阅读说明：本技术 故障数据生成方法及系统 (Fault data generation method and system ) 是由 顾雯 王丹 宫翠平 孙磊 高原 张淼 王辉 徐闻世 代凯峰 于 2020-05-29 设计创作，主要内容包括：本发明涉及一种故障数据生成方法及系统,该故障数据生成方法包括：获取第一故障数据；基于所述第一故障数据确定生成规则；根据所述第一故障数据和所述生成规则生成第二故障数据,其中,所述第二故障数据中至少包含部分所述第一故障数据。本发明通过采用不同的生成规则进行数据生成,能够提供大量可靠、真实的故障数据,并能够以真实故障数据为基础,对真实故障数据中的缺失数据进行拟合补偿；同时可以以一组真实故障数据为基础,扩展出多种工况下相同故障的仿真数据,以提供给用户更大的数据量,方便用户使用,解决由于故障数据缺乏而导致的系统功效难以验证的问题。(The invention relates to a fault data generation method and a system, wherein the fault data generation method comprises the following steps: acquiring first fault data; determining a generation rule based on the first fault data; and generating second fault data according to the first fault data and the generation rule, wherein the second fault data at least comprises part of the first fault data. According to the invention, different generation rules are adopted for data generation, so that a large amount of reliable and real fault data can be provided, and missing data in the real fault data can be subjected to fitting compensation based on the real fault data; meanwhile, simulation data of the same fault under various working conditions can be expanded on the basis of a group of real fault data so as to provide a larger data volume for a user, the use by the user is convenient, and the problem that the system efficacy is difficult to verify due to the lack of fault data is solved.)

1. A method of fault data generation, comprising:

acquiring first fault data;

determining a generation rule based on the first fault data;

and generating second fault data according to the first fault data and the generation rule, wherein the second fault data at least comprises part of the first fault data.

2. The method of generating fault data according to claim 1, wherein determining a generation rule based on the first fault data comprises: and judging whether the first fault data meet preset conditions or not, generating a judgment result, and determining a generation rule matched with the judgment result.

3. The fault data generation method according to claim 1, wherein the generation rule includes: acquiring second fault data corresponding to the first fault data; and/or performing fitting compensation on the first fault data to obtain second fault data containing the first fault data; and/or generating second fault data under at least two working conditions based on the first fault data.

4. The fault data generation method according to claim 3, wherein acquiring second fault data corresponding to the first fault data includes: second fault data associated with the first fault data are called from a prestored fault database, wherein the data volume of the second fault data is larger than that of the first fault data.

5. The method according to claim 3, wherein performing fitting compensation on the first fault data to obtain second fault data including the first fault data includes: and fitting and compensating the first fault data based on an ash box model, and simulating third fault data.

6. The method of generating fault data according to claim 3, wherein generating second fault data for at least two operating conditions based on the first fault data comprises:

inputting a set of first fault data into a data generation system;

setting working condition parameters, wherein the working condition parameters at least comprise the number of working conditions;

and generating at least two groups of second fault data matched with the number of the working conditions based on the first fault data and the working condition parameters.

7. The fault data generation method according to claim 1, further comprising: the second failure data is transmitted to an external device provided outside the data generation system.

8. A fault data generation system, comprising:

the acquisition module is used for acquiring first fault data;

a determination module to determine a generation rule based on the first fault data;

and the generating module is used for generating second fault data according to the first fault data and the generating rule, wherein the second fault data at least comprises part of the first fault data.

9. The fault data generation system of claim 8, wherein the generation module comprises:

a first generation unit configured to acquire second failure data corresponding to the first failure data;

the second generating unit is used for performing fitting compensation on the first fault data to obtain second fault data containing the first fault data;

and the third generating unit is used for generating second fault data under at least two working conditions based on the first fault data.

10. The fault data generation system of claim 8, further comprising: and a data output module for transmitting the second failure data to an external device provided outside the data generation system.

Technical Field

The invention relates to the technical field of data generation, in particular to a fault data generation method and system.

