individual. For example, in some embodiments, particular users may include management personnel, process engineers, and equipment technicians. In some embodiments, the process engineer receives an alarm list including product measurements, the technician receives alarms related to equipment sensors, and the manager receives an alarm list including both product measurements and sensor data: one of ordinary skill will recognize that any combination of items/information may be communicated as desired.

In some embodiments, the system determines the content and/or format of the display. In some embodiments, a "display," as used herein, is defined as an electronic display configured to present a visual representation of information. For example, in some embodiments, the system reads asset data from one or more databases. The system then compares the asset data to one or more alarm limits. In some embodiments, the comparison is performed periodically and the results are stored in a database. When a parameter of a primary asset exceeds one or more alarm limits, an alarm is generated according to some embodiments. As a result, in some embodiments, the system determines information to be displayed in conjunction with the visual representation of the alert. As described above, the system performs various algorithms and analyses to determine the best information content to display for a particular alert and/or user.

For example, if the robot alarms because its sensors do not detect the presence of an expected object, information about the exit counter sensor from a previous processing step may be included in the alarm display, according to some embodiments. When during analysis, the system determines that the exit counter accounted for the missing object, the system determines that the missing object must be lost somewhere between the two processing steps. In some embodiments, the system may review the maintenance history and determine that the error is typically of several root causes, such as a conveyor belt break, an actuator failure, and/or some operator error. In some embodiments, each of these root causes may have occurred and are recorded in the system and/or fed to the system at different facilities distributed over different states. In some embodiments, the system collects the action items and/or standard operational procedures needed to solve the problem. In some embodiments, the system displays one or more of an alarm, a root cause list (in this case several root causes), and a link to an action item and/or a standard operational procedure. As is evident from this non-limiting example, a significant amount of valuable production time can be saved, as even a person unfamiliar with the process can implement and/or initiate the implementation of a solution.

In some embodiments, the system selects information (primary information, secondary information, etc.) to display based on one or more attributes of the primary asset (e.g., time, temperature, pressure, power, amperage, voltage, flow rate, etc.). In some embodiments, the information. For example, it is known in the art that pressure and temperature have a direct relationship. Thus, according to some embodiments, the system automatically provides the user with a temperature and pressure timing diagram when a pressure alarm occurs (of course, other types of information displays are possible). In some embodiments, as a non-limiting example, if the system determines that an alarm is typically caused by a faulty sensor that delivers a power spike at the time of the fault, the system may automatically include this information in the form of a sensor line graph and/or root cause analysis.

In some embodiments, the system includes a process model simulator. In some embodiments, the simulator optimizes 2D and/or 3D model component performance. In some embodiments, the simulator improves 2D and/or 3D model design and provides operational analysis and/or engineering research. For example, in some embodiments, the simulator is designed to perform rigorous heat and material balance calculations for a wide variety of processes.

In some embodiments, the AI is trained using simulator data, production data, and/or a combination of simulator data and/or production data. For example, according to some embodiments, during simulation of an abnormal condition (e.g., during training and/or new facility planning), the system trains the AI model using simulated trends for prediction. In some embodiments, the system AI is trained on which process parameters are related to each other by randomizing the simulator values and analyzing the results (e.g., regression analysis). In some embodiments, the system analysis performed in the simulation is fed into the AI training model to improve the accuracy of the model. In some embodiments, this new approach to "pre-training" the AI model using a simulator allows the system to predict trend conditions that were never actually recorded in a real system. In some embodiments, during training, steps labeled in the continuously simulated trend are fed to the AI so that these steps can be excluded from the model and/or used for different models and/or analyses.

In some embodiments, the system allows the user to do one or more of the following: designing a new process; evaluating the alternative model configuration; updating or improving an existing model; evaluating and proving compliance with environmental regulations; fault detection and weak link elimination are carried out on the factory process; monitoring, optimizing and/or improving plant production and/or profitability; all of which are non-limiting examples of system capabilities. In some embodiments, the system uses a simulator to predict the impact of an alarm on one or more portions of the process. In some embodiments, the prediction is made at the time of the alarm. In some embodiments, the prediction is made during or after the occurrence of an alarm. In some embodiments, the system uses a simulator to establish associative links between asset attributes. In some embodiments, the associative links created during simulation are used to create attribute mappings. In some embodiments, the simulation is used to create an importance ranking for determining information to be displayed to a user. In some embodiments, the simulation is run manually. In some embodiments, the simulation is run by the system algorithm continuously, intermittently, and/or in response to an alarm. In some embodiments, the simulation is run by the system AI continuously, intermittently, and/or in response to an alarm. In some embodiments, the system uses actual response data to improve predictive modeling.

In some embodiments, the system includes capabilities for additional modules. In some embodiments, the additional modules include modules designed to be integrated into the system. In some embodiments, the system includes an application programming interface (i.e., API) that works with third party software and/or system software. In some embodiments, the system includes one or more programming Applications (APPs), such as conventional and/or proprietary AI applications, in some embodiments. In some embodiments, the third party software includes licensable add-ons. In some embodiments, the add-in module extends the functionality of the system in various ways.

In some embodiments, the system includes operational training. In some embodiments, a copy of the entire model may run the process using a simulator. In some embodiments, process changes may be made in the simulation without affecting the real process model. In some embodiments, the system may be used for one or more of the following: training an operator on a user interface, running a maneuver, providing training for a new equipment and/or system upgrade, and/or any other type of training requirement. In some embodiments, the training simulation model may be integrated into the system as the actual control interface of the plant process. In some embodiments, a simulator is used to train personnel for AI monitoring predictions.

In some embodiments, when the user changes the display, the system displays new information and/or reconfiguration information. In some embodiments, the system customizes the displayed information and/or format for the screen size of the display. For example, in some embodiments, if a user pulls up a display containing alert information on a first display, the information is displayed using a first information format. According to some embodiments, if the alert information is pulled up on the second display, the same information is displayed using the second information format. In some embodiments, the different format is due to the second display having a different visualization area than the first display. Further, in some embodiments, more or less information may be presented to the user on the second display based on the available visualization area determined by the system. For example, if a user is viewing alarm data from an equipment on a portable computer, such as a cellular telephone, the user may see one or more equipment control charts with highlighted alarm points, alarm lists, and breadcrumbs at the top of the browser that lead to a hierarchy of equipment and/or show links to previously viewed items. When a user accesses the same alarm data from a larger monitor, such as a desktop monitor or television screen, showing the same information presented on the portable computer, in addition, a process flow diagram may be displayed in which each item in the process flow has a countermeasure link containing instructions for how to resolve the alarm and resolve the root cause.

In some embodiments, if a user is viewing information in a window (e.g., a browser window) and the window is resized, the system automatically determines how to display the initially provided information. In some embodiments, the determining includes which portion to retain on the display and which portion to hide when resizing the display. In some embodiments, the determination is based at least in part on an analysis performed by the system. In some embodiments, the determination is based at least in part on an importance ranking. In some embodiments, the importance ranking is obtained by system analysis. In some embodiments, the importance rankings are created manually for one or more assets. In some embodiments, the importance ranking is based on one or more of the following: production flow effects, historical data, maintenance data, simulation data, AI training, or any other data source available to the system. In some embodiments, the importance rankings are different for different assets. In some embodiments, the importance rankings may cause the information hidden for the primary asset to be different than the information hidden for the secondary asset when the display and/or window is resized. In some embodiments, a new set of information (e.g., one or more new titles, graphs, charts, time controls, breadcrumbs, etc.) is displayed when the window and/or display is resized.

In some embodiments, one or more items on the display may be annotated and/or marked with comments. In some embodiments, the alarm view page is divided into a plurality of windows or sections that include one or more processes and/or alarms associated with one or more industrial process systems. In some embodiments, when the displayed resolution is reduced and the width available for visualization on the at least one user display is reduced, one or more portions and/or columns may be hidden based on one or more priorities. In some embodiments, alarms of alarm-related information associated with individual alarms are grouped based on one or more automatically assigned labels, including manually and/or system-determined links. In some embodiments, AI is used to mark trends, as described further below.

In some embodiments, the alert view page includes a header section, and/or a breadcrumb section, and/or a chart area section, and/or a grid area section, and/or a time control section. Some embodiments further comprise program logic executed by the at least one processor to enable display of the asset hierarchy within the breadcrumb section on the at least one user display. In some embodiments, each asset in the asset hierarchy is separated by conventional characters, graphics, logos, and/or symbols.

Some embodiments further include program logic executed by the at least one processor that enables a user to interact with the at least one user display to show one or more sub-assets under the selected asset, wherein when a sub-asset is selected, the breadcrumb section is updated with a new asset hierarchy and/or the chart area section is updated and/or the grid area section is updated. Some embodiments further include program logic (i.e., processor-readable instructions) executed by the at least one processor that enables further analysis of the alarm-related information through single or multiple filters of multiple sets of alarms to automatically provide a view of multiple alarm sets, and/or a detailed alarm record for a set of one or more sets of alarms.

Some embodiments further comprise program logic executed by the at least one processor to enable display of one or more portions and/or columns of a grid having one or more portions and/or columns on the at least one user display, the one or more portions and/or columns including one or more of: "time," "severity," "duration," "status," "alarm-on-alarm," "microwire (sparkline)," status, "" label, "" object, "" zone, "" value, "" limit, "and/or" unacknowledged.

Some embodiments of the invention relate to training AIs for production monitoring. In some embodiments, the system AI may be trained to identify trending anomalies. In some embodiments, the AI may be trained to predict events with some certainty. In some embodiments, the AI may be trained to identify patterns in the continuous trend data and mark these patterns as steps. In some embodiments, the AI may be trained using image and/or video feeds to identify visual defects. In some embodiments, once the AI model is trained, the AI may issue an alarm and feed relevant information to the system so that the most relevant alarm information is displayed.

Drawings

FIG. 1 depicts a non-limiting exemplary historian that includes a computer system for securely providing and obtaining configuration data, in accordance with some embodiments.

FIG. 2 illustrates a non-limiting example of an operational historian data pattern detection and communication service system in accordance with some embodiments.

FIG. 3 illustrates a non-limiting exemplary embodiment of a facility process system according to some embodiments.

FIG. 4 is an alert view page according to some embodiments.

FIG. 5 illustrates a non-limiting, exemplary embodiment of an alert view page according to some embodiments.

FIG. 6A illustrates an alert display in accordance with some embodiments.

Fig. 6B illustrates a graphical display in accordance with some embodiments.

FIG. 7 illustrates a computer system capable of implementing or containing systems and methods according to some embodiments.

Figure 8 illustrates a system for security compliance applications, in accordance with some embodiments.

Fig. 9 depicts the use of the system to detect proper seating and loading of a truck 900, according to some embodiments.

FIG. 10 illustrates the use of the system to ensure proper loading of a truck, according to some embodiments.

Fig. 11 illustrates a camera feed using the system to control truck loading operations, according to some embodiments.

FIG. 12 shows one or more programs that the system may be loaded with and/or connected to, according to some embodiments.

FIG. 13 illustrates an interface for implementing the system, according to some embodiments.

FIG. 14 represents a browser page for initiating a modeling process, in accordance with some embodiments.

FIG. 15 illustrates a model description page in accordance with some embodiments.

FIG. 16 represents a target page of a model creation process according to some embodiments.

FIG. 17 illustrates a target page after a user has entered search criteria in a variable search, in accordance with some embodiments.

FIG. 18 shows the destination page after the user has selected the add button, according to some embodiments.

FIG. 19 illustrates a feature page according to some embodiments.

FIG. 20 represents a model creation step page, according to some embodiments.

FIG. 21 illustrates adding a step to a model on a step page, according to some embodiments.

FIG. 22 illustrates an example of creating additional steps for a main model, according to some embodiments.

FIG. 23 depicts steps for using the system to define running different types of products, according to some embodiments.

FIG. 24 illustrates a step page for excluding a particular time period, according to some embodiments.

FIG. 25 illustrates a prediction page according to some embodiments.

