An analysis method and related device based on control system operation data

Abstract

The present invention discloses an analysis method based on control system operation data, by first splicing the independent variables to be analyzed into a character string, and then selecting reference characters from the character string in sequence to arrange the operation data, the data that are as identical as possible can be arranged together, thereby facilitating the specific calculation of the subsequent operation data matrix and the specific calculation of the distance between them, and the data to be analyzed can be quickly generated, so that the operation data can be analyzed accurately and efficiently. The present invention also provides a device, equipment and storage medium, which also have the above-mentioned beneficial effects.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to an analysis method based on control system operation data, an analysis device based on control system operation data, an analysis equipment based on control system operation data, and a computer-readable storage medium. Background Art

[0002] In the long-term operation of DCS (Distributed Control System), a lot of equipment operation data will be accumulated, such as the excess air coefficient of the boiler, the blowing wind speed, the wind temperature, the temperature inside the blast furnace and other data. At present, according to the DCS control system, the data generated by the DCS control system will be used to analyze and predict the corresponding matters. Before using the data generated by the DCS control system, the original data generated by the DCS control system will usually be screened first, and the screening results have a direct impact on the subsequent analysis and prediction results. Therefore, how to provide an accurate and efficient operation data analysis method is an urgent problem to be solved by technicians in this field. Summary of the invention

[0003] An object of the present invention is to provide an analysis method based on control system operation data, which can accurately and efficiently analyze the operation data; another object of the present invention is to provide an analysis device based on control system operation data, an analysis equipment based on control system operation data and a computer-readable storage medium, which can accurately and efficiently analyze the operation data.

[0004] In order to solve the above technical problems, the present invention provides an analysis method based on control system operation data, comprising:

[0005] Acquire the operation data generated by the target control system during operation;

[0006] Concatenate the independent variables that need to be analyzed corresponding to the running data into a character string;

[0007] Selecting the first preset number of characters of the character string in order from front to back as reference characters, and sorting the operation data according to the reference characters after each selection; the preset number increases with the increase in the number of selections;

[0008] After sorting the operation data, formatting the sorted operation data into multiple groups of operation data matrices, calculating the distance between any two groups of operation data matrices, eliminating the operation data corresponding to the distance greater than the distance threshold, and generating data to be analyzed;

[0009] The data to be analyzed is analyzed.

[0010] Optionally, after selecting the first preset number of characters of the character string in order from front to back as reference characters, and sorting the operation data according to the reference characters after each selection of the reference characters, the method further includes:

[0011] After sorting the operation data, deleting duplicate data in the operation data;

[0012] After the operation data is sorted, the sorted operation data is formatted into multiple groups of operation data matrices, and the distance between any two groups of operation data matrices is calculated, and the operation data corresponding to the distance greater than the distance threshold is eliminated, and the data to be analyzed is generated, including:

[0013] After deleting the duplicate data, the sorted operation data is formatted into multiple groups of operation data matrices, and the distance between any two groups of operation data matrices is calculated, and the operation data corresponding to the distance greater than the distance threshold is eliminated to generate data to be analyzed.

[0014] Optionally, after sorting the operation data, deleting duplicate data in the operation data includes:

[0015] Selecting the operation data in sequence through a sliding window;

[0016] The selected operation data in the sliding window are compared, and duplicate data in the operation data are deleted.

[0017] Optionally, analyzing the data to be analyzed includes:

[0018] Perform multiple regression analysis on the data to be analyzed to generate a regression equation.

[0019] Optionally, after performing multivariate regression analysis on the data to be analyzed and generating a regression equation, the method further includes:

[0020] The regression equation was verified by the regression coefficient significance test.

[0021] Optionally, after verifying the regression equation by the regression coefficient significance test, the method further includes:

[0022] According to the regression equation that passes the regression coefficient significance test, the maximum value and / or minimum value of the regression equation is obtained as a standard value for effectiveness screening.

