Nuclear power system operation abnormity root cause positioning method and system based on correlation analysis

Abstract

The invention provides a nuclear power system operation abnormity root cause positioning method and system based on correlation analysis, and the method comprises the steps: carrying out the correlation analysis of collected data based on a Pearson's correlation coefficient method, and obtaining a correlation coefficient matrix; performing correlation analysis on the correlation coefficient matrix based on a KMeans clustering algorithm to obtain a critical value of a cluster with a relatively large correlation coefficient as a feature threshold value; carrying out anomaly identification on the real-time data by adopting a LightGBM algorithm, and obtaining an abnormal measuring point sequence; and based on the characteristic threshold and the correlation coefficient matrix, obtaining an influence sequence of the abnormal measuring point sequence, calculating a correlation coefficient weight and obtaining a final root cause measuring point position. According to the nuclear power system operation abnormity root cause positioning method based on correlation analysis, the change condition of the system working condition can be self-adapted based on correlation analysis, the root cause measuring point can be automatically positioned, and the system operation abnormity can be represented.

Description

Technical Field

[0001] The present invention relates to the technical field of nuclear power operation and maintenance, and in particular to a method and system for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis. Background Art

[0002] With the popularization of nuclear power plant equipment sensors and the improvement of data collection technology, a large amount of data is continuously generated. This data contains important information such as equipment status, operating conditions, performance parameters, etc. How to efficiently use this data has become the key to improving operation and maintenance efficiency and safety.

[0003] Traditional anomaly recognition algorithms are based on supervised learning algorithms, which use abnormal sample data to train anomaly recognition models to identify whether nuclear power plant operating data conforms to the characteristics of historical anomalies.

[0004] However, due to the small amount of abnormal sample data in power plants, it is impossible to train abnormal recognition models based on traditional abnormal recognition algorithms, or it is impossible to effectively identify faults outside the model. The traditional call chain method based on topology structure is easier to implement for systems with simple scale, but the nuclear power plant system is abnormally complex, and it is impossible to list the call chains under all possible operating conditions in full.

[0005] Based on this, the inventor of the present application proposes a method and system for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis, in order to solve the above-mentioned technical problems. Summary of the invention

[0006] The technical problem to be solved by the present invention is to overcome the defect of great difficulty in analyzing abnormal operation of nuclear power systems in the prior art, and to provide a method and system for locating the root cause of abnormal operation of nuclear power systems based on correlation analysis.

[0007] The present invention solves the above technical problems through the following technical solutions:

[0008] The present invention provides a method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis, which is characterized in that it includes:

[0009] Step 1: Perform correlation analysis on the collected data based on the Pearson correlation coefficient method to obtain a correlation coefficient matrix;

[0010] Step 2: Perform correlation analysis on the correlation coefficient matrix based on the KMeans clustering algorithm, and obtain the critical value of the cluster with a larger correlation coefficient as the feature threshold;

[0011] Step 3: Use the LightGBM algorithm to identify anomalies in real-time data and obtain an abnormal measurement point sequence;

[0012] Step 4: Based on the characteristic threshold and the correlation coefficient matrix, the influence sequence of the abnormal measurement point sequence is obtained, the correlation coefficient weight is calculated, and the final root cause measurement point position is obtained.

[0013] According to one embodiment of the present invention, before step 1,

[0014] First, clean the collected data to remove outliers and null values.

[0015] According to one embodiment of the present invention, the cluster analysis steps in step 2 are as follows:

[0016] Based on the KMeans clustering algorithm, the correlation coefficient matrix is ​​clustered into two categories of data. First, two data are selected as the initial cluster centers, and the Euclidean distance of other collected data from the initial cluster center is calculated. These data are classified into the cluster where the nearest cluster center point is located. The average value of the data points of each class where the cluster center point is located is calculated and used as the new cluster center point until the cluster center no longer changes. The cluster with a larger correlation coefficient is output, and its boundary value is used as the feature threshold.