Background

For the process industry, the occurrence of faults is a common phenomenon. Since some faults can affect production, they must be discovered and handled in a timely manner. In the efficacy verification process of the existing fault diagnosis software, the effect of the existing fault diagnosis software can be verified only by using simple fault simulation data, so that the test result of the existing fault diagnosis software has deviation. Therefore, it is essential to have a large amount of reliable production failure data.

The conventional fault data simulation generating device obtains simulation data only through a model, has low data authenticity, reliability and practicability, and is difficult to effectively expand data so as to obtain reliable fault data with enough quantity.

Disclosure of Invention

In view of the above problems in the prior art, an object of the present invention is to provide a fault data generation method and system, which can solve the problem that the efficacy of a system (such as a fault diagnosis system, a robust structural design, etc.) is difficult to verify due to the lack of fault data.

In order to achieve the above object, an embodiment of the present invention provides a method for generating fault data, including:

acquiring first fault data;

determining a generation rule based on the first fault data;

and generating second fault data according to the first fault data and the generation rule, wherein the second fault data at least comprises part of the first fault data.

In some embodiments, determining a generation rule based on the first fault data comprises: and judging whether the first fault data meet preset conditions or not, generating a judgment result, and determining a generation rule matched with the judgment result.

In some embodiments, the generating rules comprises: acquiring second fault data corresponding to the first fault data; and/or performing fitting compensation on the first fault data to obtain second fault data containing the first fault data; and/or generating second fault data under at least two working conditions based on the first fault data.

In some embodiments, obtaining second failure data corresponding to the first failure data comprises: second fault data associated with the first fault data are called from a prestored fault database, wherein the data volume of the second fault data is larger than that of the first fault data.

In some embodiments, fitting the first fault data to obtain second fault data including the first fault data includes: and fitting and compensating the first fault data based on an ash box model, and simulating third fault data.

In some embodiments, generating second fault data for at least two operating conditions based on the first fault data comprises:

inputting a set of first fault data into a data generation system;

setting working condition parameters, wherein the working condition parameters at least comprise the number of working conditions;

and generating at least two groups of second fault data matched with the number of the working conditions based on the first fault data and the working condition parameters.

In some embodiments, further comprising: the second failure data is transmitted to an external device provided outside the data generation system.

An embodiment of the present invention further provides a system for generating fault data, including:

the acquisition module is used for acquiring first fault data;

a determination module to determine a generation rule based on the first fault data;

and the generating module is used for generating second fault data according to the first fault data and the generating rule, wherein the second fault data at least comprises part of the first fault data.

In some embodiments, the generating module comprises:

a first generation unit configured to acquire second failure data corresponding to the first failure data;

the second generating unit is used for performing fitting compensation on the first fault data to obtain second fault data containing the first fault data;

and the third generating unit is used for generating second fault data under at least two working conditions based on the first fault data.

In some embodiments, the fault data generation system further comprises: and a data output module for transmitting the second failure data to an external device provided outside the data generation system.

Compared with the prior art, the fault data generation method and the fault data generation system provided by the embodiment of the invention can provide a large amount of reliable and real fault data by adopting different generation rules to generate data, and can perform fitting compensation on missing data in the real fault data on the basis of the real fault data; meanwhile, simulation data of the same fault under various working conditions can be expanded on the basis of a group of real fault data so as to provide a larger data volume for a user, the use by the user is convenient, and the problem that the system efficacy is difficult to verify due to the lack of fault data is solved.

Drawings

In the drawings, which are not necessarily drawn to scale, like reference numerals may describe similar components in different views. Like reference numerals having letter suffixes or different letter suffixes may represent different instances of similar components. The drawings illustrate various embodiments, by way of example and not by way of limitation, and together with the description and claims, serve to explain the inventive embodiments. The same reference numbers will be used throughout the drawings to refer to the same or like parts, where appropriate. Such embodiments are illustrative, and are not intended to be exhaustive or exclusive embodiments of the present apparatus or method.