[0023] The present invention also provides an analysis device based on control system operation data, comprising:

[0024] An acquisition module, used for acquiring operation data generated by the target control system during operation;

[0025] A concatenation module, used for concatenating the independent variables corresponding to the operation data to be analyzed into a character string;

[0026] A sorting module, used for selecting the first preset number of characters of the character string in order from front to back as reference characters, and sorting the operation data according to the reference characters after each selection of the reference characters; the preset number increases with the increase of the number of selections;

[0027] A distance screening module is used to format the sorted operation data into multiple groups of operation data matrices after sorting the operation data, calculate the distance between any two groups of operation data matrices, eliminate the operation data corresponding to the distance greater than the distance threshold, and generate data to be analyzed;

[0028] The analysis module is used to analyze the data to be analyzed.

[0029] Optionally, also include:

[0030] A de-duplication module, used to delete duplicate data in the operation data after sorting the operation data;

[0031] The distance screening module is specifically used for:

[0032] After deleting the duplicate data, the sorted operation data is formatted into multiple groups of matrices, and the distance between any two groups of matrices is calculated, and the operation data corresponding to the distance greater than the distance threshold is eliminated to generate data to be analyzed.

[0033] The present invention also provides an analysis device based on control system operation data, comprising:

[0034] Memory for storing computer programs;

[0035] A processor is used to implement the steps of the analysis method based on control system operation data as described in any of the above items when executing the computer program.

[0036] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the analysis method based on control system operation data as described in any one of the above items are implemented.

[0037] The present invention provides an analysis method based on control system operation data, comprising obtaining operation data generated by a target control system during operation; concatenating independent variables corresponding to the operation data to be analyzed into a character string; selecting the first preset number of characters of the character string in order from front to back as reference characters, and sorting the operation data according to the reference characters after each selection; the preset number increases with the increase in the number of selections; after sorting the operation data, formatting the sorted operation data into multiple groups of operation data matrices, calculating the distance between any two groups of operation data matrices, eliminating the operation data corresponding to the distance greater than the distance threshold, and generating data to be analyzed; and analyzing the data to be analyzed.

[0038] By first concatenating the independent variables to be analyzed into a character string, and then selecting reference characters from the character string in turn to arrange the running data, data that are as identical as possible can be arranged together, thereby facilitating the subsequent specific calculation of the running data matrix and the specific calculation of the distances therebetween, and quickly generating the data to be analyzed, thereby enabling accurate and efficient analysis of the running data.

[0039] The present invention also provides an analysis device based on control system operation data, an analysis equipment based on control system operation data and a computer-readable storage medium, which also have the above-mentioned beneficial effects and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 A flowchart of an analysis method based on control system operation data provided by an embodiment of the present invention;

[0042] Figure 2 A flowchart of a specific analysis method based on control system operation data provided by an embodiment of the present invention;

[0043] Figure 3 A structural block diagram of an analysis device based on control system operation data provided by an embodiment of the present invention;

[0044] Figure 4 This is a structural block diagram of an analysis device based on control system operation data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The core of the present invention is to provide an analysis method based on control system operation data. In the prior art, the data generated by the DCS control system is used to analyze and predict the corresponding matters. Before using the data generated by the DCS control system, the original data generated by the DCS control system is usually screened first, and the screening results have a direct impact on the subsequent analysis and prediction results.

[0046] The present invention provides an analysis method based on control system operation data, including obtaining operation data generated by a target control system during operation; concatenating independent variables corresponding to the operation data to be analyzed into a character string; selecting the first preset number of characters of the character string in order from front to back as reference characters, and sorting the operation data according to the reference characters after each selection; the preset number increases with the increase in the number of selections; after sorting the operation data, formatting the sorted operation data into multiple groups of operation data matrices, and calculating the distance between any two groups of operation data matrices, eliminating the operation data corresponding to the distance greater than the distance threshold, and generating data to be analyzed; and analyzing the data to be analyzed.