FIG. 26 illustrates a prediction page after a preview model button is selected, in accordance with some embodiments.

FIG. 27 illustrates a prediction page after a verification model button is selected, in accordance with some embodiments.

FIG. 28 illustrates a prediction page after a continue verify button is selected, in accordance with some embodiments.

FIG. 29 shows a prediction page in which the user has selected "alerts" in the message section, according to some embodiments.

FIG. 30 shows a prediction page in which the user has selected "info" in the message section, according to some embodiments.

FIG. 31 illustrates a prediction page in which a user may configure notification preferences for the manner in which information is displayed for the system, according to some embodiments.

FIG. 32 represents a prediction page in which less frequent but more accurate preferences are selected, according to some embodiments.

FIG. 33 represents a prediction page with some consequences of predicted versus actual values of the master model, according to some embodiments.

FIG. 34 represents a prediction page in which a user has selected a portion of display 3402 to receive details about a modeled result, according to some embodiments.

FIG. 35 illustrates a review and create page according to some embodiments.

FIG. 36 represents a model page with all models created, according to some embodiments.

FIG. 37 illustrates the transformation of an image from a remote manual visual inspection station to a SCADA, in accordance with some embodiments.

Fig. 38 illustrates a system for automating quality control inspection of cans, in accordance with some embodiments.

Fig. 39 depicts a training interface for training system AI for can defect monitoring, in accordance with some embodiments.

FIG. 40 illustrates a training interface after saving a model configuration, according to some embodiments.

Fig. 41 illustrates a training interface in training an AI model, according to some embodiments.

Fig. 42 illustrates a snapshot of an AI model run in accordance with some embodiments. In some embodiments, once training is complete, the AI model may begin monitoring the feed by selecting start/stop button 4201 and not selecting training box 4202.

FIG. 43 illustrates manual classification of misclassified images according to some embodiments.

Detailed Description

FIG. 1 depicts a non-limiting exemplary historian 111 that includes a computer system for securely providing and obtaining configuration data, in accordance with some embodiments. In some embodiments, the operational historian can store (e.g., "historize") various data related to the industrial process. Some example data may include, but is not limited to, timing data, metadata, event data, configuration data, raw timing binary data, tag metadata, diagnostic log data, and the like. The operational historian can also be adapted to record trend and historical information about the industrial process for future reference. The operational historian can analyze process-related data stored in the operational historian database and transform that data into timely reports that are transmitted to one or more user displays. In this way, the operational historian can filter (e.g., curate) data to improve the visibility of the data to the user (e.g., via the user display) without overwhelming the user and/or overburdening the communication network.

In some embodiments, the historian 111 can include a timing database 133 and a relational database 136. In at least one embodiment, both the timing database 133 and the relational database 136 may derive data from a variety of sources during the data acquisition 130, including, but not limited to, one or more servers 131a, one or more human-machine interface (HMI) applications 131b, at least one application server 131c, and/or manually entered and/or external data 131 d. In some embodiments, the timing data may be provided in part by process control data stored in the timing database 133, where the timing data may represent historical plant or facility process information, such as a continuum of process flow values measured over a period of time. In some embodiments, configuration data may be provided at least in part by relational database 136, such as configuration settings and associated storage capabilities of cloud services used by historian 111.

FIG. 2 illustrates a non-limiting example of an operational historian data pattern detection and communication service system in accordance with some embodiments. In some embodiments, the system 200 can analyze data stored in at least one operational historian and transform the data into a timely report that is transmitted to one or more user displays. As such, various aspects of the system 200 may filter (e.g., curate) data to increase numbersBased on visibility to the user (e.g., via the user display) without overwhelming the user and/or overburdening the communication network. In some embodiments, the system 200 can include an operational historian 202 (e.g., including the historian 111 of FIG. 1), and/or a reporting service 204, and/or a report database 206, and/or a curation service 208, and/or a user-specific report collection 210, and/or a general report collection 212, and/or an alert service 214, and/or a search service 216. In at least one embodiment, the system 200 can generate one or more data reports or summaries for the user based on data provided by the operational historian 202 and/or other providers. In some embodiments, the historian 202 can include processor-executable instructions embodied on a storage memory (e.g., as part of a computer server) to provide an operable historian 202 via a software environment. Exemplary operational historians 202 include those provided by AVEVA Group pic and its subsidiariesHistorian andonline, AVEVA Group pic and its subsidiaries also have trademarks associated with such products.

In some embodiments, the operational historian 202 can be adapted to store (e.g., "historize") various types of data related to the industrial process. In some embodiments, the data includes, but is not limited to, timing data, metadata, event data, configuration data, raw timing binary data, tag metadata, diagnostic log data, and the like. In some embodiments, the operational historian 202 can be adapted to record trend and historical information about one or more industrial processes for future reference. For example, in some embodiments, the operational historian 202 can store data regarding various aspects of a facility process (such as, but not limited to, an industrial process) in quantities that cannot be interpreted or analyzed by humans. For example, an operational historian may receive two million or more data values (e.g., tags associated with process control components, process variables, etc.) per second.

In some embodiments, the reporting service 204 can be adapted to retrieve data from the operational historian 202, detect patterns in the retrieved data, generate reports that include information about the detected patterns, and store the generated reports in a report repository, such as database 206. In some embodiments, the reporting service 204 includes processor-executable instructions embodied on a storage memory to provide the reporting service 204 via a software environment and a communication network. For example, in some embodiments, reporting service 204 may be provided as processor-executable instructions comprising processes, functions, routines, methods, and/or subroutines used by computer 203 alone or in conjunction with additional aspects of system 200, in accordance with some embodiments of the present disclosure. More details of the reporting service 204 are provided herein.

In some embodiments, computer 203 may be adapted to provide a reporting service 204, a reporting database 206 (or an interface with a computer-readable storage medium storing reporting database 206), a curation service 208, a user-specific report collection 210, a general report collection 212, an alert service 214, and a search service 216, as further described herein. In some embodiments, the report database 206 may be adapted to store reports generated by the reporting service 204 as an organized collection of data, as further described herein. In some embodiments, the user display 218 may be adapted to receive and send data to and from the user-specific report set 210, and/or the general report set 212, and/or the alert service 214, and/or the search service 216, as further described herein. For example, in some embodiments, the reporting service 204 can be adapted to retrieve data from the operational historian 202 by sending a query to the operational historian 202, which the operational historian 202 receives and uses to select stored data that matches the query. In some embodiments, the operational historian 202 can then send the selected data to the reporting service 204. In some embodiments, the reporting service 204 may retrieve the data continuously or at intervals. In some embodiments, the reporting service 204 may retrieve and/or receive data from additional sources, including reporting application 206 (e.g., via an Application Programming Interface (API) of the reporting service 204), the built-in reporting service 208 (e.g.,online built-in reporter), application-specific reporting services configured based on client applications, and/or "human machine interface" (HMI), and/or any other conventional reporting service.

In some embodiments, the reporting service 204 may be adapted to analyze the data using algorithms and/or AI to detect certain patterns (e.g., "patterns of interest") and/or inconsistencies in the data for reporting and/or triggering alarms. For example, some algorithms include statistical algorithms, machine-learned AI algorithms, rule-based algorithms, and the like, and according to some embodiments, when certain patterns are detected by the system, the reporting service 204 may generate reports on these detected patterns. In some embodiments, the report includes text, graphics (e.g., a graph, an image, etc.), and/or metadata, and/or one or more alerts or alert data. In some embodiments, the report may include information about the detected pattern in a format compliant with the curation service 208 and/or in a format understandable to humans when displayed via a display and/or HMI. In some embodiments, reporting service 204 may transform data from a format that is difficult for curation service 208 and humans to a format that is understandable by curation service 208 and humans when displayed via user devices (e.g., displays, screens, projectors, augmented reality glasses, helmets, and/or anything capable of visually presenting information) 218. Further, in some embodiments, after generating the report, the reporting service 204 may send the report to the report database 206 for storage.

In some embodiments, the report database 206 may be adapted to store reports as an organized collection of data. In some embodiments, the report database 206 may store reports at a central location for access by various systems and displays. In some embodiments, the system 200 includes a plurality of reporting services 204, each reporting service 204 capable of retrieving data from the operational historian 202, detecting patterns in the data, generating reports, and storing the reports in a report database 206. In some embodiments utilizing multiple reporting services, each reporting service may operate independently, or the collective operation service may operate on portions of a larger reporting task in parallel. In some embodiments, the reports in the database 206 are available for access via the search service 216, and/or from the user-specific report set 210, and/or the general report set 212, and/or the reports may be sent in real-time via the alert service 214 to one or more user displays 218 in the form of alerts. In some embodiments, the user display 218 may be embodied as a mobile display having a mobile application ("app"). For example, in accordance with some embodiments, various aspects of the present disclosure may be installed via an app store, and may be optimized for touch screens. In some embodiments, aspects of the present disclosure may be browser-based and may contain data components including charts, trends, grids, and the like.

FIG. 3 illustrates a non-limiting exemplary embodiment of a facility process system 300 according to some embodiments. In some embodiments, the facility process system 300 can include at least one computer 203, at least one operational historian 201, at least one reporting database 206, at least one user device 218 (including a processor and/or display), at least one communication network 302, and a coupled fluid treatment system 310. In some embodiments, the historian 201 may be adapted to provide the operational historian 202, and the operational historian 202 may be adapted to store (e.g., "historize") various types of data associated with the fluid treatment system 310, as further described herein. In some embodiments, the fluid handling system 310 of this non-limiting embodiment includes at least one pump 303, one or more valves 304, at least one sensor 306, and at least one process controller 308.

In some embodiments, within the facility process system 300, the computers 203, the operational historian 201, the report database 206, the user equipment 218, and various components of the fluid handling system 310 (e.g., pumps 303, valves 304, sensors 306, process controllers 308) may be communicatively connected via the communication network 302. In some embodiments, communication network 302 may facilitate the exchange of data between historian 201, computer 203, report database 206, one or more user devices 218, and components of fluid treatment system 310.

In some embodiments, the communication network 302 in the embodiment of fig. 3 may be a Local Area Network (LAN) coupled to other telecommunications networks, including other LANs or portions of the internet or an intranet. In some embodiments, the communication network 302 may be any telecommunication network that facilitates data exchange, such as those operating in accordance with IEEE 802.3 (e.g., ethernet) and/or IEEE 802.11 (e.g., Wi-Fi) protocols. In another embodiment, the communication network 302 is any medium that allows data to be physically transmitted over serial or parallel communication channels (e.g., copper, wire, fiber optics, a computer bus, wireless communication channels, etc.). In some embodiments, the communication network 302 may include, at least in part, a process control network.

In some embodiments, the fluid treatment system 310 may be adapted to modify or refine a feedstock to produce a final product (e.g., in the chemical, oil and gas, food and beverage, pharmaceutical, water treatment, and power industries). In some embodiments, the system is configured to optimize processes and treatment systems other than fluid treatment system 310. Exemplary processes may include, but are not limited to, those in the chemical, oil and gas, food and beverage, pharmaceutical, water treatment, and power industries. In some embodiments, the process controller 308 may provide an interface or gateway between components of the fluid handling system 310 (e.g., the pumps 303, the valves 304, the sensors 306) and other components of the system 300 (e.g., the historian 201, the computer 203, the report database 206, the user device 218). In some embodiments, the components of the fluid treatment system 310 may communicate directly with the historian 201, and/or the computer 203, and/or the report database 206, and/or the user device 218 via the communication network 302. In some embodiments, the process controller 308 may send and receive data to and from the pump 303, and/or the valve 304, and/or the sensor 306 to control and/or monitor various aspects of the fluid treatment system 310.

Some embodiments relate to improved processing and display of data in electronic devices, including, for example, computers and/or computer servers (e.g., computer systems or servers functioning as manufacturing execution systems) that provide technical solutions in which users can effectively monitor processes, retrieve, process, and view data. Some embodiments include systems and methods for arranging, constructing, and transmitting data or data sets in a computer or computer server using one or more data or data streams. In some embodiments, the data or data set may include one or more alerts or reminders related to the at least one asset.

