阅读说明：本技术 化工装置尾气含氧量计算方法、装置、存储介质及处理器 (Chemical device tail gas oxygen content calculation method and device, storage medium and processor ) 是由 韩华伟 贾学五 高新江 王春利 张帆 于 2020-05-25 设计创作，主要内容包括：本发明提供一种化工装置尾气含氧量计算方法、装置、存储介质及处理器,属于化工技术领域。该计算方法包括：检测所述化工装置的尾气含氧量以外其他位点的当前数据；根据所述其他位点的当前数据,基于含氧量预测模型,计算所述化工装置的尾气含氧量,其中所述含氧量预测模型为所述尾气含氧量的波动历史数据以及与所述尾气含氧量的波动历史数据相关的其他位点的历史数据进行神经网络训练得到的模型。本发明不依赖于人力,保证化工装置的安全运行。(The invention provides a method and a device for calculating oxygen content of tail gas of a chemical device, a storage medium and a processor, and belongs to the technical field of chemical industry. The calculation method comprises the following steps: detecting current data of other sites except the oxygen content of the tail gas of the chemical device; and calculating the oxygen content of the tail gas of the chemical device based on an oxygen content prediction model according to the current data of the other sites, wherein the oxygen content prediction model is obtained by performing neural network training on fluctuation historical data of the oxygen content of the tail gas and historical data of the other sites related to the fluctuation historical data of the oxygen content of the tail gas. The invention does not depend on manpower and ensures the safe operation of the chemical device.)

1. A chemical plant tail gas oxygen content calculation method is characterized by comprising the following steps:

detecting current data of other sites except the oxygen content of the tail gas of the chemical device;

and calculating the oxygen content of the tail gas of the chemical device based on an oxygen content prediction model according to the current data of the other sites, wherein the oxygen content prediction model is obtained by performing neural network training on fluctuation historical data of the oxygen content of the tail gas and historical data of the other sites related to the fluctuation historical data of the oxygen content of the tail gas.

2. The method for calculating the oxygen content in the tail gas of the chemical plant according to claim 1, wherein the fluctuation historical data is historical data in which the duration of abnormal operation data within a preset duration is greater than a preset percentage of the preset duration.

3. The chemical plant tail gas oxygen content calculation method according to claim 1, wherein the oxygen content prediction model is obtained by:

acquiring fluctuation historical data of the oxygen content of the tail gas;

calculating a gray level correlation coefficient of the fluctuation historical data and the historical data of each of other sites at the same operation time;

extracting the fluctuation historical data and historical data of other sites with the gray scale correlation coefficient larger than a correlation coefficient threshold value, wherein the correlation coefficient threshold value is determined according to whether tail gas continuously participates in the blasting reaction;

and training based on the extracted data and the neural network to obtain the oxygen content prediction model.

4. The chemical plant tail gas oxygen content calculation method according to claim 2, wherein the gray scale correlation coefficient is calculated by the following formula:

wherein x is₀For fluctuating historical data, x_iThe historical data of the ith site in other sites at the same operation time is shown, rho is a preset coefficient, and k is the serial number of the historical data.

5. The chemical plant tail gas oxygen content calculation method according to claim 1, wherein when the tail gas continues to participate in the blasting reaction, the correlation coefficient threshold is 0.6; when the tail gas does not continuously participate in the blasting reaction, the threshold value of the correlation coefficient is 0.8.

6. The chemical plant exhaust gas oxygen content calculation method according to claim 1, wherein the neural network training uses a MATLAB neural network.

7. The chemical plant tail gas oxygen content calculation method according to claim 1, wherein 70% of the fluctuation history data of the raffinate hydrogen peroxide concentration and the history data of other sites related to the fluctuation history data of the raffinate hydrogen peroxide concentration are used for training the hydrogen peroxide concentration prediction model, 15% of the data are used for testing the hydrogen peroxide concentration prediction model, and 15% of the data are used for verifying the hydrogen peroxide concentration prediction model.