[0047] By first concatenating the independent variables to be analyzed into a character string, and then selecting reference characters from the character string in turn to arrange the running data, data that are as identical as possible can be arranged together, thereby facilitating the subsequent specific calculation of the running data matrix and the specific calculation of the distances therebetween, and quickly generating the data to be analyzed, thereby enabling accurate and efficient analysis of the running data.

[0048] In order to enable those skilled in the art to better understand the scheme of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0049] Please refer to Figure 1 , Figure 1 The present invention provides a flowchart of an analysis method based on control system operation data in an embodiment of the present invention.

[0050] See also Figure 1 In an embodiment of the present invention, the analysis method based on the control system operation data includes:

[0051] S101: Acquire operation data generated by the target control system during operation.

[0052] In this step, the operation data generated by the DCS control system as the target control system during operation, i.e., historical data, also called raw data, will first be extracted. In the embodiment of the present invention, there is no specific limitation on the specific type of the above operation data, which needs to be determined according to the specific application field of the target control system. For example, if the target control system is specifically applied to a thermal power unit, the above operation data may include the air excess coefficient of the boiler, the blowing wind speed, the wind temperature, the temperature inside the blast furnace, and other data.

[0053] S102: concatenate the independent variables corresponding to the running data to be analyzed into a character string.

[0054] As for the above-mentioned operation data, since it is specifically the data generated by the target control system, the operation data at this time usually has the characteristics of high uniformity of expression, good integrity of data information, and a large amount of data repetition. Correspondingly, in this step, the independent variables that need to be analyzed for the above-mentioned various operation data will be spliced ​​into a string. The independent variable is the factor that needs to be analyzed, which is equivalent to the category of the operation data that needs to be analyzed. In this step, the independent variables that need to be analyzed will first be spliced ​​into a string so that the operation data can be sorted later.

[0055] S103: Selecting the first preset number of characters of the character string in order from front to back as reference characters, and sorting the running data according to the reference characters after each reference character is selected.

[0056] In an embodiment of the present invention, the preset number increases as the number of selections increases. That is, in this step, the first preset number of characters in the character string generated by S102 will be selected as reference characters first, usually the first character will be selected as the reference character first, and the character string will be divided into two parts, one part is the selected reference character, and the other part is the remaining characters in the character string. On this basis, the operation data will be sorted according to the character string divided into two parts, that is, according to the reference characters. Since the operation data is specifically divided into pieces, and each piece of data usually represents various types of operation data generated by the target control system at the same time, each piece of data will include multiple specific operation data.

[0057] In this step, after a reference character is selected, the entries in the running data can be sorted according to the specific values ​​of the running data corresponding to the reference character according to the preset rules, specifically in the order from large to small or from small to large, to achieve the sorting of the running data. After the sorting is completed once, the preset number will be increased in this step, that is, the length of the reference character selected at the beginning of the string will be increased, and then a new reference character will be selected according to the increased preset number, and the process of sorting the running data will be re-executed, usually until the preset number is greater than the length of the string generated in S102.

[0058] It should be noted that, in the embodiment of the present invention, except for the first selection of reference characters, each selection of reference characters will include the previous reference characters, so the order of sorting the corresponding running data according to the reference characters in the previous time will not be disrupted. For example, in this step, the first character and the remaining characters of the string can be divided into two parts first, and the running data can be sorted for the first time; then the first two characters of the string are used as the first part, and the remaining characters are used as the second part to sort the running data after the first sorting; repeat this process continuously, so that running data that is as similar as possible can be arranged together. In the embodiment of the present invention, there is no specific limitation on the size of each increase in the above-mentioned preset number, which depends on the specific situation.

[0059] S104: After sorting the operation data, format the sorted operation data into multiple groups of operation data matrices, calculate the distance between any two groups of operation data matrices, eliminate the operation data corresponding to the distance greater than the distance threshold, and generate data to be analyzed.

[0060] In the embodiment of the present invention, each piece of operation data can be formatted into a set of operation data matrices, so that the sorted operation data can be formatted into multiple sets of operation data matrices. At this time, each set of operation data matrices has its corresponding eigenvalue. Afterwards, the distance between any two sets of operation data matrices can be calculated in this step. The calculation formula of the distance is as follows:

[0061]

[0062] Where A and B represent two groups of running data matrices, x and y are the eigenvalues ​​corresponding to the running data matrices of group A and group B respectively, and n is the data position in each running data matrix.