Some embodiments include a computer-implemented method comprising program logic executed by at least one processor of a computer system, the program logic capable of providing an environment that allows a user to utilize a Graphical User Interface (GUI) to visualize data or data blocks, monitor data and alarms, including one or more transitions to and from alarm or reminder states, such as those transitions that may be received from the industrial process system 300. For example, in some embodiments, the historian 111 can provide a tool for use by a user that enables the user to monitor memory blocks and functions. In addition, some embodiments enable a user to observe incoming event data, the merging of snapshots in storage blocks, and responses to queries. In some embodiments, this information may be conveyed to the user in the GUI in the form of text and/or graphics. In some embodiments, the GUI may have various icons indicating different event data, storage blocks, or snapshots, as well as alarms. Further, some embodiments include a computer-implemented method comprising: retrieving, by a computer system, a file comprising a plurality of data from a data repository; displaying data or updating a display based at least in part on data or information related to the file via a display screen of a user interface in communication with the computer system.

Some embodiments include a system, a server, and computer-implemented program logic executed by at least one processor configured to represent hierarchical assets, and various attributes of each asset that can be uploaded to enable one or more users to search for assets at higher levels, rather than and/or in addition to individual attributes of the assets, and then visualize at least one available reminder and/or alarm for each matching asset.

In some embodiments, the systems, servers, and methods may include audible reminders or alerts associated with visual displays, such as displays on one or more user devices 218. In some embodiments, the system may process visualizations including automatic groupings of alerts for assets based on attributes of the assets. In some embodiments, the property of the asset may include a monitored parameter of the asset, such as time, temperature, pressure, power, flow rate, and/or any measurement that may be communicated visually or by electrical signals. In some embodiments, the system may detect attributes such as visual changes and/or anomalies associated with the physical asset using a camera and/or any sensor capable of detecting the propagating electromagnetic energy and converting the detection into an electrical signal. In some embodiments, the system may associate an anomaly occurring in the secondary asset with a condition that caused an alarm in the primary asset. In some embodiments, the system predicts anomalies that will occur in the secondary assets based on historical data including maintenance records, statistical analysis, continuous or intermittent relevance analysis, root cause analysis algorithms, AI training, and/or any other available data source.

In some embodiments, the system uses artificial intelligence, machine learning, and/or deep learning (collectively referred to herein as AI) to detect and/or classify images and/or sensor data to perform analysis. In some embodiments, the system may analyze two or more assets in a process flow and generate a written or visual report describing the impact that an alarm condition of one asset may have on both upstream and downstream processes. In some embodiments, the system may learn in real time whether the predicted effect matches the observed effect and adjust the prediction for the current bias and future events. In some embodiments, the systems, servers, and methods may provide quick and easy to understand visualization of alerts and reports on one or more displays. In some embodiments, the display may comprise a display of a computer system, personal digital assistant, cellular or smart phone, digital tablet, and/or other fixed or mobile internet device.

Some embodiments provide computer-implemented systems and methods including program logic executed by at least one processor that enables grouping of alarms that may be associated with individual alarms based on one or more automatically assigned tags, such as one or more of the alarms of the above-described example embodiment of the facility process system 300. In some embodiments, the correlation between the group and each alarm instance may be based on a one-to-one and/or one-to-many mapping of attribute values for valid summaries of alarms, and/or an explicit identification of one or more reasons for each alarm instance, and the action to be taken in response. In some embodiments, further alarm analysis may be performed through a single or multiple filters of multiple sets of alarms, which may automatically provide a view of detailed alarm records, causes, and/or response actions for multiple alarm sets, a set of one or more sets of alarms.

Some embodiments include computer-implemented systems and methods, including program logic executed by at least one processor to enable one or more users to visualize all relevant alerts for an asset based on one or more asset searches, such as one or more searches initiated by search service 216. Some embodiments may include automatic grouping of alarms based on attributes of the alarms and/or analysis of those attributes. In some embodiments, the system may provide a reason and/or effect correlation between the group and the individual alert instances. In some embodiments, the systems and methods may automatically process (e.g., using AI) and display one or more intuitive groupings and corresponding details, and/or view a large number of alarms based on one or more assets, so that the user can focus on problem areas (e.g., which area in yesterday my plant alarms the most) without spending a significant amount of time finding the area with the most number of alarms.

FIG. 4 is an alert view page 400 according to some embodiments. As shown, in some embodiments, the systems and methods may process and display an alert viewing page 400 that is divided into a plurality of windows or portions that may allow one or more users to view various details about one or more alerts on the user device 218. For example, in some embodiments, the portions may include, but are not limited to, a header portion 410, and/or a breadcrumbs portion 420, and/or a charts area portion 430, and/or a grid area portion 440, and/or a time control portion 450. According to some embodiments, the title section 410 may be the same as in the exploration section, the only difference being that the title section will not contain search controls.

In some embodiments, within breadcrumb section 420, the asset hierarchy is represented using breadcrumbs that can display the directory path of the current folder or web page and provide access to the respective parent directory. In some embodiments, each asset in the asset hierarchy may be separated by conventional graphics, logos, symbols, and/or characters (such as a special logo ">", or any other suitable character or combination of characters and graphics). In some embodiments, by pressing a special mark, the user may present one or more sub-assets under the selected asset. In some embodiments, by selecting a sub-asset, the system may refresh the breadcrumb with a new asset hierarchy and/or update the chart area section 430 and/or the grid area section 440. In some embodiments, the hierarchy leads to additional analysis including cause and/or action items. In some embodiments, the additional analysis is user-specific.

In some embodiments, the system may display one or more portions and/or columns of the grid (grid area portion 440) at a higher resolution, including but not limited to alert information such as one or more of the following: "time," severity, "" duration, "" status, "" alarm-on-alarm, "" microwire map, "" status, "" label, "" object, "" area, "" value, "" limit, "and/or" unacknowledged. In some embodiments, when the resolution is reduced (i.e., the display size available to the grid is reduced), at least some columns may be hidden based on one or more priorities specified by a user, system, administrator, or other person or system. For example, in some embodiments, the systems and methods may process and display the shrinkage of the width and/or height of the "microwire map" as the resolution decreases. In some embodiments, a "microwire map" is a conventional minibar map showing the general shape of the change in the measurement value. In some embodiments, the system may be based on: the time in alarm; a "not confirmed" bar graph; an "object"; "area"; the "limit" and/or "value" columns to process and display one or more columns. In some embodiments, the system may process and display one or more columns based on a text label of the alarm type (e.g., "high-high"), while the associated icon may remain. In some embodiments, the columns include links to message boards, reports, reasons, and/or action items previously saved in the system and/or provided by the system (e.g., via AI).

FIG. 5 illustrates a non-limiting, exemplary embodiment of an alert viewing page 500 in accordance with some embodiments. In some embodiments, grid 510 may present a list of all alerts generated for a selected asset and its sub-assets. Some further embodiments include one or more additional contiguous and/or overlapping designs that include alarm displays and statistics. In some embodiments, the systems and methods may process and provide a chart area (shown on the left side of fig. 5 and enlarged in fig. 6A and 6B) that may be used to display useful alert summary information, wherein a snapshot of the alert activity is provided to the user. For example, some embodiments include an alarm display 520 and an alarm count 530. In some embodiments, a user may interact with pareto chart 530 to access more specific data in a grid area. In some embodiments, the chart area may include a pareto chart 530 (fig. 6B) that may display the number of alarms for a given time period.

In some embodiments, grid 510 may include an alert column 550 including, but not limited to, a data column 555, a time column 558, and/or a reminder column 560 for displaying one or more different reminder symbols. Further, in some embodiments, grid 510 may include an "alarm in" column 562, a status column 564, an alarm signal column 566, a signal chart status column 568, a label column 570, and/or an object column 572. Further, in some embodiments, grid 510 may include a region column 574, a value column 576, a limit column 578, and/or an unacknowledged column 580. In some other embodiments, the alarm viewing page 500 may be filtered by time or date using a selection filter 590 displayed at the bottom of the alarm viewing page 500.

In some embodiments, alarms may be grouped by alarms, tags, areas, and/or objects by a "group by following" control. In some embodiments, an alarm may be selected based on conditions using selector 520 including, but not limited to, selected conditions 521, 523, 525, and 527. Referring to FIG. 6A, in some embodiments, the "group by following" control (selector 520) may be located at the top of the chart area. In some embodiments, a "group by press" tag may include a set of buttons or other conventional interface features that may allow a user to display alarm data in pareto chart 530 based on an alarm (condition), tag, area, or object, where the tag interprets the current group. In some embodiments, the systems and methods may enable a default condition by alarm (condition). In some embodiments, when the user changes the groupings by clicking on one of the buttons, the grid and pareto charts 530 may be redrawn based at least in part on the user's input.

In some embodiments, the grid may display a rectangular color key next to the data in all cells of the column represented by the currently selected group (represented as reminder column 560). In some embodiments, pareto chart 530 may then show a set of data representing the number of alarms grouped by the current selection. In FIG. 6B, alarm counts 532, 534, 536, 538, 539 are shown, in accordance with some embodiments. In some embodiments, the color of the column and legend item rectangular color keys may match (alert column 560) the rectangular color keys in the grid. In the case of press alarm (condition) grouping, the grid may show two rectangular color keys in the label column and the condition column. In the case of a label column, an area column, and an object column, a rectangular color key may appear in each cell of a corresponding column in the network. In some embodiments, a "group by … press" selection may be indicated by a highlighted color (e.g., such as blue) of the corresponding button on the control. In some embodiments, all buttons on the "group by …" control may have a tooltip to interpret the group.

Referring back to fig. 5, as well as fig. 6B, in some embodiments, a pareto chart 530 may be displayed under the "group by following" controls previously described. In some embodiments, in one or more of the various columns described, the pareto chart 530 may describe the number of alarms by alarm (condition), label, area, or object (depending on the "group by following" control). In some embodiments, chart 530 may show up to 10 columns; however, the number of columns may vary, and may include more or fewer columns than shown in the non-limiting embodiment of FIG. 5. In some embodiments, the columns may be arranged in descending order, with the first 9 columns being the top 9 columns. In some embodiments, column 10 (if present) may represent the sum of all other data. In some embodiments, if there are less than 9 items, then no other columns are shown and the remaining columns may share the chart width.

Referring to FIG. 6B, in some embodiments, a chart 530 may show a header (such as "alarm count") at the top that describes the charted data. In some embodiments, chart 530 may include a y-axis marked with a numbered scale and may have gray grid lines extending across chart 530. In some embodiments, chart 530 may include a legend with a legend entry for each column depicted in the chart. In some embodiments, the legend item may contain a rectangular color key corresponding to the color of each column in the chart, and contain a label for the ID or name of the current item 532, 534, 536, 538, 539 represented. In some embodiments, if the legend text exceeds the container size, the legend text may be truncated using an ellipse and a tooltip that appears to display the full name if the user hovers over the truncated legend item text.

In some embodiments, when a column or legend item of grid 510 is clicked, item highlighting may occur. In some embodiments, when a user first clicks on a column or legend item, the column and legend item will become highlighted, while all other column or legend items will be darkened. In some embodiments, the user may click on the other columns or legend items that are dimmed to add them to the highlight.

In some embodiments, when highlighted in place, the highlighted (i.e., not darkened) column and legend items may be clicked to remove the items from the highlight. In some embodiments, once all columns are highlighted, or all highlights are removed, chart 530 may re-enter the original state in which no column or legend item is darkened.

In some embodiments, the pareto chart 530 may be a fixed size when the screen height is high, and the chart 530 may also shrink once the height of the screen drops below the initial height. In some embodiments, the legend area height may be a generally fixed height such that all legend items may be displayed, and when the screen size is too small to show meaningful data in the bar chart portion, the legend area may shrink and include a scroll bar so that the user may still access all legend items. In some embodiments, when the screen width is reduced such that the time control overlaps the chart 530, the chart 530 container automatically resizes such that no overlap occurs. In some embodiments, a chart such as pareto chart 530 is replaced with a different chart when the size of the screen or window is adjusted.