FIG. 1 is a flow chart of a fault data generation method of an embodiment of the present invention;

FIG. 2 is a flow chart of another embodiment of a fault data generation method according to an embodiment of the present invention;

FIG. 3 is a flowchart of a method for generating fault data according to another embodiment of the present invention;

FIG. 4 is a schematic structural diagram of a fault data generation system according to an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of a generating module of the fault data generating system according to the embodiment of the present invention;

FIG. 6 is another schematic diagram of a fault data generation system according to an embodiment of the present invention;

fig. 7 is a schematic structural diagram of a fault data generation system according to an embodiment of the present invention.

Detailed Description

The following detailed description of specific embodiments of the present invention is provided in connection with the accompanying drawings, which are not intended to limit the invention.

It will be understood that various modifications may be made to the embodiments disclosed herein. Accordingly, the foregoing description should not be construed as limiting, but merely as exemplifications of embodiments. Other modifications will occur to those skilled in the art which are within the scope and spirit of the invention.

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and, together with a general description of the invention given above, and the detailed description of the embodiments given below, serve to explain the principles of the invention.

These and other features of the invention will become apparent from the following description of preferred forms of embodiment, given as non-limiting examples, with reference to the accompanying drawings.

It should also be understood that, although the invention has been described with reference to some specific examples, a person of skill in the art shall certainly be able to achieve many other equivalent forms of the invention, having the characteristics as set forth in the claims and hence all coming within the field of protection defined thereby.

The above and other aspects, features and advantages of the present invention will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.

Specific embodiments of the present invention are described hereinafter with reference to the accompanying drawings; however, it is to be understood that the disclosed embodiments are merely exemplary of the invention, which can be embodied in various forms. Well-known and/or repeated functions and constructions are not described in detail to avoid obscuring the invention in unnecessary or unnecessary detail. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the present invention in virtually any appropriately detailed structure.

Fig. 1 is a flowchart of a fault data generation method according to an embodiment of the present invention. As shown in fig. 1, an embodiment of the present invention provides a method for generating fault data, including:

s11, acquiring first fault data;

s12, determining a generation rule based on the first fault data;

and S13, generating second fault data according to the first fault data and the generating rule, wherein the second fault data at least comprises part of the first fault data.

The first failure data is failure data obtained by actual detection, and the second failure data is related data constructed for failure diagnosis, testing, and the like. The data generation system can acquire the first fault data from the outside, or can store the first fault data in a database of the data generation system in advance, and the first fault data can be called directly when in use.

Specifically, the process data of each production facility and the data content when a fault occurs or a facility is defective in each process may be recorded in an actual production process (for example, a coal gasification process), and the recorded data may be summarized to obtain first fault data.

The fault data includes fault type, fault cause, fault rate (fault occurrence rate), severity level of different faults, etc., and the fault type may include equipment fault, electrical fault, etc. The same type of fault can occur under different working conditions, for example, in a coal gasification process, when different loads exist in the same equipment, the fault occurrence rate of the equipment is different.

After the first fault data are obtained, the first fault data are analyzed, and a generation rule matched with the first fault data is determined. After the generation rule is determined, corresponding second fault data can be generated according to the first fault data and the generation rule.

The generation rule is used to describe a specific generation manner of the second failure data. The generating of the rule includes: acquiring second fault data corresponding to the first fault data; and/or performing fitting compensation on the first fault data to obtain second fault data containing the first fault data; and/or generating second fault data under at least two working conditions based on the first fault data.

In step S12, determining a generation rule based on the first fault data specifically includes: and judging whether the first fault data meet preset conditions or not, generating a judgment result, and determining a generation rule matched with the judgment result.

Judging whether the first fault data meets a preset condition comprises the following steps: judging whether the first fault data meet a preset data volume or not; and/or judging whether the first fault data has data loss or not; and/or judging whether the first fault data needs to be expanded or not.

In some embodiments, when a fault needs to be diagnosed according to the first fault data, since the acquired first fault data has a small data amount and does not reach the data amount required for fault diagnosis, it is difficult to obtain an accurate diagnosis result by directly adopting the first fault data to perform fault diagnosis, and more fault data related to the first fault data needs to be acquired.