8. The utility model provides a chemical plant device tail gas oxygen content accounting device which characterized in that, this accounting device includes:

a detection unit and a processing unit, wherein,

the detection unit is used for detecting the current data of other sites except the oxygen content of the tail gas of the chemical device;

the processing unit is used for calculating the oxygen content of the tail gas of the chemical device based on an oxygen content prediction model according to the current data of other sites, wherein the oxygen content prediction model is a model obtained by performing neural network training on fluctuation historical data of the oxygen content of the tail gas and historical data of other sites related to the fluctuation historical data of the oxygen content of the tail gas.

9. The chemical plant tail gas oxygen content calculation device according to claim 8, wherein the fluctuation history data is history data in which the duration of the abnormal operation data within a preset duration is greater than a preset percentage of the preset duration.

10. The chemical plant tail gas oxygen content calculation device according to claim 8, wherein the oxygen content prediction model is obtained by:

acquiring fluctuation historical data of the oxygen content of the tail gas;

calculating a gray level correlation coefficient of the fluctuation historical data and the historical data of each of other sites at the same operation time;

extracting the fluctuation historical data and historical data of other sites with the gray scale correlation coefficient larger than a correlation coefficient threshold, wherein the correlation coefficient threshold is related to whether tail gas continuously participates in the blasting reaction;

and training based on the extracted data and the neural network to obtain the oxygen content prediction model.

11. The chemical plant tail gas oxygen content calculation device of claim 10, wherein the gray scale correlation coefficient is calculated by the following formula:

wherein x is₀For fluctuating historical data, x_iThe historical data of the ith site in other sites at the same operation time is shown, rho is a preset coefficient, and k is the serial number of the historical data.

12. The chemical plant tail gas oxygen content calculation device according to claim 8, wherein the correlation coefficient threshold is 0.6 when the tail gas continues to participate in the blasting reaction; when the tail gas does not continuously participate in the blasting reaction, the threshold value of the correlation coefficient is 0.8.

13. The chemical plant exhaust gas oxygen content calculation apparatus according to claim 8, wherein the neural network training uses a MATLAB neural network.

14. The chemical plant tail gas oxygen content calculation device according to claim 8, wherein 70% of the fluctuation history data of the raffinate hydrogen peroxide concentration and the history data of other sites related to the fluctuation history data of the raffinate hydrogen peroxide concentration are used for training the hydrogen peroxide concentration prediction model, 15% of the data are used for testing the hydrogen peroxide concentration prediction model, and 15% of the data are used for verifying the hydrogen peroxide concentration prediction model.

15. A machine-readable storage medium having stored thereon instructions for causing a machine to perform the method for calculating oxygen content of chemical plant exhaust according to any one of claims 1 to 7.

16. A processor configured to run a program, wherein the program is executed to perform the method for calculating oxygen content of chemical plant exhaust according to any one of claims 1 to 7.

Technical Field

The invention relates to the technical field of chemical industry, in particular to a method and a device for calculating oxygen content of tail gas of a chemical device, a storage medium and a processor.

Background

Oxygen, as a reactant or a reaction product in many chemical plants, often appears in tail gas discharged from different reaction stages (for example, oxygen is discharged from both the hydrogenation stage and the oxidation stage of a device for producing hydrogen peroxide by an anthraquinone process). The oxygen with higher concentration is easy to become a fuse for dangerous accidents such as explosion, fire and the like, and especially when the oxygen with content exceeding the threshold value is contacted with other flammable and explosive materials (for example, tail gas of an oxidation tower of a hydrogen peroxide device returns to a hydrogenation tower to be contacted with hydrogen), safety accidents are easy to occur. Therefore, real-time monitoring of the oxygen content (i.e. oxygen content) in the tail gas of the chemical plant is one of the key points for ensuring the safe operation of the plant.

The tail gas oxygen content in the existing device is lack of on-line measuring equipment, manual sampling is adopted, and the method is long in sampling interval time and high in cost. The developed automatic sampling tester for the oxygen content of the tail gas has high cost and large measurement error, and the emissions can not reach the environmental protection standard and can not meet the practical requirements of chemical enterprises in China.

Disclosure of Invention

The invention aims to provide a method and a device for calculating the oxygen content of tail gas of a chemical device, a storage medium and a processor.