In some embodiments, the system presents one or more of information, settings, and/or links on an exploration page. In some embodiments, the exploration page (or portion) is a display that prioritizes information based on previously viewed and/or searched terms. In some embodiments, using this time control, the system may quickly select a predefined time selection and retrieve the alarm records from the server based on past user interactions. In some embodiments, the start and end times may be customized in the exploration page.

In some embodiments, the system and methods associated therewith may process the data based on the asset hierarchy and the selected duration, wherein the original alert is retrieved from a system server, such as computer 203. In some embodiments, during this stage, a portion of the grid area showing a basic skeleton, outline, or template (including some animations in some further embodiments) may be displayed to indicate that the grid is waiting for data from the server, as well as to indicate a conversion of the raw data to grid format. In some embodiments, once the data is retrieved from the server, the client may merge the related records and present the merged view in the grid.

In some embodiments, the systems and methods may process one or more rules applied during alarm record consolidation. For example, in some embodiments, the processed rules may group all records based on alarm IDs. In some embodiments, the end time ('ef') is calculated based on the current time ('cf') and the end time ('tc.ef') specified in the time control. In some embodiments, if 'cf' is greater than 'tc.et', then 'ef' will be 'tc.ef' (i.e., the end time that the system displays to the user is the end time specified in the time control). In some embodiments, if 'ct' is less than or equal to 'et', then 'et' will be 'ct' (i.e., the end time is selected by the system as the current time). In some embodiments, if the end time 'et' is the current time 'ct', the display will be continually updated with current time data as the current time changes.

In some embodiments, if the group contains an ' alarm set ' record, then the ' unack ' (i.e. unconfirmed) duration is retrieved from the ' alarm _ unackrations ' (alarm unconfirmed duration) property in the ' alarm. If not, then according to some embodiments, the unack duration and/or in-alarm duration is retrieved from the ' alarm _ durations ' (alarm durations) in the ' alarm. If neither record (acknowledge or clear) exists, both the unack duration and the in-alarm duration are calculated based on the end time 'et' as described above.

In some embodiments related to rule-based processing, if the group contains an 'alarm. acknowledged' record, the unacknowledged duration is retrieved from the 'alarm _ unackrations' property in the 'alarm. acknowledged' record. The "in alarm" duration information is then calculated based on the start time specified in the time control and the event time registered in the' alarm. Clear ' records are not present, in some embodiments, the mid-alarm duration is calculated based on the start time and end time ' et ' specified in the time control.

In some embodiments, if the group contains only' area. Later, additional properties (such as "alarm in", "silence", and "hold") are calculated. For example, some embodiments include rule-based process definitions that may include one or more of the following:

a. "alarm in": clear' records do not exist for each alarm for the duration of the query, then this attribute is set to true for that alarm. If not, the attribute is set to false.

B. 'lay aside': the attribute is retrieved from the last record of each alarm for the duration of the query.

C. "silence": the attribute is retrieved from the last record of each alarm for the duration of the query.

In some embodiments, a micro-line graph (e.g., a small inline or overlay graph) is constructed by retrieving process values from the system server for the particular tags mentioned in each alarm record. In some embodiments, if the process value is null for a given label, an empty microwire map (indicated in some embodiments by filling the microwire map graph with a solid color) may be displayed in the grid or grid portion. In some embodiments, if a process value exists, a micro-line graph is drawn using the process value. In some embodiments, after the micro-line plot is drawn, a portion of the micro-line plot is highlighted based on the 'in alarm' duration and colored according to the severity of the alarm.

In some embodiments, the systems and methods may process tests including, but not limited to: verifying that all parts are present in the rendered page; verifying that a predefined time selection can be selected in the time control; and/or the verification may be made with a custom time selection in the time control.

FIG. 7 illustrates an architecture of a computer 203 that can provide aspects of an operational historian data pattern detection and communication services system 200 (FIG. 2) via a software environment. In this embodiment, computer 203 (FIG. 3) may include at least one processor 702, at least one memory 704, and at least one input/output (I/O) interface 706 that interfaces with at least one I/O component 708. In some embodiments, the memory 704 includes an operational historian interface 202, a reporting service 204, a report database 206, a curation service 208, a user-specific report set 210, a general report set 212, an alert service 214, and a search service 216, each of which is embodied in processor-executable instructions for execution by the processor 702. In some embodiments, processor 702, memory 704, and I/O interface 706 are communicatively and/or electrically connected to each other. In some embodiments, I/O interface 706 is communicatively and/or electrically connected to I/O component 708. In some embodiments, the processor 702 may be adapted to execute processor-executable instructions stored in the memory 704 to implement the operational historian interface 202, and/or the reporting service 204, and/or the report database interface 206, and/or the curation service 208, and/or the user-specific report collection 210, and/or the general report collection 212, and/or the reminder service 214, and/or the search service 216. In some embodiments, the I/O interface 706 of FIG. 7 provides a physical data connection between the computer 103 and the I/O component 708. In an embodiment, the I/O interface 706 is a network interface card ("NIC") or modem, and the I/O component 708 is a telecommunications network.

In some embodiments, the operational historian interface 202 of FIG. 7 can be adapted to provide a connection between a computer 203 and the operational historian 202. In some embodiments, the operational historian interface 202 can retrieve and/or receive data from the operational historian 202 via the I/O interface 706, as further described herein. In some embodiments, the report database interface 206 of fig. 7 may be adapted to provide a connection between the computer 203 and a computer-readable storage medium capable of storing the report database 206. In some embodiments, report database interface 206 facilitates publishing reports from report service 204 to report database 206 via I/O interface 706, as further described herein. In another embodiment, the report database interface 206 facilitates the curation service 208 and the search service 216 to access the report database 206 via the I/O interface 706, as further described herein.

Figure 8 illustrates a system for security compliance applications, in accordance with some embodiments. In some embodiments, the AI is trained to classify images from the camera 801 and determine whether a person is wearing a safety helmet in a safe area. In some embodiments, if the user is wearing the headgear 802, the system classifies the image as compliant 1803 and takes no action. In some embodiments, if the user 1804 not wearing headgear is classified as not compliant 1805, an alarm is generated. The use of image training AI is discussed in further detail below.

Fig. 9 depicts the use of the system to detect proper placement and loading of a truck 900, according to some embodiments. In some embodiments, the system is trained to determine whether truck 901 is within boundary 902 using images from camera 903. In some embodiments, an alarm is generated if the truck is outside the boundary. In some embodiments, the system controls display lights or images that show an indication that the truck is properly seated and/or improperly seated that are visible to both the driver and the facility personnel. In some embodiments, the system generates an alarm when a loading operation is initiated. In some embodiments, the system is trained to recognize loading operations using the camera and AI of the system. In some embodiments, if truck 901 is outside boundary 902, the system prevents truck loading operations.

Fig. 10 illustrates the use of the system to ensure proper loading of a truck 1000, according to some embodiments. In some embodiments, the system monitors area 1003 using camera 1001 to determine when the level of material 1004 reaches a certain height. In some embodiments, the system provides an alarm and/or alert when the level of material 1004 reaches a certain height. In some embodiments, the system stops the hopper 1007 when the level of the material 1004 reaches a certain height 1004. In some embodiments, when the level of material 1004 reaches a certain height 1004, a different hopper 1008 (or any hopper) begins the loading operation. In some embodiments, all of the hoppers are running simultaneously, and the system stops the loading operation for each respective hopper when the respective area below the hopper accumulates a pre-trained material level.

Fig. 11 illustrates a camera feed using the system to control a truck loading operation 1100, according to some embodiments. In some embodiments, there are three hoppers 1101, 1102, and 1103 that the system has been trained to recognize. In some embodiments, the system outlines each hopper and/or monitored area with a box (or any shape) on the camera feed so that the user can verify that the system identifies the hopper and/or monitored area. In some embodiments, the system provides an alarm when the stockpile reaches the hopper, as shown in conditional 1106. In some embodiments, as shown in conditional 1105, the system issues an alarm and/or alert when the windrow reaches the side of the truck and/or approaches the hopper. In some embodiments, when conditions 1105 and/or 1106 occur, the system starts and/or stops the hopper. In some embodiments, the system may monitor the stockpile 1104 from the hopper 1103 and apply the same rules as the other hoppers 1104.

FIG. 12 illustrates one or more programs that the system may be loaded with and/or connected to, in accordance with some embodiments. In some embodiments, the system may be configured to model and monitor one or more process parameters in which data is recorded as tags. In some embodiments, the system may be loaded onto one or more platforms 1201, 1202, 1203. In some embodiments of the present invention, the,the one or more platforms include any software that monitors one or more camera feeds and/or can access one or more system tags from one or more real-time sources and/or databases. In some embodiments, the one or more platforms comprise And/orThey are allA trademark of a subsidiary and/or subsidiary company thereof.

FIG. 13 illustrates an interface for implementing the system, according to some embodiments. In some embodiments, the system provides a welcome page 1300. In some embodiments, the welcome page 1300 and/or one or more other displays provided by the system are provided through a conventional browser. In some embodiments, the home page 1300 and/or one or more other displays provided by the system are provided through a system browser. In some embodiments, the terms "browser," "window," and/or "display" refer to a conventional browser and/or a system-provided browser. In some embodiments, the term "page" refers to a browser and/or display showing system information. In some embodiments, the browser includes a home button 1301, a title portion 1302, a welcome page link 1303, a browser close button 1304, a start button 1307, a link 1308 to online help, blogs, and/or instructional videos, and/or a link 1309 to social media. In some embodiments, the welcome page 1300 includes a welcome message 1305 and/or a program description 1306.

FIG. 14 illustrates a browser page used to initiate the modeling process 1400, in accordance with some embodiments. In some embodiments, the system provides condition detection and future condition planning and/or prediction using real-time data streams while accounting for low latency requirements of operations. In some embodiments, through a system connected to one or more monitoring platforms, the system automatically detects one or more historian databases and/or runtime data sources 1401 and displays them in data source portion 1402. In some embodiments, the system automatically connects to one or more historian databases and/or runtime data sources 1401. In some embodiments, a user manually connects one or more historian databases and/or runtime data sources 1401 to the system. In some embodiments, a user can add one or more historian databases and/or runtime data sources using add button 1403. In some embodiments, the system indicates in model portion 1406 that there is no model 1404 present and/or provides information about modeling process 1405. In some embodiments, the user may initiate the modeling process by selecting the create model button 1407. In some embodiments, the system provides a link to import the sample model 1408 and/or request help 1409.

FIG. 15 illustrates a model description page 1500 in accordance with some embodiments. In some embodiments, after selecting create model button 1407, the user is directed to model description page 1500. In some embodiments, model description page 1501 includes a header portion 1501 and/or a name and description portion 1502. In some embodiments, the model description page 1500 includes links 1503 1508 to each page used in the model creation process. In some embodiments, the pages used in the model creation process include name and description 1503, features 1504, variables 1505, step 1506, high levels 1507 (which also include predicted pages described later), and/or browsing and creation 1508. In some embodiments, one or more links 1503 and 1508 are displayed on each page during the model creation process. In some embodiments, the name and description portion 1502 includes a name input portion 1509, a description input portion 1510, a creator input portion 1511, a creation time input portion 1512, a last modifier input portion 1513, and/or a last modification time input portion 1514. In some embodiments, the system provides a cancel button 1515, a return button 1516, and/or a next button 1517. In some embodiments, the system provides a breadcrumb and/or page selection icon 1518 that allows selection of different model creation pages.

FIG. 16 shows a target page 1600 of the model creation process, in accordance with some embodiments. In some embodiments, destination page 1600 includes name 1601 entered in name portion 1509 of the previous page. In some embodiments, the goal page prompts the user to consider goals of the model according to desired or undesired conditions 1602. In some embodiments, once the user understands the goal of the model, the user may begin searching 1603 for tags associated with achieving the goal.