[0063] In an embodiment of the present invention, a distance threshold is preset, and then the operating data corresponding to the distance greater than the distance threshold is eliminated to generate the data to be analyzed. Obviously, the calculation order of the above distances will be executed according to the final arrangement order of the above operating data, and the distance between the operating data matrices corresponding to the operating data arranged in the front is obviously less, while the difference in the arrangement order is large, then the distance between the operating data matrices corresponding to the operating data will be larger. Therefore, in this step, when the calculated distance is greater than the preset distance threshold, the operating data corresponding to the operating data matrix arranged in the back will be deleted. It should be noted that the above distance threshold can be a fixed value or a dynamic value determined according to all the calculated distances, depending on the specific circumstances, and is not specifically limited here.

[0064] S105: Analyze the data to be analyzed.

[0065] The specific analysis process will be described in detail in the following embodiments of the invention and will not be described in detail here.

[0066] An analysis method based on control system operation data provided by an embodiment of the present invention includes obtaining operation data generated by a target control system during operation; concatenating independent variables corresponding to the operation data to be analyzed into a character string; selecting the first preset number of characters of the character string in order from front to back as reference characters, and sorting the operation data according to the reference characters after each selection; the preset number increases with the increase in the number of selections; after sorting the operation data, formatting the sorted operation data into multiple groups of operation data matrices, and calculating the distance between any two groups of operation data matrices, eliminating the operation data corresponding to the distance greater than the distance threshold, and generating data to be analyzed; and analyzing the data to be analyzed.

[0067] By first concatenating the independent variables to be analyzed into a character string, and then selecting reference characters from the character string in turn to arrange the running data, data that are as identical as possible can be arranged together, thereby facilitating the subsequent specific calculation of the running data matrix and the specific calculation of the distances therebetween, and quickly generating the data to be analyzed, thereby enabling accurate and efficient analysis of the running data.

[0068] The specific contents of the analysis method based on control system operation data provided by the present invention will be described in detail in the following invention embodiments.

[0069] Please refer to Figure 2 , Figure 2 The present invention provides a flowchart of a specific analysis method based on control system operation data.

[0070] See also Figure 2In an embodiment of the present invention, the analysis method based on the control system operation data includes:

[0071] S201: Acquire operation data generated by the target control system during operation.

[0072] S202: concatenate the independent variables corresponding to the running data to be analyzed into a character string.

[0073] S203: Selecting the first preset number of characters of the character string in order from front to back as reference characters, and sorting the running data according to the reference characters after each reference character is selected.

[0074] The above S201 to S203 are basically the same as S101 to S103 in the above invention embodiment. Please refer to the above invention embodiment for details, which will not be repeated here.

[0075] S204: After sorting the operation data, delete duplicate data in the operation data.

[0076] In this step, it is necessary to delete duplicate data in the running data, and the so-called duplicate data is exactly the same data. In this step, it is necessary to delete duplicate data in the running data to reduce the amount of calculation in subsequent steps.

[0077] Specifically, this step may specifically include: selecting the operating data in sequence through a sliding window; comparing the operating data selected in the sliding window, and deleting duplicate data in the operating data. That is, in this step, the above-mentioned duplicate data can be deleted specifically by setting a sliding window. In an embodiment of the present invention, a sliding window with a size of W data can be pre-set. When using a sliding window, the first record that enters the sliding window will slide out of the sliding window, and the next record of the last record will enter the sliding window, thereby achieving: selecting the operating data in sequence through a sliding window; comparing the newly entered data with the data in the sliding window to determine whether the data is the same, and then in this step, it is necessary to delete the same data in the sliding window, that is, duplicate data. Using a sliding window can increase the speed of eliminating the same data.