In order to achieve the purpose, the invention provides a method for calculating the oxygen content of tail gas of a chemical device, which comprises the following steps: detecting current data of other sites except the oxygen content of the tail gas of the chemical device; and calculating the oxygen content of the tail gas of the chemical device based on an oxygen content prediction model according to the current data of the other sites, wherein the oxygen content prediction model is obtained by performing neural network training on fluctuation historical data of the oxygen content of the tail gas and historical data of the other sites related to the fluctuation historical data of the oxygen content of the tail gas.

Preferably, the fluctuation historical data is historical data in which the time length of the data which abnormally operates within a preset time length is greater than a preset percentage of the preset time length.

Preferably, the oxygen content prediction model is obtained by: acquiring fluctuation historical data of the oxygen content of the tail gas; calculating a gray level correlation coefficient of the fluctuation historical data and the historical data of each of other sites at the same operation time; extracting the fluctuation historical data and historical data of other sites with the gray scale correlation coefficient larger than a correlation coefficient threshold, wherein the correlation coefficient threshold is related to whether tail gas continuously participates in the blasting reaction; and training based on the extracted data and the neural network to obtain the oxygen content prediction model.

Preferably, the gray scale correlation coefficient is calculated by the following formula:

wherein x is₀For fluctuating historical data, x_iThe historical data of the ith site in other sites at the same operation time is shown, rho is a preset coefficient, and k is the serial number of the historical data.

Preferably, when the tail gas continues to participate in the blasting reaction, the threshold value of the correlation coefficient is 0.6; when the tail gas does not continuously participate in the blasting reaction, the threshold value of the correlation coefficient is 0.8.

Preferably, the neural network training uses a MATLAB neural network.

Preferably, 70% of the fluctuation history data of the raffinate hydrogen peroxide concentration and the history data of other sites related to the fluctuation history data of the raffinate hydrogen peroxide concentration are used for training the hydrogen peroxide concentration prediction model, 15% of the data are used for testing the hydrogen peroxide concentration prediction model, and 15% of the data are used for verifying the hydrogen peroxide concentration prediction model.

The invention also provides a chemical plant tail gas oxygen content calculating device, which comprises: the device comprises a detection unit and a processing unit, wherein the detection unit is used for detecting the current data of other sites except the oxygen content of the tail gas of the chemical device; the processing unit is used for calculating the oxygen content of the tail gas of the chemical device based on an oxygen content prediction model according to the current data of other sites, wherein the oxygen content prediction model is a model obtained by performing neural network training on fluctuation historical data of the oxygen content of the tail gas and historical data of other sites related to the fluctuation historical data of the oxygen content of the tail gas.

Preferably, the fluctuation historical data is historical data in which the time length of the data which abnormally operates within a preset time length is greater than a preset percentage of the preset time length.

Preferably, the oxygen content prediction model is obtained by: acquiring fluctuation historical data of the oxygen content of the tail gas; calculating a gray level correlation coefficient of the fluctuation historical data and the historical data of each of other sites at the same operation time; extracting the fluctuation historical data and historical data of other sites with the gray scale correlation coefficient larger than a correlation coefficient threshold, wherein the correlation coefficient threshold is related to whether tail gas continuously participates in the blasting reaction; and training based on the extracted data and the neural network to obtain the oxygen content prediction model.

Preferably, the gray scale correlation coefficient is calculated by the following formula:

wherein x is₀For fluctuating historical data, x_iFor the same time of operationRho of historical data of the ith site in other sites is a preset coefficient, and k is a serial number of the historical data.

Preferably, when the tail gas continues to participate in the blasting reaction, the threshold value of the correlation coefficient is 0.6; when the tail gas does not continuously participate in the blasting reaction, the threshold value of the correlation coefficient is 0.8.

Preferably, the neural network training uses a MATLAB neural network.

Preferably, 70% of the fluctuation history data of the raffinate hydrogen peroxide concentration and the history data of other sites related to the fluctuation history data of the raffinate hydrogen peroxide concentration are used for training the hydrogen peroxide concentration prediction model, 15% of the data are used for testing the hydrogen peroxide concentration prediction model, and 15% of the data are used for verifying the hydrogen peroxide concentration prediction model.