Namely, when the first fault data is judged not to meet the preset data volume, adopting a first generation rule: second fault data corresponding to the first fault data is obtained. I.e. a larger amount of second fault data associated with the first fault data is called directly from a pre-stored fault database.

The pre-stored fault database stores a large amount of actual fault data which can be directly used, and the actual fault data comprises continuous fault data. The continuous fault data may be continuous fault data in a predetermined time period, or may be continuous fault data in a continuous flow.

Specifically, when the first fault data is fault data within a certain time period, more fault data with the same fault type as the first fault data within more time periods can be called by traversing the pre-stored fault database to generate second fault data, so that more fault data can be generated to facilitate fault diagnosis. In a specific implementation, other failure data associated with the first failure data may also be called, and the present invention is not particularly limited.

In some embodiments, as shown in fig. 2, without acquiring the first fault data, the second fault data may be directly acquired from a pre-stored fault database according to the first generation rule, where the specific acquisition method includes:

s21, setting generation parameters;

and S22, traversing a pre-stored fault database based on the generation parameters, and calling second fault data corresponding to the generation parameters.

The generation parameters include parameters such as a fault type, a fault device and a fault time. I.e. in case the user does not have any data resources, second failure data may also be generated for failure diagnosis, testing, etc.

The second fault data acquired based on the first generation rule are actual fault data which are real and reliable, and the practicability is high, so that the efficiency test and verification of systems such as fault diagnosis and robust structural design are facilitated.

In some embodiments, the acquired first failure data is not complete failure data, but is a data fragment with partial data missing, and therefore, when it is determined that there is data missing in the first failure data, a second generation rule is adopted: and fitting and compensating the first fault data to obtain second fault data containing the first fault data.

Specifically, fitting compensation is performed on the first fault data based on a gray box model, third fault data are simulated, the third fault data are missing fault data, and the third fault data and the acquired first fault data form a complete set of fault data. The finally generated second fault data not only contains actual data, but also contains simulation data, and compared with the method of simply using the simulation data to carry out scientific research or simulation verification, the data reliability is high. By using the second generation rule to generate the fault data, the incomplete fault data can be effectively fitted and supplemented, the data fragments in the hands of the user are converted into an available form, and the user can use the data conveniently. The grey box model combines the mechanism model with the neural network model, and the accuracy of data simulation can be greatly improved.

Further, after the second failure data is generated according to the second generation rule, a greater number of failure data may be obtained based on the first generation rule, and a specific generation manner is similar to that of the second failure data under the first generation rule, and details are not repeated here.

In other embodiments, as shown in fig. 3, when it is determined that the first failure data needs to be expanded, a third generation rule is used to generate second failure data, which specifically includes:

s31, inputting a group of first fault data into the data generation system;

s32, setting working condition parameters, wherein the working condition parameters at least comprise the number of working conditions;

and S33, generating at least two groups of second fault data matched with the number of the working conditions based on the first fault data and the working condition parameters.

It should be noted that the operating condition parameter represents any value of a physical quantity that is capable of indicating a (target or actual) physical state or operating condition of the operating device. For example, the parameter may be a parameter when a certain operating device has a different load, or may be a parameter when a certain operating device is in a different operating state (operating or stopped).

Specifically, in order to verify the universality of the fault diagnosis software, the fault diagnosis software is generally verified under multiple working conditions, that is, the number of the working conditions is at least greater than 1, so that fault data of the same fault or the same type of fault under different working conditions needs to be acquired, a user can import the acquired first fault data into the data generation system, set working condition parameters by using an expansion function therein, and expand and generate multiple sets of fault data of the same fault or the same type of fault under different working conditions (for example, different loads) based on the working condition parameters and on the set of fault data so as to be further used.

After the second failure data is generated, the generated data may be reused as the first failure data, and steps S12 through S13 may be cyclically executed until a desired data amount is reached.

The three generation rules may be used simultaneously or at least one of them may be used, and the present invention is not particularly limited.

In some embodiments, the fault data generation method further comprises: the data generation system is updated. The updating data generation system comprises a fault database and updating parameters, wherein the updating parameters comprise updating generation parameters and/or working condition parameters.