[0017] According to one embodiment of the present invention, the step between step 2 and step 3 further includes:

[0018] Based on the correlation coefficient matrix, for different adjustment variables, data with correlation coefficients greater than the characteristic threshold are screened as influence sequences.

[0019] According to one embodiment of the present invention, in step 4,

[0020] By building a working condition identification model, it is possible to determine whether the real-time data is abnormal.

[0021] According to one embodiment of the present invention, step 4 comprises:

[0022] Step 41: first collect the operating data of the power plant system under different operating conditions for a period of time, manually remove the abnormal data, and build a working condition recognition model based on the open source toolkit Lightgbm algorithm;

[0023] Step 42: input the real-time data into the operating condition identification model, and output the predicted operating condition and predicted probability corresponding to the current data; if the probability is greater than the set threshold, the predicted operating condition is correct, otherwise the predicted operating condition is wrong and the current real-time data is not within the normal operating condition range.

[0024] According to one embodiment of the present invention, step 4 further includes:

[0025] Step 43: find the correlation sequence greater than the characteristic threshold, obtain a measuring point sequence that meets the requirements, calculate the correlation coefficient weights of other measuring points with each measuring point, and take the maximum value as the final root cause measuring point.

[0026] The present invention also provides a nuclear power system operation abnormality root cause positioning system based on correlation analysis, which is characterized in that it is implemented by adopting the nuclear power system operation abnormality root cause positioning method based on correlation analysis as described above, and the positioning system includes:

[0027] The acquisition system is used to perform correlation analysis on the acquired data based on the Pearson correlation coefficient method to obtain a correlation coefficient matrix;

[0028] An analysis module is used to perform correlation analysis on the correlation coefficient matrix based on a KMeans clustering algorithm, and obtain a critical value of a cluster with a larger correlation coefficient as a feature threshold;

[0029] The recognition module is used to identify anomalies in real-time data using the LightGBM algorithm and obtain an abnormal measurement point sequence;

[0030] The calculation module is used to obtain the influence sequence of the abnormal measurement point sequence based on the characteristic threshold and the correlation coefficient matrix, calculate the correlation coefficient weight and obtain the final root cause measurement point position.

[0031] The present invention also provides an electronic device, comprising: a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and the programs or instructions are executed by the processor to implement the method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis as described above.

[0032] The present invention also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis as described above is implemented.

[0033] The positive and progressive effects of the present invention are:

[0034] The present invention is based on a method for locating the root cause of abnormal operation of a nuclear power system, which performs correlation analysis on the collected data to obtain a correlation coefficient matrix, and performs correlation analysis on the correlation coefficient matrix based on a KMeans clustering algorithm to obtain a critical value of a cluster with a larger correlation coefficient as a feature threshold, and then uses a LightGBM algorithm to identify abnormalities in real-time data and obtain an abnormal measurement point sequence, and finally obtains an influence sequence of the abnormal measurement point sequence based on the feature threshold and the correlation coefficient matrix, calculates the correlation coefficient weight and obtains the final root cause measurement point position. The present invention can adapt to changes in system operating conditions based on correlation analysis, automatically locate root cause measurement points, and characterize system operation abnormalities. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The above and other features, properties and advantages of the present invention will become more apparent through the following description in conjunction with the accompanying drawings and embodiments, in which:

[0036] Figure 1 It is a flow chart of the method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis of the present invention;

[0037] Figure 2 A schematic diagram of an implementation scheme of a correlation coefficient matrix of the present invention;

[0038] Figure 3 It is a schematic diagram of the structure of the electronic device of the present invention. DETAILED DESCRIPTION

[0039] The present invention is further described below in conjunction with specific embodiments and drawings. More details are elaborated in the following description to facilitate a full understanding of the present invention. However, the present invention can obviously be implemented in a variety of other ways different from the description herein. Those skilled in the art can make similar generalizations and deductions based on actual application situations without violating the connotation of the present invention. Therefore, the protection scope of the present invention should not be limited by the content of this specific embodiment.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0041] Reference Figure 1 The present invention proposes a method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis, comprising:

[0042] Step 1: Perform correlation analysis on the collected data based on the Pearson correlation coefficient method to obtain a correlation coefficient matrix.