The invention also provides a machine-readable storage medium, which stores instructions for causing a machine to execute the chemical plant exhaust gas oxygen content calculation method.

The invention also provides a processor which is characterized by being used for running the program, wherein the program is used for executing the chemical plant tail gas oxygen content calculation method when being run.

By adopting the technical scheme, the method, the device, the storage medium and the processor for calculating the oxygen content of the tail gas of the chemical device are adopted to detect the current data of other sites except the oxygen content of the tail gas of the chemical device; and calculating the oxygen content of the tail gas of the chemical device based on an oxygen content prediction model according to the current data of the other sites, wherein the oxygen content prediction model is obtained by performing neural network training on fluctuation historical data of the oxygen content of the tail gas and historical data of the other sites related to the fluctuation historical data of the oxygen content of the tail gas. According to the invention, the oxygen content is obtained according to the model after the model is built, and the safe operation of the chemical device is ensured without depending on manpower.

Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows.

Drawings

The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the embodiments of the invention without limiting the embodiments of the invention. In the drawings:

fig. 1 is a flowchart of a method for calculating oxygen content in tail gas of a chemical plant according to an embodiment of the present invention;

FIG. 2 is a flowchart illustrating a method for building an oxygen content prediction model according to an embodiment of the present invention;

fig. 3 is a block diagram of a device for calculating oxygen content in exhaust gas of a chemical apparatus according to an embodiment of the present invention.

Description of the reference numerals

1 detection unit 2 processing unit

Detailed Description

The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating embodiments of the invention, are given by way of illustration and explanation only, not limitation.

Example one

Fig. 1 is a flowchart of a method for calculating an oxygen content of an exhaust gas of a chemical plant according to an embodiment of the present invention. As shown in fig. 1, the calculation method includes:

step S11, detecting the current data of other sites except the oxygen content of the tail gas of the chemical device;

specifically, the site may be different measurement objects of different chemical plants, such as the oxygen content of the tail gas of the hydrogenation tower, the oxygen content of the tail gas of the oxidation tower or the concentration of the hydrogen peroxide in the raffinate, and may also be different measurement objects in the same chemical plant, such as the oxygen content of the tail gas of the hydrogenation tower, the hydrogen content or other contents, and the like for the hydrogenation tower. In the embodiment of the invention, if the oxygen content of the tail gas of the hydrogenation tower is required to be detected, the current data of other sites except the oxygen content of the tail gas of the hydrogenation tower can be detected firstly.

Step S12, calculating the oxygen content of the tail gas of the chemical device based on an oxygen content prediction model according to the current data of the other sites, wherein the oxygen content prediction model is a model obtained by performing neural network training on fluctuation historical data of the oxygen content of the tail gas and historical data of the other sites related to the fluctuation historical data of the oxygen content of the tail gas, and the fluctuation historical data is historical data of which the duration of abnormal operation data in a preset duration is greater than the preset percentage of the preset duration.

Specifically, the embodiment of the invention substitutes the detected current data of other sites based on the oxygen content prediction model to calculate the oxygen content of the tail gas of the chemical engineering device. The oxygen content prediction model is obtained by performing neural network training on fluctuation historical data of the oxygen content of the exhaust and historical data of other sites related to the fluctuation historical data of the oxygen content of the exhaust. The fluctuation history data refers to history data in which the duration of the data abnormally operated within a preset duration is greater than a preset percentage of the preset duration, and the preset percentage may be 30%, but is not limited thereto. For example, if the site has 3 months of historical data and the preset time is 1 month, all the historical data can be divided into three parts, and of the 1 st month of historical data, 10 days of historical data are data of abnormal operation (abnormal operation can be marked on the data), and then 10 days account for about 33% of the 1 st month, and are greater than the preset percentage, then the 1 st month of historical data are fluctuation historical data. In the historical data of month 2 and month 3, the historical data of day 5 and day 4 are abnormal operation data, the percentage of month 1 is less than 30%, and the historical data of month 2 and month 3 are not fluctuation historical data. The historical data of other sites related to the fluctuation historical data can be directly obtained, and can also be obtained according to the obtaining mode provided by the following embodiment of the invention.