Specifically, after the second fault data is generated, the input first fault data or the generated second fault data may be stored in the fault database to update the fault database, and parameters of the data generation system are updated, so as to implement dynamic adjustment of the fault data, and provide a large amount of reliable fault data for use.

In some embodiments, the fault data generation method further comprises: the second failure data is transmitted to an external device provided outside the data generation system. The external device may be hardware or software, and for example, the generated second fault data may be sent to the fault diagnosis software, and a fault diagnosis test may be performed based on the second fault data to verify the efficacy of the fault diagnosis software.

In specific implementation, data can be sent out in a continuous mode through a data protocol (such as an OPC protocol) commonly used in the process industry, dynamic and continuous data are provided, the actual production situation is simulated, and the use by a user is facilitated.

According to the fault data generation method provided by the embodiment of the invention, different generation rules are adopted for data generation, a large amount of reliable and real fault data can be provided, and missing data in the real fault data can be subjected to fitting compensation on the basis of the real fault data; meanwhile, simulation data of the same fault under various working conditions can be expanded on the basis of a group of real fault data so as to provide a larger data volume for a user, the use by the user is convenient, and the problem that the system efficacy is difficult to verify due to the lack of fault data is solved.

Fig. 4 is a schematic structural diagram of a fault data generation system according to an embodiment of the present invention. As shown in fig. 4, the fault data generation system includes:

an obtaining module 41, configured to obtain first fault data;

a determination module 42 for determining a generation rule based on the first fault data;

a generating module 43, configured to generate second failure data according to the first failure data and the generating rule, where the second failure data includes at least a part of the first failure data.

The obtaining module 41 may obtain the first failure data directly input by the user, or may obtain the first failure data provided by a third party through an input interface 411 as shown in fig. 6, so as to be used later.

Further, as shown in fig. 5, the generating module includes:

a first generation unit 431 for acquiring second failure data corresponding to the first failure data;

a second generating unit 432, configured to perform fitting compensation on the first fault data to obtain second fault data including the first fault data;

a third generating unit 433, configured to generate second fault data under at least two operating conditions based on the first fault data.

As shown in fig. 6, the fault data generation system further includes: and the storage module 44 is used for storing the input first fault data, the generated second fault data and the prestored fault data.

The above-mentioned fault data generation system further includes a data output module 45 for transmitting the second fault data to an external device provided outside the data generation system.

The data output module 45 may be a wired output interface or a wireless transmission unit, and may continuously transmit the generated second failure data to an external device for further use through a data protocol (e.g., OPC protocol) commonly used in the process industry.

The fault data generation system further includes a user interface 46 on which a user may perform data import, database management, and control generation modules to implement the generation (e.g., invocation, fitting, and expansion) of fault data. In addition, the user can directly operate on the user interaction interface to lead the fault data out of the storage module in different formats for analysis.

In the data generating system according to the embodiment of the present invention, the obtaining module 41 obtains the first failure data, the determining module 42 determines the data generating rule, and the generating module 43 generates the data according to the data generating rule. The data generation system provided by the embodiment of the invention can generate sufficient, complete and comprehensive fault data so as to carry out fault detection or verification subsequently.

Fig. 7 is a schematic structural diagram of a fault data generation system according to another embodiment of the present invention. The fault data generation system comprises a memory 71 and a processor 72, wherein the processor 72 is configured to perform the method in any of the preceding embodiments based on instructions stored in the memory. The memory 71 may include, for example, a system memory, a fixed nonvolatile storage medium, and the like. The system memory stores, for example, an operating system, an application program, a BootLoader (BootLoader), and other programs.

The system, module or unit described in the above embodiments may be implemented by a computer chip or an entity, or implemented by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

The above embodiments are only exemplary embodiments of the present invention, and are not intended to limit the present invention, and the scope of the present invention is defined by the claims. Various modifications and equivalents may be made by those skilled in the art within the spirit and scope of the present invention, and such modifications and equivalents should also be considered as falling within the scope of the present invention.