[0043] It can be seen that before step 1, the collected data is cleaned to remove outliers and null values.

[0044] Then, for the collected data, the characteristic variables x1, x2...x n Conduct correlation analysis.

[0045] Specifically, the present invention uses the Pearson correlation coefficient method to perform correlation analysis and obtain a correlation coefficient matrix. The correlation coefficient is used to measure the degree of correlation between two variables, and its value is between -1 and 1. The larger the value, the higher the degree of correlation. A positive number indicates a positive correlation, and a negative number indicates a negative correlation.

[0046] For example, you can refer to Figure 2 , the higher the correlation, the darker the color. Pearson correlation coefficient ρ between two variables x,y , the analysis results correlation coefficient matrix is ​​as follows:

[0047] Among them, cov is the covariance and σ is the standard deviation.

[0048] Step 2: Perform correlation analysis on the correlation coefficient matrix based on the KMeans clustering algorithm, and obtain the critical value of the cluster with a larger correlation coefficient as the feature threshold.

[0049] The analysis is as follows:

[0050] Based on the correlation coefficient matrix in step 1, the correlation coefficient matrix is ​​clustered into 2 types of data based on the KMeans clustering algorithm. First, select 2 data as the initial cluster centers, calculate the Euclidean distance of other data from the cluster center, classify these data into the clusters where the nearest cluster center is located, calculate the average value of the data points in the class where each cluster center is located, and use it as the new cluster center u. Repeat the above steps until the cluster center no longer changes, output the cluster with the larger correlation coefficient, and use its boundary value as the feature threshold. The feature threshold is:

[0051]

[0052] Furthermore, based on the correlation coefficient matrix calculated in step 1, for different feature variables, the data with correlation coefficients greater than the feature threshold in step 2 are screened. i The filtered related variables are used as their influence series.

[0053] For example, the influence sequence of X1 is (X3, X7, X 12 ,X 14 ,X 27 ...), the influence sequence of X2 is (X1,X3,X4,X6...) and so on.

[0054] Step 3: Use the LightGBM algorithm to identify anomalies in real-time data and obtain an abnormal measurement point sequence.

[0055] The anomaly identification process is as follows:

[0056] Collect the operating data of the power plant system under different operating conditions for the past two years or a complete refueling cycle, and manually remove the data in abnormal time periods. Build an operating condition recognition model based on the open source toolkit LightGBM algorithm.

[0057] After the model is put into operation, for real-time data, the operating condition identification model will output the predicted operating condition and predicted probability p corresponding to the current data, and set the threshold to 0.7. That is, when the p value is greater than 0.7, the current data predicted operating condition is considered correct, otherwise it is wrong, that is, the current data is not within the normal operating condition range and is considered to be an abnormal situation.

[0058] Step 4: Based on the feature threshold and correlation coefficient matrix, the influence sequence of the abnormal measurement point sequence is obtained, the correlation coefficient weight is calculated, and the final root cause measurement point position is obtained.

[0059] It can be seen that during the operation of a nuclear power plant, if an abnormality occurs in a local part of the system, the data will change and then be transmitted outward, which will cause other data to change. The correlation coefficient can reflect the degree of change in the data.

[0060] For example, at a certain moment, there are multiple characteristic parameters X1, X2, X3...X j , calculate the influence sequence through steps 1 and 2, and then traverse the characteristic parameters to determine whether the correlation coefficient of the influence sequence of Xj is greater than the characteristic threshold in step 2. If it does not meet the requirements, it means that the abnormal source is not caused by the abnormality of the location monitored by Xj, until the parameter sequence X1, X2...X that meets the requirements is obtained. t , and finally we will get a measuring point sequence Xq that meets the requirements, where Xq is X1, X2...X q For each measuring point Xq, calculate the correlation coefficient weight and Tq of other measuring points and obtain the sequence Tq (T1, T2...Tq), and take the maximum value as the final root cause measuring point.