Example two

In the present embodiment, a difference from the embodiment is that a method for establishing an oxygen content prediction model is mainly provided, and particularly, a more detailed method for obtaining historical data of other sites related to fluctuation historical data is provided.

Specifically, the oxygen content prediction model is obtained by the following method:

step S21, obtaining fluctuation historical data of oxygen content of the tail gas;

specifically, the data acquired in the embodiment of the present invention may be operation data stored in a Distributed Control System (DCS) or Laboratory Information Management System (LIMS) record data, but not all the history data of the site is acquired, and only the fluctuation history data is acquired. The meaning of the fluctuation history data is as described above.

Step S22, calculating the grey scale correlation coefficient of the fluctuation historical data and the historical data of each of other sites at the same operation time;

specifically, since the historical data of other sites may also have a certain influence on the historical data of the oxygen content, the embodiment of the present invention further needs to determine the correlation between the fluctuation historical data and the historical data of other sites at the same operation time. The same time of operation means that if the fluctuation history data is data of 1 month in 2020 (even, in particular, several minutes and several seconds to several days), the history data of other points at which the gradation correlation coefficient is calculated should use the data of 1 month in 2020. Since there may be many other sites, the historical data of each site corresponding to the operation time can be used to calculate the gray scale correlation coefficient with the fluctuation historical data.

Step S23, extracting the fluctuation historical data and the historical data of other sites with the gray scale correlation coefficient larger than the correlation coefficient threshold value, wherein the correlation coefficient threshold value is related to whether the tail gas continuously participates in the blasting reaction;

specifically, if the gray scale correlation coefficient calculated by the historical data of the H site and the fluctuation historical data is greater than the correlation coefficient threshold, it indicates that the historical data of the H site and the fluctuation historical data have a large correlation, and extraction is required, that is, on the basis of extracting the fluctuation historical data, the historical data of the H site is also required to be extracted. In consideration of safety, the threshold value of the correlation coefficient depends on whether the tail gas continuously participates in the blasting reaction, and if the tail gas continuously participates in the blasting reaction, the threshold value of the correlation coefficient is smaller than that when the tail gas does not continuously participate in the blasting reaction.

And step S24, training based on the extracted data and the neural network to obtain the oxygen content prediction model.

Specifically, for example, the MATLAB neural network toolbox is used for performing the operation, the number of nodes of an input layer of the neural network is the number of other sites, the number of nodes of an intermediate layer is 7, the number of nodes of each layer is 50, and the number of nodes of an output layer is 1, which corresponds to the output variable. 70% of the data samples were used to train the model, 15% of the data samples were used to test the model, and 15% of the data samples were used to validate the model. The running environment is WINDOWS7, MATLAB2019 a.

EXAMPLE III

In this embodiment, the difference from the first and second embodiments is that a more detailed method for calculating the gray scale correlation coefficient between the fluctuation history data and the history data at one of the other sites at the same operation time is mainly provided, and the other calculation methods are similar to those in the first and second embodiments and will not be described again here.

Specifically, the gray scale correlation coefficient is calculated by the following formula:

wherein x is₀For fluctuating historical data, x_iThe historical data of the ith site in other sites at the same operation time is shown, rho is a preset coefficient, and k is the serial number of the historical data. That is, assuming that the 1 st site among other sites is taken as an example, the 1 st site has a lot of historical data, and the historical data correspond to the operation time of the fluctuation historical data, for example, the fluctuation historical data is 60 data acquired every 12 hours within 30 days, then the 1 st site also uses 60 data acquired every 12 hours within 30 days, and can be regarded as having sequence numbers 1-60, and the sorting is based on the time sequence.

Example four

In this embodiment, different from the first to third embodiments, the preset time length, the data interval and the exhaust gas post-treatment are mainly provided to cause different correlation coefficient thresholds. Other extraction methods are similar to those in the first to third embodiments, and are not described herein again.