FIG. 17 shows target page 1700 after the user has entered search terms in variable search 1603, according to some embodiments. In some embodiments, a user may enter tags and/or process descriptions into the variable search 1701 to search for tags that contain and/or are associated with descriptive names. In some embodiments, the located one or more tags may be added to the feature tag list 1702. In some embodiments, the tag list 1702 includes portions for one or more of a tag name 1703, a description 1704, a min-max value 1705, a database location 1706, and/or a real-time data source 1707. In some embodiments, after the user selects all tags that meet the goal, tags may be added to the model by selecting add button 1707.

FIG. 18 shows destination page 1800 after the user has selected add button 1707, according to some embodiments. In some embodiments, the target page 1800 includes a toggle 1801 for closing and opening tab conditions 1802 and 1805 (similar toggles represented by the basic shape are used across multiple pages). In some embodiments, the tag conditions include a tag name portion 1806, a conditional statement portion 1807, and a condition values portion 1808 for setting alarms and/or reminders. In some embodiments, the system provides an additional conditions section 1809 that allows the user to select to alert/remind when any or all of the conditions 1802 and 1805 are satisfied ("alert/remind" refers to any notification supported by the system, as described in this disclosure). In some embodiments, each tag condition may be configured by a user as a parameter used by the tag. In some embodiments, the system automatically selects the appropriate conditional statement-based parameters used by the tag. For example, in some embodiments, tag condition 1802 is based on a length parameter, and provides an alarm when the length is not between 6-8 millimeters (set in section 1808) (set in section 1807). In some embodiments, the exemplary tag condition 1803 is based on a width parameter, and when the width is greater than 60 millimeters (set in portion 1807) (set in portion 1808), the condition provides an alarm. In some embodiments, the exemplary tag condition 1803 is based on the value of one tag being equal to (set in portion 1807) the value of another tag (set in portion 1808). In some embodiments, exemplary tag condition 1805 is based on the alarm tag containing (portion 1807) a true value (portion 1808) indicating that the alarm is active. In some embodiments, the one or more conditions are conditions that the system AI uses for decision making when monitoring the process. In some embodiments, any condition may be set for any system tag.

FIG. 19 illustrates a feature page 1900 according to some embodiments. In some embodiments, the features page 1900 includes additional tabs based on one or more previous user-selected tabs on the target page 1700. In some embodiments, the feature page is automatically populated with tags associated with each user-selected tag. In some embodiments, automatic tag selection is based on relevance analysis performed by the system. In some embodiments, automatic tag selection is based on attribute mappings created manually and/or by the system using AI. In some embodiments, the user may add additional tags to the variable tag list 1901 using the variable search 1902. In some embodiments, the system monitors and provides analysis and countermeasures as additional information to the alarm, as previously described and/or in the embodiments presented below.

FIG. 20 illustrates a model creation step page 2000, according to some embodiments. In some embodiments, the steps page 2000 includes a description portion 2001, the description portion 2001 instructing the user how to decompose the process data 2002 into process steps 2003-. In some embodiments, process step 2003 may be a startup period. In some embodiments, process step 2004 may be an initialization period step. In some embodiments, process step 2005 can be a steady state step. In some embodiments, once steps are marked in the model, the system may use data and/or images created from these steps to identify corresponding steps throughout the marked and/or unmarked other tags (i.e., a repeating pattern may be marked once and automatically applied to each occurrence). In some embodiments, the system uses AI to associate steps (or sub-steps) of the tag with other data in the same process and/or a different process to generate an alarm/alert when an abnormal condition is detected. For example, the system may associate a product width parameter with data from an extruder temperature tag initialization step (where such relationship was previously unknown) and provide the new relationship in the information section of the alarm/reminder.

FIG. 21 shows adding steps to a model on a step page 2100, in accordance with some embodiments. In some embodiments, the user may add a step by selecting the add step button 2101. In some embodiments, the user is presented with one or more portions to add the step name 2102 and/or description 2103. For example, according to some embodiments, the step name 2102 may be "initialize" and/or the description 2103 may state "during initialization, most motors start and give erroneous and changing signals that should be modeled separately". In some embodiments, step page 2100 includes inputs for establishing step base 2104, step actions 2105, and/or "any/all" conditions 2106. In some embodiments, the step page 2100 includes a condition 2107 that includes a toggle switch, an additional feature search 2108, and/or a save step button 2109. In some embodiments, the system uses the step name 2102 and description 2103 to tag the current and/or different processes that match the data and/or image values associated with the step. In some embodiments, the step foundation 2104 defines what type of data is input into the model (e.g., label data or image data). In some embodiments, condition 2107 includes a tag name, a condition operator (e.g., "equal"), and a trigger value (e.g., "false"), similar to those discussed above. In some embodiments, step action portion 2105 may be used to mark a step as substep 2010 when a condition is satisfied. In some embodiments, when creating the model, the system excludes the time range defined by substep 2010. In some embodiments, when condition 2107 is not satisfied, the time range defined by tag condition 2107 is included in the model. In some embodiments, data from the sub-steps is excluded from the main model and stored in a database for use during system analysis and/or in a different model. In some embodiments, when condition 2107 is satisfied, step action portion 2105 includes a selectable ignore step 2011 option. In some embodiments, the ignore step 2011 excludes the conditional 2107 data from the model. In some embodiments, the system uses the time range for which the condition 2107 is satisfied and marks the corresponding time range of another tag with the step name 2102 (i.e., the time range of the condition tag 2107 is used to mark one or more tags from the feature list 1702 and/or the variable list 1901).

FIG. 22 shows an example 2200 of creating additional steps for a master model, according to some embodiments. In some embodiments, the browser is similar to step page 2100. In some embodiments, the previously created steps are listed in step section 2201. In some embodiments, a step may be defined by a plurality of conditions 2202 and 2203. For example, the period of time of the main model may be identified by the rpm of the extruder screw motor speed and/or by the actual value of the water pump tag (e.g., flow rate, amperage, etc.) that is a certain percentage of the set point. In some embodiments, when both conditions are satisfied, the model is configured to ignore step 2204.

FIG. 23 depicts step 2300 of using the system to define running different types of products, according to some embodiments. In some embodiments, the equipment used to produce the product in the master model is the same equipment used to produce a different product. In some embodiments, the system allows a time period for the production of another product to be flagged as a sub-step and/or ignored. For example, the first condition 2302 can be when the extruder start time is less than a certain time. In some embodiments, the second condition 2303 may be when another component, such as a roller, is not operating. In some embodiments, when any/all condition 2301 is selected as "all," the system creates a sub-step in the master model (the sub-step is not used in the master model, but is still used to identify tag features, and is then saved in the database) and/or ignores the time period, the sub-step, and/or the sub-step,

FIG. 24 illustrates a step page 2400 for excluding certain time periods, in accordance with some embodiments. In some embodiments, the particular time period is a maintenance time period. In some embodiments, the first condition 2401 may be for setting a start time for exclusion (e.g., greater than a certain date). In some embodiments, the second condition 2402 may be used to set an end time for time period exclusion (e.g., less than a certain date).

FIG. 25 illustrates a prediction page 2500 according to some embodiments. In some embodiments, the page is predicted. In some embodiments, the prediction page (labeled advanced in some embodiments) allows a user to configure how and/or when predictions are displayed. In some embodiments, the prediction page includes a date and/or time selection 2501 of "begin reading data". In some embodiments, prediction page 2500 includes a preview button 2502 to preview the model and/or perform model training (using AI) by selecting a number 2503 for a time type 2504 (e.g., day, hour, minute) of data. For example, according to some embodiments, time and/or date selection 2501 may be 4 months prior to the current date. In some embodiments, the number 2503 is set to 10 and the time type 2504 is set to days. In some embodiments, the values in number 2503 and time type 2504 define the amount of data used to train and/or preview the model.

FIG. 26 illustrates prediction page 2600 after selection of preview model button 2502 now, in accordance with some embodiments. In some embodiments, prediction page 2600 includes a feature preview 2601 and a variable preview 2602. In some embodiments, the feature preview 2601 includes information from the tags listed in the feature list 1702. In some embodiments, the variable preview includes information from the variable list 1901. In some embodiments, after a model is created, the model may be verified using the verify model button 2603.

Fig. 27 shows a prediction page 2700 after the verification model button 2603 is selected, according to some embodiments. In some embodiments, the system marks the label information (e.g., a micro-line plot) with one or more error icons 2701 at the location and/or time associated with the error. In some embodiments, the system tags the label information with one or more warning icons 2702. In some embodiments, the system provides information 2703 in the browser describing the number of errors, warnings, and/or information messages. In some embodiments, by selecting the continue verification button 2704, details of errors, warnings, and/or information messages can be viewed.

FIG. 28 illustrates prediction page 2800 after the continue verification button 2704 is selected, in accordance with some embodiments. In some embodiments, prediction page 2800 includes message portion 2801, details portion 2802, and suggested actions portion 2803. In some embodiments, message selection 2801 allows a user to select each of the error, warning, and/or information messages that the system reports on prediction page 2700. For example, in some embodiments, error 2804 is selected for browsing. In some embodiments, the system provides a detailed description of the error in detail block 2802. In some embodiments, the system provides countermeasures against errors in a recommendation action portion 2803. In some embodiments, the details and/or suggested actions are the product of manual data entry and/or one or more of AI analysis using any of the techniques described in this disclosure. For example, according to some embodiments, the system may report in details section 2802 that one or more data sources are not connectable and suggest to the user to use the suggested software to verify the connection and/or update the credentials.

FIG. 29 shows a prediction page 2900 in which the user has selected "Warning" in message portion 2901, according to some embodiments. In some embodiments, message portion 2901, details portion 2902, and suggested actions portion 2903 present a similar type of information (except specific to alerts) as the corresponding partial error portion in prediction page 2800. For example, detail section 2902 may display information that states that a particular variable is not associated with and/or is not related to the target (i.e., the tag in feature list 1702). In some embodiments, suggested actions section 2903 may suggest to the user to delete the variable, view the variable later, and/or retain the variable if it is determined that the tag may be filled with relevant data at some other time.

Fig. 30 shows a prediction page where the user has selected "info" in the message portion 3001, according to some embodiments. In some embodiments, message portion 3001, detail portion 3002, and suggested action portion 3003 present a similar type of information (except that specific to the information) as the corresponding "alarm" portion in prediction page 2800. For example, according to some embodiments, detail section 3002 for information selection 3001 may include a list of variables that define steps where no data is to be omitted (e.g., a flat line (flatline) diagram). In some embodiments, as a non-limiting example, the system may suggest modification steps and/or define different time periods in the suggest actions portion 3003.

Fig. 31 illustrates a prediction page 3100 in which a user can configure notification preferences for the manner in which information is displayed for the system, according to some embodiments. In some embodiments, notification preferences 3101 allow the user to select the more frequent 3102 option using preference button 3103. In some embodiments, more frequent option 3102 configures the system to notify the user by an alarm/reminder before the time set in time block 3104 when the predicted trend or value will exceed the limit. For example, the system may display an alarm/reminder two hours before the limit is expected to be reached. In some embodiments, selecting more frequent options may be less accurate because the predicted values last for a longer period of time. In some embodiments, more frequent settings give the user more time to react.

Fig. 32 shows a prediction page 3200 in which less frequent but more accurate preferences are selected. In some embodiments, notification preferences 3201 allow the user to select less frequent 3202 options using preference buttons 3203. In some embodiments, less frequent option 3102 configures the system to notify the user by an alarm/reminder before the time set in time block 3204 (less time than in 3104) when the predicted trend or value exceeds the limit. For example, the system may display an alarm/reminder one hour before the limit is expected to be reached. In some embodiments, selecting the less frequent option is more accurate because the prediction value used is closer to the limit of the tag. In some embodiments, the less frequent setting gives the user less time to react.