[0078] S205: After deleting duplicate data, format the sorted operation data into multiple groups of operation data matrices, calculate the distance between any two groups of operation data matrices, eliminate the operation data corresponding to the distance greater than the distance threshold, and generate data to be analyzed.

[0079] In this step, the operation data after the duplicate data is removed in the above S204 is specifically used to format it into an operation data matrix, the distance between any two sets of operation data matrices is calculated, and part of the operation data is removed according to the above distance to generate the data to be analyzed. Compared with the above S104, the difference between this step and the above S104 is that in this step, the data to be analyzed is specifically generated according to the operation data after the duplicate data is removed, and the rest of the content is basically the same as S104 in the above invention embodiment. Please refer to the above invention embodiment for details, and no further description will be given here.

[0080] S206: Perform multiple regression analysis on the data to be analyzed to generate a regression equation.

[0081] In this step, the data to be analyzed is modeled using a multivariate linear regression method. Specifically, in this embodiment of the present invention, it is assumed that x 1 ,x 2 ,…x p There are p (p ≥ 2) related parameters, and y is the actual performance value of the final equipment. Then the specific model established by the multiple regression analysis is:

[0082] y=β 0 +β 1 x 1 +β 1 x 1 +…β p x p +ε

[0083] ε~N(0,σ 2 )

[0084] Among them, β 0 ,β 1 ,β 2 ,…β p There are p+1 parameters, among which β 0 is the regression constant; β 1 ,β 2 ,…β p can be used as the weight value of different parameters, and ε~N(0,σ 2 ) is a random error. Specifically, in this step, the least squares method can be used to calculate the minimum error between the estimated value and the sample value, and finally the required coefficient β and constant ε are obtained by matrix solution to generate the final regression equation.

[0085] S207: Verify the regression equation through regression coefficient significance test.

[0086] In this step, the above regression equation can be verified by a regression coefficient significance test to confirm whether the above regression equation is meaningful. Usually, when the significance level calculated by the above regression coefficient significance test is less than 0.05, the regression equation can be considered to be meaningful. The specific content of the regression coefficient significance test can be referred to the prior art, and will not be repeated here.

[0087] S208: According to the regression equation that passes the regression coefficient significance test, the maximum value and / or minimum value of the regression equation is obtained as a standard value for effectiveness screening.

[0088] In this step, the mathematical model obtained by the multivariate linear regression method in S206 to S207 is subjected to multi-data simulation to form a final effective value screening and provide the validity of the input data. In this step, the maximum value, minimum value, or maximum value and minimum value of the regression equation can be obtained through the above regression equation, so as to serve as the standard value for validity screening.

[0089] An analysis method based on control system operation data provided by an embodiment of the present invention can arrange data that are as identical as possible together by first concatenating the independent variables to be analyzed into a character string, and then selecting reference characters from the character string in sequence to arrange the operation data, thereby facilitating the subsequent specific calculation of the operation data matrix and the specific calculation of the distances therebetween, and can quickly generate data to be analyzed, thereby achieving accurate and efficient analysis of the operation data.

[0090] An analysis device based on control system operation data provided by an embodiment of the present invention is introduced below. The analysis device based on control system operation data described below and the analysis method based on control system operation data described above can refer to each other.

[0091] Figure 3 A structural block diagram of an analysis device based on control system operation data provided by an embodiment of the present invention, referring to Figure 3 , the analysis device based on the control system operation data may include:

[0092] The acquisition module 100 is used to acquire the operation data generated by the target control system during operation.

[0093] The concatenation module 200 is used to concatenate the independent variables corresponding to the operation data to be analyzed into a character string.

[0094] The sorting module 300 is used to select the first preset number of characters of the string as reference characters in order from front to back, and sort the running data according to the reference characters after each selection; the preset number increases with the increase in the number of selections.

[0095] The distance screening module 400 is used to format the sorted operating data into multiple groups of operating data matrices after sorting the operating data, calculate the distance between any two groups of operating data matrices, eliminate the operating data corresponding to the distance greater than the distance threshold, and generate data to be analyzed.