Specifically, for the preset duration and the data interval, for the detection of the oxygen content, the preset duration may be 30 days, and the data interval may be 12 hours.

For the correlation coefficient threshold, please see table 1:

TABLE 1

When the tail gas continues to participate in the blasting reaction, the correlation coefficient threshold value can be 0.6; the threshold correlation coefficient may be 0.8 when the exhaust gas does not continue to participate in the detonation reaction.

Although the specific values are provided in the embodiment, the values are only preferable values in the embodiment of the present invention, and may be other values, which is not limited in the embodiment of the present invention.

EXAMPLE five

Fig. 3 is a block diagram of a device for calculating oxygen content in exhaust gas of a chemical apparatus according to an embodiment of the present invention. As shown in fig. 3, the computing device includes: the device comprises a detection unit 1 and a processing unit 2, wherein the detection unit 1 is used for detecting current data of other sites except the oxygen content of tail gas of the chemical device; the processing unit 2 is configured to calculate an oxygen content of the exhaust gas of the chemical plant based on an oxygen content prediction model according to the current data of the other sites, where the oxygen content prediction model is a model obtained by performing neural network training on fluctuation history data of the oxygen content of the exhaust gas and history data of the other sites related to the fluctuation history data of the oxygen content of the exhaust gas.

Preferably, the fluctuation historical data is historical data in which the time length of the data which abnormally operates within a preset time length is greater than a preset percentage of the preset time length.

Preferably, the oxygen content prediction model is obtained by: acquiring fluctuation historical data of the oxygen content of the tail gas; calculating a gray level correlation coefficient of the fluctuation historical data and the historical data of each of other sites at the same operation time; extracting the fluctuation historical data and historical data of other sites with the gray scale correlation coefficient larger than a correlation coefficient threshold, wherein the correlation coefficient threshold is related to whether tail gas continuously participates in the blasting reaction; and training based on the extracted data and the neural network to obtain the oxygen content prediction model.

Preferably, the gray scale correlation coefficient is calculated by the following formula:

wherein x is₀For fluctuating historical data, x_iThe historical data of the ith site in other sites at the same operation time is shown, rho is a preset coefficient, and k is the serial number of the historical data.

Preferably, when the tail gas continues to participate in the blasting reaction, the threshold value of the correlation coefficient is 0.6; when the tail gas does not continuously participate in the blasting reaction, the threshold value of the correlation coefficient is 0.8.

Preferably, the neural network training uses a MATLAB neural network.

Preferably, 70% of the fluctuation history data of the raffinate hydrogen peroxide concentration and the history data of other sites related to the fluctuation history data of the raffinate hydrogen peroxide concentration are used for training the hydrogen peroxide concentration prediction model, 15% of the data are used for testing the hydrogen peroxide concentration prediction model, and 15% of the data are used for verifying the hydrogen peroxide concentration prediction model.

The embodiment provides a device for calculating oxygen content in tail gas of a chemical device, which is similar to the first to fourth embodiments and is not repeated herein.

By adopting the technical scheme, the method, the device, the storage medium and the processor for calculating the oxygen content of the tail gas of the chemical device are adopted to detect the current data of other sites except the oxygen content of the tail gas of the chemical device; and calculating the oxygen content of the tail gas of the chemical device based on an oxygen content prediction model according to the current data of the other sites, wherein the oxygen content prediction model is obtained by performing neural network training on fluctuation historical data of the oxygen content of the tail gas and historical data of the other sites related to the fluctuation historical data of the oxygen content of the tail gas. According to the invention, the oxygen content is obtained according to the model after the model is built, and the safe operation of the chemical device is ensured without depending on manpower.

The chemical device tail gas oxygen content calculation device comprises a processor and a memory, wherein the detection unit, the processing unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel may be set to one or more, and the oxygen content (object of the present invention) is detected by adjusting the kernel parameters.

The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

The embodiment of the invention provides a storage medium, wherein a program is stored on the storage medium, and when the program is executed by a processor, the method for calculating the oxygen content of the tail gas of the chemical device is realized.

The embodiment of the invention provides a processor, which is used for running a program, wherein the program is run to execute the method for calculating the oxygen content of the tail gas of a chemical device.