FIG. 33 shows a prediction page 3300 with some results of predicted values versus actual values for the main model, according to some embodiments. In some embodiments, the system presents a display 3301 (e.g., a bar graph, pie chart, etc.) that shows the predicted value 3303 of the trend prediction at a specified time against the actual value 3302 of the trend prediction at the same specified time, display 3301. In some embodiments, each actual value 3302 and predicted value 3303 on display 3301 is associated with a different target (i.e., one tag from feature tag list 1702). In some embodiments, each actual value 3302 and predicted value 3303 on display 3301 is associated with a different goal. In some embodiments, each actual 3302 and predicted 3303 value on display 3301 is associated with a mixture of the same and different targets (e.g., two bar portions are associated with one label and the other three bar portions are each associated with a different label). In some embodiments, each actual value 3302 and predicted value 3303 on display 3301 is associated with the same and/or different tags from variable tag list 1901. In some embodiments, each actual value 3302 and predicted value 3303 on display 3301 is associated with any possible combination of labels from feature label list 1702 and/or variable label list 1901. In some embodiments, display 3301 shows the predicted likelihood of occurrence in percent versus time. In some embodiments, the system displays a notification and/or an alarm/reminder when the probability of occurrence reaches a certain percentage (e.g., 80%).

Figure 34 represents a prediction page 3400 in which a user has selected 3401 a portion of a display 3402 to receive details about a modeled result, according to some embodiments. In some embodiments, the details include a summary section 3403. In some embodiments, summary section 3403 includes the time and/or date at which the notification was sent, a list of tags associated with selection 3401, the value of each tag at the predicted time, and/or the value of each tag at the actual time. In some embodiments, the analysis portion 3404 displays one or more possible root causes of the alarm (using any of the system tools described in this disclosure). In some embodiments, the suggestion portion 3405 displays one or more suggested corrective actions for the alert (using any of the system tools described in this disclosure).

FIG. 35 illustrates a browse and create page 3500 in accordance with some embodiments. In some embodiments, after the user is satisfied with the results of the model verification, the user may select the create button 3501 that completes the model creation process and begin running the model using the real-time production values.

FIG. 36 illustrates a model page 3600 with all created models 3601-3603 according to some embodiments. In some embodiments, model page 3600 is the same as or similar to page 1400. In some embodiments, the model page 3600 includes a model list 3601 that lists all created models 3602-3604, an information section 3605 that lists all information associated with a model selected from the model list 3601, and/or a data source section 3606 that lists all available data sources for the created model. In some embodiments, the model list 3601 may include a model run status icon 3613 and/or a notification icon 3614. In some embodiments, information portion 3605 may include one or more of a running status, a number of notifications, a number of errors, a number of alerts, a number of information messages, and/or any other information deemed relevant by a user and/or system. In some embodiments, the information portion may include an alert summary 3607, a chart (e.g., a micro-line graph) 3608, alert details 3609, associated tag analysis 3610 (e.g., an analysis by the system of tags in the variable tag list 1901 or any other tags that the system determines are relevant to the alert), suggested actions portion 3611, and/or any other information that the user and/or system deems relevant. In some embodiments, by selecting detail button 3612, more and/or all of the details associated with the alarm may be viewed.

As a non-limiting example, the extrusion process model 3602 predicts with 80% certainty that a limit associated with a label (e.g., a label listed in the alert summary 3607) will be violated within 52 minutes (as shown in the alert details 3609). In some embodiments, the system shows that the cooling zone stops at 25 ℃ (in section 3610) when the pressure increases. In some embodiments, the system suggests increasing the water flow to the cooling zone to 4.5gpm and continuing to monitor to ensure that the cooling zone temperature drops below 25 ℃.

In some embodiments, a manufacturing facility monitors remote equipment using one or more HMIs (human machine interfaces) displayed on one or more GUIs (graphical user interfaces). In some embodiments, a SCADA (supervisory control and data acquisition) system is used for remote monitoring. In some embodiments, the SCADA system components include one or more of a monitoring computer, a remote terminal unit, a programmable logic controller, a communication infrastructure, and/or a human machine interface. In some embodiments, the SCADA system provides monitoring and command execution (e.g., changing set points, controlling scheduling, etc.). In some embodiments, the system uses a conventional SCADA system also known as an RTU (remote terminal unit). In some embodiments, the system is incorporated byIn the SCADA system provided.

In some embodiments, the facility has various feeds that help monitor the remote process. In some embodiments, the feed includes digital information provided by conventional lens cameras, infrared cameras, digital cameras, visualization software (e.g., on an electron microscope that converts electronic signals and/or electromagnetic waves into visual images), and/or video recording software, among others. The term "camera" as used herein encompasses any of the above items and any conventional visualization hardware and/or software. As used herein, "alarm," "alert," "alarm/alert," and/or "notification" includes any information that the system is capable of providing, such as, but not limited to, past trends, future predictions, historical data, maintenance data, root cause analysis, equipment mapping, associations between alarms and secondary equipment, AI training interfaces, and/or any other method disclosed herein. In some embodiments, the facility has various manual visual inspections that need to be performed. In some embodiments, the manual visual inspection of the component includes instrumentation, lights, component movement, component color, size, shape, depth, vibration, and/or any other physical property that may be classified as a visual characteristic. In some embodiments, the system monitors the process using a conventional audio collector (e.g., a microphone) and the data collected therewith. In some embodiments, the system uses stress-strain gauges (e.g., wheatstone bridges). In some embodiments, the system uses images from the feed to transform one or more manual checkpoint monitoring components into a digital representation on the SCADA HMI. In some embodiments, the system facilitates capturing and analyzing monitoring data for integration into a SCADA system.

FIG. 37 illustrates the transformation of an image from remote manual visual inspection station 3700 to SCADA 3710 according to some embodiments. The remote human vision station 3730 may include lights 3701, meters 3702, vents 3703 with fan letters 3704 (e.g., small tape or paper that moves with air coming out of the vents indicating that the fan is running), an oscillating chart 3705, gears 3706, and/or levers 3707. For example, by using a camera, the system can be trained to recognize both normal and abnormal configurations for each of these items. In some embodiments, the system compares the expected value of the light 3701 with the actual value obtained by the camera feed. In some embodiments, the comparison is specific to the product or operating condition. In some embodiments, the system checks certain tag and/or system setting configurations and determines what products are running and/or the expected light patterns associated with those products. In some embodiments, the system will use a video camera to compare the current state of the lamp 3701 with expected conditions and return an alarm if the system determines that the lamp 3701 is in an abnormal state. In some embodiments, the system uses AI in the comparison. The system details for training an AI to accomplish these types of tasks will be described later with reference to some embodiments.

Similarly, in some embodiments, the camera of the visual monitoring meter 3702 may send a digital representation to the system, which then converts it to a digital value. According to some embodiments, the system is configured and arranged to convert the camera feed to a digital representation continuously, intermittently, or as the position of the meter 3702 changes. In some embodiments, the system is configured to compare the last received image with the current image and only upload changes between the two images to a database, such as a historian database, for storage and/or analysis. In some embodiments, by storing only changes in one or more process component images, substantial memory capacity is saved.

In some embodiments, a remote assembly requiring vents 3703 is visually monitored using fan hyacinth 3704 (e.g., beaten paper, lit LEDs, rotating veils (veins), and/or other conventional techniques) to ensure that the fan is running and providing proper cooling. In some embodiments, the components do not use fan hyacinth, but rather have sensors that send information to SCADA 3710. In some embodiments, the system is configured to receive a video feed from a camera and store the feed as a video clip. In some embodiments, the system uses a camera to take pictures of the fan hyacinth 3704 at random time intervals. In some embodiments, the training system interprets changes in the photograph as an indication of normal conditions. In some embodiments, the system may be trained to interpret no change in the photograph as an abnormal condition. In some embodiments, the training system identifies motion and/or changes in photographs in the video segment as normal conditions. In some embodiments, the system uses the training to identify abnormal fan hyacinth 3704 conditions, such as when no movement of the vent hyacinth 3704 occurs. In some embodiments, the system reports an abnormal condition to SCADA 3710 in the form of an alarm.

In some embodiments, the system uses a camera to monitor local electronic equipment, such as oscilloscope 3705. In some embodiments, remote electronic equipment such as oscilloscope 3705 does not send digital information to SCADA 3710, but rather the system is used to send visual data for display and analysis. In some embodiments, the remote electronic equipment does transmit numerical information to SCAD A3710, and the system serves as redundancy to ensure that the content displayed at SCADA 3710 is the same as the content displayed at remote monitoring station 3700. In some embodiments, this redundancy may be applied to any electronic equipment that displays a visual representation and/or reports signal data, so that the system can quickly detect errors or loss of communication and report in the form of an alarm. In some embodiments, this feature may also be desirable for meters 3702 (and/or any analog devices) that may have a stuck and/or damaged display that are otherwise reporting correctly, in which case the system reports an alarm.

In some embodiments, as a non-limiting example, the system monitors process hardware such as gear 3706. In some embodiments, the system may monitor and record the motion of gear 3706 as a video segment and compare the current segment to the reference segment as described above. In some embodiments, the system monitors one or more components, such as the gear 3706, by taking pictures intermittently or periodically. In some embodiments, the video and/or photographs may be compared to normal reference photographs stored during training and/or maintenance so that the system may determine whether a physical component of the hardware is damaged (e.g., a tooth on a gear is missing). In some embodiments, the system may predict how a defect of a physical component will affect the operation of the component, as well as the operation of any other components in the facility that are associated with the operation of the physical component. In some embodiments, the system may use the change in the physical component to correlate other unexpected exceptions in the process. For example, in some embodiments, gear 3706 controls the operation of levers 3707, 3708 when remote station 3730 receives a signal from SCADA 1110, in accordance with some embodiments. In some embodiments, a broken tooth on the gear may cause the first lever 1107 to lift as intended, but the lever 1107 lifts only half way. In some embodiments, a system monitoring both levers 3707, 3708 and gear 3706 associates a lever anomaly with a gear anomaly and reports the association with an alarm. In some embodiments, the system can use a combination of visual data and electrically collected data to perform this type of correlation analysis.

In some embodiments, the alarm is displayed on SCADA 3710. In some embodiments, SCADA 3710 includes one or more monitors 3711, televisions 3712, clients 3713, interfaces 3714 (e.g., keyboard, mouse, handles (pads), etc.), computers 3715, and/or remote displays (not shown but described below). One or more SCADA components may be centrally located, distributed over an on-site facility, embodied in a mobile computer, and/or located off-site while remaining within the scope of the present disclosure.

In some embodiments, as shown in fig. 37, information from cameras 3721 is sent to system 3722 for processing and analysis as described herein before being sent to SCADA system 3723. In some embodiments, the system can automate the manual visual inspection process using and leveraging existing low cost camera streams. In some embodiments, the system uses data from the camera 3721 stream to train the AI 3722 monitoring process and associate all visual data and analysis from a particular component with a corresponding component tag within the SCADA system 3723. In some embodiments, the system trains the AI using data from existing component tags (e.g., control limits, regulatory limits, current trends, historical trends, maintenance records, etc.) as input and determines relevant information to be displayed to the user along with the alert.

Fig. 38 illustrates a system for automating a quality control inspection 3800 for cans, in accordance with some embodiments. In some embodiments, the camera 3801 monitors defect checkpoints and processes the images using AI to determine if a can is defective. In some embodiments, cans 3802 that are not defective are systematically categorized as eligible 3803. In some embodiments, defective cans 3804 having defects 3806 are classified as failing by the system. Using the system in this manner, according to some embodiments, production speed can be significantly increased because the system does not need to slow down the conveyor and/or create bottlenecks for inspecting the cans. In some embodiments, the system improves quality assurance by checking each can produced, rather than drawing only a sample of the can, as is common in current manufacturing. Additionally, in some embodiments, personnel costs may be reduced because the system may inspect the canisters at a higher rate and accuracy than if multiple people were working together. In some embodiments, the system may be trained to associate a particular defect 3806 with one or more tags in the SCADA system to supplement the alarm information and reports described herein.