[0096] The analysis module 500 is used to analyze the data to be analyzed.

[0097] Preferably, in the embodiment of the present invention, it also includes:

[0098] A de-duplication module, used to delete duplicate data in the operation data after sorting the operation data;

[0099] The distance screening module is specifically used for:

[0100] After deleting the duplicate data, the sorted operation data is formatted into multiple groups of matrices, and the distance between any two groups of matrices is calculated, and the operation data corresponding to the distance greater than the distance threshold is eliminated to generate data to be analyzed.

[0101] Preferably, in an embodiment of the present invention, the deduplication module includes:

[0102] The sliding selection unit is used to select the operation data in sequence through a sliding window.

[0103] The sliding deletion unit is used to compare the operation data selected in the sliding window and delete duplicate data in the operation data.

[0104] Preferably, in the embodiment of the present invention, the analysis module 500 is specifically used for:

[0105] Perform multiple regression analysis on the data to be analyzed to generate a regression equation.

[0106] Preferably, in the embodiment of the present invention, it also includes:

[0107] The verification module is used to verify the regression equation through a regression coefficient significance test.

[0108] Preferably, in the embodiment of the present invention, it also includes:

[0109] The standard value module is used to obtain the maximum value and / or minimum value of the regression equation as the standard value for effectiveness screening according to the regression equation that passes the regression coefficient significance test.

[0110] The analysis device based on control system operation data of this embodiment is used to implement the aforementioned analysis method based on control system operation data. Therefore, the specific implementation method of the analysis device based on control system operation data can be seen in the embodiment part of the analysis method based on control system operation data in the previous text. For example, the acquisition module 100, the splicing module 200, the sorting module 300, the distance screening module 400, and the analysis module 500 are respectively used to implement steps S101 to S105 in the above-mentioned analysis method based on control system operation data. Therefore, its specific implementation method can refer to the description of the corresponding each part of the embodiment, which will not be repeated here.

[0111] An analysis device based on control system operation data provided in an embodiment of the present invention is introduced below. The analysis device based on control system operation data described below and the analysis method based on control system operation data and the analysis device based on control system operation data described above can be referenced to each other.

[0112] Please refer to Figure 4 , Figure 4 This is a structural block diagram of an analysis device based on control system operation data provided by an embodiment of the present invention.

[0113] Reference Figure 4 The analysis device based on the control system operation data may include a processor 11 and a memory 12 .

[0114] The memory 12 is used to store computer programs; the processor 11 is used to implement the analysis method based on control system operation data described in the above-mentioned embodiment of the invention when executing the computer program.

[0115] The processor 11 in the analysis device based on control system operation data of this embodiment is used to install the analysis device based on control system operation data described in the above invention embodiments, and the processor 11 combined with the memory 12 can realize the analysis method based on control system operation data described in any of the above invention embodiments. Therefore, the specific implementation of the analysis device based on control system operation data can be seen in the embodiment of the analysis method based on control system operation data in the above text, and its specific implementation can refer to the description of the corresponding various partial embodiments, which will not be repeated here.

[0116] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, an analysis method based on control system operation data introduced in any of the above-mentioned embodiments of the invention is implemented. The rest of the content can refer to the prior art and will not be described in detail here.

[0117] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0118] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0119] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0120] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0121] The above is a detailed introduction to an analysis method based on control system operation data, an analysis device based on control system operation data, an analysis equipment based on control system operation data, and a computer-readable storage medium provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present invention, the present invention can also be improved and modified in a number of ways, and these improvements and modifications also fall within the scope of protection of the claims of the present invention.