The embodiment of the invention provides equipment, which comprises a processor, a memory and a program which is stored on the memory and can run on the processor, wherein the processor executes the program and realizes the following steps:

detecting current data of other sites except the oxygen content of the tail gas of the chemical device; and calculating the oxygen content of the tail gas of the chemical device based on an oxygen content prediction model according to the current data of the other sites, wherein the oxygen content prediction model is obtained by performing neural network training on fluctuation historical data of the oxygen content of the tail gas and historical data of the other sites related to the fluctuation historical data of the oxygen content of the tail gas.

The fluctuation historical data is historical data of which the time length of the data which abnormally operates in a preset time length is greater than a preset percentage of the preset time length.

The oxygen content prediction model is obtained by the following method: acquiring fluctuation historical data of the oxygen content of the tail gas; calculating a gray level correlation coefficient of the fluctuation historical data and the historical data of each of other sites at the same operation time; extracting the fluctuation historical data and historical data of other sites with the gray scale correlation coefficient larger than a correlation coefficient threshold, wherein the correlation coefficient threshold is related to whether tail gas continuously participates in the blasting reaction; and training based on the extracted data and the neural network to obtain the oxygen content prediction model.

The gray scale correlation coefficient is calculated by the following formula:

wherein x is₀For fluctuating historical data, x_iThe historical data of the ith site in other sites at the same operation time is shown, rho is a preset coefficient, and k is the serial number of the historical data.

When the tail gas continuously participates in the blasting reaction, the threshold value of the correlation coefficient is 0.6; when the tail gas does not continuously participate in the blasting reaction, the threshold value of the correlation coefficient is 0.8.

The neural network training uses a MATLAB neural network.

70% of the fluctuation historical data of the raffinate hydrogen peroxide concentration and the historical data of other sites related to the fluctuation historical data of the raffinate hydrogen peroxide concentration are used for training the hydrogen peroxide concentration prediction model, 15% of the data are used for testing the hydrogen peroxide concentration prediction model, and 15% of the data are used for verifying the hydrogen peroxide concentration prediction model.

The device herein may be a server, a PC, a PAD, a mobile phone, etc.

The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device:

detecting current data of other sites except the oxygen content of the tail gas of the chemical device; and calculating the oxygen content of the tail gas of the chemical device based on an oxygen content prediction model according to the current data of the other sites, wherein the oxygen content prediction model is obtained by performing neural network training on fluctuation historical data of the oxygen content of the tail gas and historical data of the other sites related to the fluctuation historical data of the oxygen content of the tail gas.

The fluctuation historical data is historical data of which the time length of the data which abnormally operates in a preset time length is greater than a preset percentage of the preset time length.

The oxygen content prediction model is obtained by the following method: acquiring fluctuation historical data of the oxygen content of the tail gas; calculating a gray level correlation coefficient of the fluctuation historical data and the historical data of each of other sites at the same operation time; extracting the fluctuation historical data and historical data of other sites with the gray scale correlation coefficient larger than a correlation coefficient threshold, wherein the correlation coefficient threshold is related to whether tail gas continuously participates in the blasting reaction; and training based on the extracted data and the neural network to obtain the oxygen content prediction model.

The gray scale correlation coefficient is calculated by the following formula:

wherein x is₀For fluctuating historical data, x_iThe historical data of the ith site in other sites at the same operation time is shown, rho is a preset coefficient, and k is the serial number of the historical data.

When the tail gas continuously participates in the blasting reaction, the threshold value of the correlation coefficient is 0.6; when the tail gas does not continuously participate in the blasting reaction, the threshold value of the correlation coefficient is 0.8.

Preferably, the neural network training uses a MATLAB neural network.

Preferably, 70% of the fluctuation history data of the raffinate hydrogen peroxide concentration and the history data of other sites related to the fluctuation history data of the raffinate hydrogen peroxide concentration are used for training the hydrogen peroxide concentration prediction model, 15% of the data are used for testing the hydrogen peroxide concentration prediction model, and 15% of the data are used for verifying the hydrogen peroxide concentration prediction model.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.

The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.