Fig. 39 depicts a training interface 3900 for training a system AI for can defect monitoring, in accordance with some embodiments. In some embodiments, the training interface is embedded in and/or is part of the SCADA or other HMI included with the system. In some embodiments, the training process begins with the user creating a profile name 3901 and then selecting an update profile button 3902. In some embodiments, this will result in model configuration portion 3903 being present. In some embodiments, model configuration portion 3903 includes one or more inputs regarding name 3904, type 3905, migration model 3906, generational threshold 3907, category 0 name 3908, category 1 name 3909, category 0 threshold 3910, category 1 threshold 3911, lock threshold selection 3912, and/or save button 3913.

In some embodiments, the name 3904 is used to identify the AI profile created using the confirmation part 3903. In some embodiments, type 3905 defines the classification rules that the AI uses to assign to each image. In some embodiments, as shown in exemplary FIG. 39, the type is selected as a binary classifier (i.e., binomial classification). In some embodiments, the binary classifier groups the images into one of two groups (e.g., defective, non-defective). In some embodiments, as type 3905, a multi-class classification may be selected. In some embodiments, multiclass classification classifies images into groups using a combination of binary classifiers.

In some embodiments, the migration model 3906 may be selected to import previously trained AI models. In some embodiments, the imported AI model may have been used for similar analysis. In some embodiments, the imported AI models may have been used for the same analysis at different locations or facilities. For example, in some embodiments, multiple can shapes are being produced at the same factory. In some embodiments, defects found in various can shapes are similar, such as defect 3806. In some embodiments, the AI of the system may learn to identify defects in different products from previous defect classifications for one product. In some embodiments, importing an AI model using the migration model 3905 may significantly improve the AI training process by reducing the amount of manual feedback required for the new model; manual training is discussed further below.

In some embodiments, model configuration 3903 involves setting a generation threshold 3907. In some embodiments, the generation-defined learning algorithm (i.e., AI) will traverse the number of iterations of the training sample. In some embodiments, the system provides input for dividing the sample size into a plurality of batches, wherein the model weights are updated after each batch. In some embodiments, the batch type includes a batch gradient descent, a random gradient descent, and/or a mini-batch gradient descent, as non-limiting examples. In some embodiments, the generation threshold 3907 determines the number of generations that will be stopped from training later if the verification loss does not improve. In some embodiments, category 0 name 3908 and category 1 name 3909 are used to name each group (e.g., defective, non-defective) created when type 3905 is selected. In some embodiments, the model configuration is saved by selecting a save button 3913.

FIG. 40 illustrates a training interface 4000 after saving a model configuration, according to some embodiments. In some embodiments, the system saves the information entered into the model configuration portion 3903 as the AI profile 4001. In some embodiments, selection of the configuration button 4002 allows a user to modify one or more model configuration parameters. In some embodiments, new button 4003 allows the user to create a new AI profile. In some embodiments, the training interface 4000 includes a status indicator 4004. In some embodiments, the status indicator indicates whether the model has been trained. In some embodiments, training interface 4000 includes tabs 4006, 4007, and/or 4008 that display images from defect checkpoints and/or locations in the production line. In some embodiments, the unclassified tab 4005 shows unclassified images from a camera feed. In some embodiments, the image appears on an unclassified tab because classification using AI has not been applied to the image. In some embodiments, the unclassified images in unclassified tab 4005 are used to train the AI model.

In some embodiments, to begin training the AI model, the training checkbox 4011 is selected. In some embodiments, one or more images (e.g., 4008, 4009) are then manually selected from the unclassified tabs and classified (i.e., flagged as defective or non-defective) using one of the classification buttons 4012, 4013, 4015. In some embodiments, the sort buttons are unsorted 4012, qualified 4013, and/or unqualified 4015 buttons. In some embodiments, when one or more images are selected and the eligible button 4013 is selected, the one or more images are moved and/or copied from the unclassified tab 4005 to the eligible tab 4006. In some embodiments, when one or more images are selected and the eligible button 4014 is selected, the one or more images are moved and/or copied from the unclassified tab 4005 to the ineligible tab 4007. In some embodiments, the system trains the AI using manual classification.

In some embodiments, the system uses one or more of a training set, a validation set, and/or a test set during training, tuning, model parts, and/or testing. In some embodiments, most of the images used for training are assigned to the training set. In some embodiments, the percentage of images assigned to the training set is between 40% and 80%. In some embodiments, the training set is used to fit parameters for the process of adjusting weights. In some embodiments, a few images for training are assigned to the validation set.

In some embodiments, the percentage of images assigned to the validation set is between 10% and 30%. In some embodiments, the validation set is an intermediate stage in AI training for selecting the best model and/or optimizing the model. In some embodiments, a portion of the images used for training are assigned to the test set.

In some embodiments, the test set includes manually classified images and is used for result testing and final model performance evaluation.

In some embodiments, the system uses a loss function to optimize the training process. In some embodiments, the training set and the validation set are used to calculate the loss based on how well the model uses the data from both sets. In some embodiments, the loss is the sum of the errors that occurred for each sample in the training set or validation set. In some embodiments, the loss represents the degree to which the model performs desirably or undesirably after each generational iteration.

In some embodiments, the system uses the accuracy index to interpret the performance of the AI model. In some embodiments, the accuracy rate represents a ratio of the number of correct predictions to the total number of predictions. In some embodiments, accuracy is used to measure the prediction of the model compared to the real data.

In some embodiments, the system creates and/or tests the AI model using conventional algorithms and/or techniques. In some embodiments, the system uses proprietary algorithms and/or techniques to create and/or test the AI model.

Fig. 41 illustrates a training interface 4100 when training an AI model, according to some embodiments. In some embodiments, once the images are classified, the model may be trained by selecting the start training button 4101. In some embodiments, during training, the system displays a loss map 4102, the loss map 4102 displays a training loss line 4103 and a validation loss line 4104. In some embodiments, during training, the system displays an accuracy map 4105, the accuracy map 4105 displays a training accuracy line 4106 and a validation accuracy line 4107. In some embodiments, the system displays a generation progress bar 4108 that is populated during each generation. In some embodiments, the loss value and/or accuracy value is also displayed in the AI profile box 4109 and/or the model box 4110. In some embodiments, state 4111 indicates that training is in progress.

Fig. 42 illustrates a snapshot 4200 of an AI model run in accordance with some embodiments. In some embodiments, once training is complete, the AI model may monitor for a start by selecting start/stop button 4201 and not selecting training box 4202 to monitor for a feed. In some embodiments, state 4203 indicates that AI image classification is running. In some embodiments, image feed 4204 is displayed by the system. In some embodiments, the outline 4205 of the image in the image feed 4204 is different for pass and fail images. In some embodiments, image feed 4204 is color-coded (e.g., green is passed and red is not passed).

FIG. 43 illustrates manual classification of misclassified images 4300, according to some embodiments. In some embodiments, before, after, and/or during an image classification run, a user may click on the eligible tab 4301 and/or the ineligible tab 4302 to view the classified images. In some embodiments, if one or more images are misclassified, the user may reclassify the images using the unclassified button 4304, the qualified button 4305, and/or the unqualified button 4306. In some embodiments, when the user manually re-classifies the images, the manual classification is used to further train the AI model. In some embodiments, the selected image 4303 is magnified 4307 over another portion of the display.

In some embodiments, the same process as described above for classifying defects is also used to train AIs in any of the embodiments presented in this disclosure. In some embodiments, the same process for classifying defects as described above may be used to train an AI model for any application not disclosed herein.

Some embodiments may comprise a special purpose computer including various computer hardware, as described in greater detail below. Some embodiments within the scope of the present disclosure may also include computer-readable media for carrying or having computer-executable instructions or data structures stored thereon. In some embodiments, such computer-readable media can be any available media that can be accessed by a special purpose computer. By way of example, and not limitation, such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to carry or store desired program code means in the form of computer-executable instructions or data structures and which can be accessed by a general purpose or special purpose computer, according to some embodiments. According to some embodiments, when information is transferred or provided over a network or another communications connection (either hardwired, wireless, or a combination of hardwired or wireless) to a computer, the computer properly views the connection as a computer-readable medium. Thus, in some embodiments, any such connection is properly termed a computer-readable medium and/or a processor-readable medium. Combinations of the above should also be included within the scope of computer-readable media in some embodiments.

In some embodiments, computer-executable instructions comprise, for example, instructions and data which cause a general purpose computer, special purpose computer, or special purpose processor to perform a certain function or group of functions.

Some embodiments include a system for implementing various aspects of the disclosure, including a special purpose computer in the form of a conventional computer, including a processing unit, a system memory, and a system bus that couples various system components including the system memory to the processing unit.

In some embodiments, the system bus may be any of several types of bus structures including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures. In some embodiments, the system memory includes Read Only Memory (ROM) and Random Access Memory (RAM). In addition, some embodiments include a basic input/output system (BIOS), which can be stored in ROM containing the basic routines that help to transfer information between elements within the computer, such as during start-up. Further, in some embodiments, the computer may comprise any computer (e.g., processor, desktop computer, laptop computer, tablet computer, PDA, cellular telephone, mobile telephone, smart television, etc.) capable of receiving or sending IP addresses wirelessly to and from the internet.

In some embodiments, the computer may also include a magnetic hard disk drive for reading from and writing to a magnetic hard disk, a magnetic disk drive for reading from or writing to a removable magnetic disk, and an optical disk drive for reading from or writing to a removable optical disk such as a CD-ROM or other optical media. In some embodiments, the magnetic hard disk drive, magnetic disk drive, and optical disk drive can be connected to the system bus by a hard disk drive interface, a magnetic disk drive interface, and an optical drive interface, respectively. In some embodiments, the drives and their associated computer-readable media may provide nonvolatile storage of computer-executable instructions, data structures, program modules and other data for the computer. Although the exemplary environment described herein employs a magnetic hard disk, a removable magnetic disk and a removable optical disk, other types of computer readable media for storing data can be used according to some embodiments, including, but not limited to, magnetic tape cassettes, flash memory cards, digital video disks, Bernoulli cartridges, RAMs, ROMs, Solid State Drives (SSDs), and the like.

In some embodiments, a computer typically includes a variety of computer-readable media. In some embodiments, computer-readable media can be any available media that can be accessed by the computer and includes both volatile and nonvolatile media, removable and non-removable media. By way of example, and not limitation, in some embodiments computer readable media may comprise computer storage media and communication media. According to some embodiments, computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. In some embodiments, computer storage media is non-transitory and includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, SSDs, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be accessed by a computer for storage of desired non-transitory information. In some embodiments, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.

Some embodiments include program modules comprising program code that may be stored on the hard disk, magnetic disk, optical disk, ROM, and/or RAM, including an operating system, one or more application programs, other program modules, and program data. In some embodiments, a user may enter commands and information into the computer through a keyboard, pointing device, or other input devices, such as a microphone, joy stick, game pad, satellite dish, scanner, or the like. In some embodiments, these and other input devices are often connected to the processing unit through a serial port interface that is coupled to the system bus. In some embodiments, input devices may be connected by other interfaces, such as a parallel port, game port, or a Universal Serial Bus (USB). In some embodiments, a monitor or other display is also connected to the system bus via an interface, such as a video adapter. In addition to the monitor, in some embodiments, personal computers typically include other peripheral output devices (not shown), such as speakers and printers.

In some embodiments, one or more aspects of the present disclosure may be embodied in computer-executable (computer-readable) instructions (i.e., software), routines, or functions stored as application programs, program modules, and/or program data in system memory or in non-volatile memory. In some embodiments, the software may be stored remotely, such as on a remote computer having remote application programs. In some embodiments, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular data types when executed by a processor in a computer or other device. In some embodiments, the computer-executable instructions may be stored on one or more tangible, non-transitory computer-readable media (e.g., hard disks, optical disks, removable storage media, solid state memory, RAM, etc.) and executed by one or more processors or other devices (including any of the devices disclosed herein).