Claims

1. An analysis method based on control system operation data, characterized in that: include: Acquire the operation data generated by the target control system during operation; Concatenate the independent variables that need to be analyzed corresponding to the running data into a character string; Selecting the first preset number of characters of the character string in order from front to back as reference characters, and sorting the operation data according to the reference characters after each selection of the reference characters; The preset number increases as the number of selections increases; After sorting the operation data, formatting the sorted operation data into multiple groups of operation data matrices, calculating the distance between any two groups of operation data matrices, eliminating the operation data corresponding to the distance greater than the distance threshold, and generating data to be analyzed; Analyzing the data to be analyzed; The step of calculating the distance between any two sets of running data matrices includes: According to the operation data matrix, the eigenvalues ​​corresponding to the operation data matrix, the data positions in the operation data matrix and Calculate the distance between any two sets of running data matrices; Where A and B represent two groups of running data matrices, x and y are the eigenvalues ​​corresponding to the running data matrix of group A and the running data matrix of group B respectively, n is the data position in each running data matrix, and d is the distance between the running data matrix of group A and the running data matrix of group B.

2. The method according to claim 1, characterized in that After selecting the first preset number of characters of the character string in order from front to back as reference characters, and sorting the operation data according to the reference characters after selecting the reference characters each time, the method further includes: After sorting the operation data, deleting duplicate data in the operation data; After the operation data is sorted, the sorted operation data is formatted into multiple groups of operation data matrices, and the distance between any two groups of operation data matrices is calculated, and the operation data corresponding to the distance greater than the distance threshold is eliminated, and the data to be analyzed is generated, including: After deleting the duplicate data, the sorted operation data is formatted into multiple groups of operation data matrices, and the distance between any two groups of operation data matrices is calculated, and the operation data corresponding to the distance greater than the distance threshold is eliminated to generate data to be analyzed.

3. The method according to claim 2, characterized in that After sorting the operation data, deleting duplicate data in the operation data includes: Selecting the operation data in sequence through a sliding window; The selected operation data in the sliding window are compared, and duplicate data in the operation data are deleted.

4. The method according to claim 1, characterized in that: The analyzing the data to be analyzed comprises: Perform multiple regression analysis on the data to be analyzed to generate a regression equation.

5. The method according to claim 4, characterized in that After performing multiple regression analysis on the data to be analyzed and generating a regression equation, the method further includes: The regression equation was verified by the regression coefficient significance test.

6. The method according to claim 5, characterized in that After verifying the regression equation by the regression coefficient significance test, the method further includes: According to the regression equation that passes the regression coefficient significance test, the maximum value and / or minimum value of the regression equation is obtained as a standard value for effectiveness screening.

7. An analysis device based on control system operation data, characterized in that: include: An acquisition module, used for acquiring operation data generated by the target control system during operation; A concatenation module, used for concatenating the independent variables corresponding to the operation data to be analyzed into a character string; A sorting module, used for selecting the first preset number of characters of the character string in order from front to back as reference characters, and sorting the operation data according to the reference characters after selecting the reference characters each time; The preset number increases as the number of selections increases; A distance screening module is used to format the sorted operation data into multiple groups of operation data matrices after sorting the operation data, calculate the distance between any two groups of operation data matrices, eliminate the operation data corresponding to the distance greater than the distance threshold, and generate data to be analyzed; An analysis module, used for analyzing the data to be analyzed; Wherein, the distance screening module is specifically used for: According to the operation data matrix, the eigenvalues ​​corresponding to the operation data matrix, the data positions in the operation data matrix and Calculate the distance between any two sets of running data matrices; Where A and B represent two groups of running data matrices, x and y are the eigenvalues ​​corresponding to the running data matrix of group A and the running data matrix of group B respectively, n is the data position in each running data matrix, and d is the distance between the running data matrix of group A and the running data matrix of group B.

8. The device according to claim 7, characterized in that Also includes: A de-duplication module, used to delete duplicate data in the operation data after sorting the operation data; The distance screening module is specifically used for: After deleting the duplicate data, the sorted operation data is formatted into multiple groups of matrices, and the distance between any two groups of matrices is calculated, and the operation data corresponding to the distance greater than the distance threshold is eliminated to generate data to be analyzed.

9. An analysis device based on control system operation data, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the analysis method based on control system operation data as claimed in any one of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the analysis method based on control system operation data as claimed in any one of claims 1 to 6 are implemented.

Images