In some embodiments, the functionality of the program modules may be combined or distributed as desired. In some embodiments, the functions may be embodied in whole or in part in firmware or hardware equivalents such as integrated circuits, application specific integrated circuits, Field Programmable Gate Arrays (FPGAs), and the like. In addition, in some embodiments, the computer may operate in a networked environment using logical connections to one or more remote computers. In some embodiments, the remote computers may each be another personal computer, a tablet computer, a PDA, a server, a router, a network PC, a peer device or other common network node, and typically include many or all of the elements described above relative to the computer. In some embodiments, the logical connections include a Local Area Network (LAN) and a Wide Area Network (WAN) that are presented herein by way of example and not limitation. In some embodiments, such networking environments are commonplace in office-wide or enterprise-wide computer networks, intranets and the Internet.

In some embodiments, when used in a LAN networking environment, the computer can be connected to the local network through a network interface or adapter. According to some embodiments, when used in a WAN networking environment, the computer may include a modem, a wireless link, or other means for establishing communications over the wide area network, such as the Internet. In some embodiments, the modem, which may be internal or external, is connected to the system bus via the serial port interface. In some embodiments, in a networked environment, program modules depicted relative to the computer, or portions thereof, may be stored in the remote memory storage device. It will be appreciated that the network connections shown are exemplary and other means of establishing communications over a wide area network may be used in some embodiments.

In some embodiments, the computer-executable instructions are stored in a memory, such as a hard drive, and executed by the computer. Advantageously, in some embodiments, the computer processor has the capability to perform all operations (e.g., execute computer-executable instructions) in real time. In some embodiments, the order of execution or performance of the operations in embodiments of the disclosure shown and described herein is not essential, unless otherwise specified. That is, in some embodiments, operations may be performed in any order, unless otherwise specified, and embodiments of the disclosure may include more or less operations than those disclosed herein. For example, in some embodiments, it is contemplated that executing or performing a particular operation before, contemporaneously with, or after another operation is within the scope of aspects of the disclosure.

Some embodiments of the disclosure may be implemented with computer-executable (i.e., processor-executable, processor-readable) instructions. In some embodiments, the computer-executable instructions may be organized into one or more computer-executable components or modules. In some embodiments, various aspects of the disclosure may be implemented with any number and organization of such components or modules. For example, in some embodiments, aspects of the disclosure are not limited to the specific computer-executable instructions or the specific components or modules illustrated in the figures and described herein. Some embodiments of the present disclosure may include different computer-executable instructions or components having more or less functionality than illustrated and described herein.

For the purposes of this disclosure, the term "server" should be understood to refer, in some embodiments, to a service point that provides processing, databases, and communication facilities. In some embodiments, a computer may be capable of sending or receiving signals, such as via a wired or wireless network, or may be capable of processing or storing signals, such as in memory as a physical memory state, and may then function as a server. Thus, in some embodiments, a device capable of functioning as a server may include, for example, a dedicated rack-mounted server, a desktop computer, a laptop computer, a set-top box, an integrated device combining various features, such as two or more of the features of the devices described above, and so on. By way of example and not limitation, in some embodiments, the term "server" may refer to a single physical processor with associated communication and data storage and database facilities, or it may refer to a networked or clustered complex of processors and associated network and storage devices and operating software and one or more database systems and application software that support the services provided by the server. In some embodiments, the server may be configurable or capableThere are a number of variations, however, according to some embodiments, a server may generally include one or more central processing units and memory. In some embodiments, a server may also include one or more mass storage devices, one or more power supplies, one or more wired or wireless network interfaces, one or more input/output interfaces, or one or more operating systems, such asServer, Mac OS X, Unix, Linux, and/or any other conventional operating system.Andis a registered trademark of Microsoft Corporation, Redmond, Washington.

For purposes of this disclosure, for example, in some embodiments, "network" should be understood to refer to a network to which devices may be coupled such that communications may be exchanged between, for example, servers and clients, peer-to-peer communications, or other types of devices, including between wireless devices coupled via a wireless network. In some embodiments, for example, the network may also include mass storage devices such as a network attached storage device (NAS), a Storage Area Network (SAN), or other form of computer or machine readable media. In some embodiments, the network may include the internet, one or more Local Area Networks (LANs), one or more Wide Area Networks (WANs), wired type connections, wireless type connections, cellular, or any combination thereof. Also, in some embodiments, sub-networks that may employ different architectures or that may conform to or be compatible with different protocols may interoperate within a larger network. In some embodiments, for example, various types of devices may be made available to provide interoperability for different architectures or protocols. In some embodiments, routers may provide links between otherwise separate and independent LANs. In some embodiments, the communication links or channels may comprise, for example, analog telephone lines such as twisted wire pairs, coaxial cable, full or partial digital lines including T1, T2, T3, or T4 types of lines, an "integrated services digital network" (ISDN), a "digital subscriber line" (DSL), wireless links including satellite links, or other communication links or channels such as may be known to those skilled in the art. Further, in some embodiments, for example, a computer or other type of associated electronic device may be remotely coupled to the network, such as via a telephone line, a cell line, and/or a satellite link.

For purposes of this disclosure, in some embodiments, a "wireless network" should be understood as coupling users and/or clients with a network. According to some embodiments, the wireless network may employ an independent ad-hoc network, a mesh network, a wireless lan (wlan) network, a cellular network, or the like. In some embodiments, the wireless network may also include a system of terminals, gateways, routers, etc. coupled by radio links, etc. that may move freely, randomly, or organize themselves arbitrarily such that the network topology may change rapidly from time to time. In some embodiments, the wireless network may also employ a variety of network access technologies, including "long term evolution" (LTE), WLAN, Wireless Router (WR) networks, or second, third, fourth, or fifth generation (2G, 3G, 4G, or 5G) cellular technologies, among others. In some embodiments, the network access technology may enable wide area coverage for devices such as clients with varying degrees of mobility. For example, in some embodiments, the network may be via one or more network access technologies such as "global system for mobile communications" (GSM), "universal mobile telecommunications system" (UMTS), "general packet radio service" (GPRS), "enhanced data GSM environment" (EDGE), 3GPP LTE, LTE Advanced, "wideband code division multiple access" (WCDMA),802.11b/g/n, etc., implementing RF or wireless type communications. In some embodiments, the wireless network may include virtually any type of wireless communication mechanism by which to communicate information, such as in a wireless communication systemSignals may be communicated between clients (i.e., computers accessing the server) and/or devices such as computers, between networks, and/or within networks, etc.

For the purposes of this disclosure, a client (or customer or user) may, in some embodiments, comprise a computer capable of sending or receiving signals, such as via a wired or wireless network. In some embodiments, for example, the client may comprise a desktop or portable device, such as a cellular telephone, a smart phone, a display pager, a Radio Frequency (RF) transmitter/receiver, an Infrared (IR) transmitter/receiver, a Near Field Communication (NFC) transmitter/receiver, a Personal Digital Assistant (PDA), a handheld computer, a tablet computer, a phablet, a laptop computer, a set-top box, a wearable computer, an integrated device that incorporates various features, such as those of the above-described devices, and so forth.

In some embodiments, client devices may differ in capabilities or features, and claimed subject matter is intended to encompass a wide variety of possible variations. In some embodiments, a web-enabled fixed or mobile device may include a browser application configured to receive and send web pages, web-based messages, and the like. According to some embodiments, the browser application may be configured to receive and display graphics, text, multimedia, and the like, employing virtually any conventional web-based language.

It is to be understood that the system, in accordance with some embodiments, is not limited in its application to the details of construction and the arrangement of components set forth in the foregoing description or illustrated in the drawings. The system is capable of combining elements from some embodiments and of being practiced or of being carried out in various ways. Also, in some embodiments, it is to be understood that the phraseology and terminology used herein is for the purpose of description and should not be regarded as limiting. The use of "including," "comprising," or "having" and variations thereof herein, is meant to encompass the items listed thereafter and equivalents thereof as well as additional items, according to some embodiments. According to some embodiments, unless specified or limited otherwise, the terms "mounted," "connected," "supported," and "coupled" and variations thereof are used broadly and encompass both direct and indirect mountings, connections, supports, and couplings. Further, in some embodiments, "connected" and "coupled" are not restricted to physical or mechanical connections or couplings. In some embodiments, the term "substantially" as used herein includes a range of ± 10% of the unit of measure associated therewith, unless otherwise specified.

In some embodiments, the preceding discussion is presented to enable a person skilled in the art to make and use the embodiments disclosed herein. Various modifications to the illustrative embodiments will be readily apparent to those skilled in the art, in light of some embodiments, and the principles of one or more embodiments may be applied to other embodiments and applications without departing from the scope of the present disclosure. Thus, some embodiments of the invention are not intended to be limited to the embodiments shown, but are to be accorded the widest scope consistent with the principles and features disclosed herein. In some embodiments, the foregoing detailed description will be read with reference to the figures, in which like elements in different figures have like reference numerals. The drawings, which are not necessarily to scale, depict some embodiments and are not intended to limit the scope of any embodiments of the invention. According to some embodiments, those skilled in the art will recognize that the embodiments provided herein have many useful alternatives, and are within the scope of the present disclosure.

Some embodiments disclosed herein generally describe non-traditional approaches to systems and methods for visualization of process data management and data alarms that are not well known and, further, none of the known conventional methods or systems teach or suggest such approaches. Moreover, in some embodiments, the particular functional features are a significant technical improvement over conventional methods and systems, including at least the operation and functionality of the computing system as a technical improvement. In some embodiments, these technical improvements include one or more aspects of the systems and methods described herein that describe the details of how the machine operates and the federal law enforcement clearly shows that this is the nature of the statutory subject matter as opposed to improvements in machine operation made by the prior art.

In some embodiments, one or more embodiments described herein include functional limitations that work together in ordered combinations to transform the operation of data repositories in a manner that ameliorates the data storage and update problems of pre-existing databases. Some embodiments described herein include systems and methods for managing single or multiple content data items across different sources or applications that can cause problems to users of such systems and services, and where it is difficult or impossible to maintain reliable control over distributed information.

The description herein further describes embodiments that provide novel features that improve the performance of communications and software, systems and servers by providing automated functions that efficiently and more efficiently manage resource and asset data for users in a manner that cannot be done efficiently by hand. Thus, one of ordinary skill will readily recognize that these functions provide automated functions as described herein in a manner that is not well known, nor, of course, conventional. Thus, the system described herein is not directed to the idea of abstraction, but rather provides significant tangible innovation. Moreover, the functionality described herein is not imaginable in previously existing computing systems and does not exist until the disclosed system addresses the technical problem described above.

In some embodiments, it is recognized in the disclosure herein that enabling users to visualize all relevant alerts for or related to an asset, coordinate automatic grouping of alerts, and/or correlation between groups and individual alert instances based on one or more asset searches, according to some embodiments, results in new computing functionality and is a technical problem for network communications and other server-based technologies. Some embodiments herein provide one or more technical solutions in the field of computer-implementation of one or more graphical displays of packets and associated data, wherein alerts are analyzed in real-time using communications across networks, computers, databases, and/or the internet, thereby improving the performance and techniques of representing hierarchical assets and attributes of those assets in a manner that cannot be efficiently done manually or done at all.

It will be appreciated by those skilled in the art that while the system has been described above in connection with certain embodiments and examples, the system is not necessarily limited thereto and that the specification, drawings and appended claims are intended to encompass a wide variety of embodiments, examples, uses, modifications and departures from the embodiments, examples and uses.

Having described aspects of the present disclosure in detail above, it will be apparent that modifications and variations are possible in accordance with some embodiments without departing from the scope of aspects of the present disclosure as defined in the appended claims. In some embodiments, as various changes could be made in the above constructions, products, and methods without departing from the scope of aspects of the disclosure, it is intended that all matter contained in the above description and shown in the accompanying drawings shall be interpreted as illustrative and not in a limiting sense.