[0061] In summary, the present invention is based on the root cause location method of nuclear power system operation abnormality based on correlation analysis, performs correlation analysis on the collected data, obtains the correlation coefficient matrix, and performs correlation analysis on the correlation coefficient matrix based on the KMeans clustering algorithm, obtains the critical value of the cluster with a larger correlation coefficient as the feature threshold, and then uses the LightGBM algorithm to identify abnormalities in real-time data, and obtains the abnormal measurement point sequence, and finally obtains the influence sequence of the abnormal measurement point sequence based on the feature threshold and the correlation coefficient matrix, calculates the correlation coefficient weight and obtains the final root cause measurement point position. Based on correlation analysis, the present invention can adapt to changes in system operating conditions, automatically locate root cause measurement points, and can characterize system operation abnormalities.

[0062] The present invention also proposes a nuclear power system operation abnormality root cause positioning system based on correlation analysis, which is implemented by the nuclear power system operation abnormality root cause positioning method based on correlation analysis as described above. The positioning system includes:

[0063] The acquisition system is used to perform correlation analysis on the acquired data based on the Pearson correlation coefficient method to obtain a correlation coefficient matrix;

[0064] The analysis module is used to perform correlation analysis on the correlation coefficient matrix based on the KMeans clustering algorithm, and obtain the critical value of the cluster with a larger correlation coefficient as the feature threshold;

[0065] The recognition module is used to identify anomalies in real-time data using the LightGBM algorithm and obtain an abnormal measurement point sequence;

[0066] The calculation module is used to obtain the influence sequence of the abnormal measurement point sequence based on the characteristic threshold and the correlation coefficient matrix, calculate the correlation coefficient weight and obtain the final root cause measurement point position.

[0067] Reference Figure 3 The present invention also provides an electronic device 900, including: a processor 901 and a memory 902, the memory 902 stores a program or instruction that can be run on the processor 901, and the program or instruction is executed by the processor 901 to implement the above-mentioned method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis. When the program or instruction is executed by the processor 901, each process of the implementation method of the above-mentioned method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis is implemented, and the same technical effect can be achieved. In order to avoid repetition, it will not be repeated here.

[0068] The present invention also provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the above-mentioned method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis is implemented. When the program or instruction is executed by the processor, each process of the implementation method of the above-mentioned method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis is implemented, and the same technical effect can be achieved. In order to avoid repetition, it will not be repeated here.

[0069] For those skilled in the art, the above invention disclosure is only used as an example and does not constitute a limitation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary implementation of the present application.

[0070] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0071] Some aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". The processor may be one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DAPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, or combinations thereof. In addition, various aspects of the present application may be expressed as computer products located in one or more computer-readable media, which include computer-readable program codes. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, tapes ...), optical disks (e.g., compact disks CDs, digital versatile disks DVDs ...), smart cards, and flash memory devices (e.g., cards, sticks, key drives ...).

[0072] A computer-readable medium may include a propagated data signal containing computer program code, such as in baseband or as part of a carrier wave. The propagated signal may have a variety of manifestations, including electromagnetic, optical, etc., or a suitable combination. A computer-readable medium may be any computer-readable medium other than a computer-readable storage medium, which may be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit a program for use. The program code on the computer-readable medium may be propagated via any suitable medium, including radio, cable, fiber optic cable, radio frequency signal, or similar medium, or any combination of the above mediums.

[0073] Similarly, it should be noted that in order to simplify the description disclosed in this application, so as to help understand one or more embodiments of the invention, in the above description of the embodiments of the present application, sometimes multiple features are merged into one embodiment, drawings or descriptions thereof. However, this disclosure method does not mean that the features required by the object of the present application are more than the features mentioned in the claims. In fact, the features of the embodiment are less than all the features of the single embodiment disclosed above. In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "approximately", "approximately" or "substantially" in some examples. Unless otherwise specified, "approximately", "approximately" or "substantially" indicate that the number allows a variation of ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of the present application are approximate values, in specific embodiments, such numerical settings are as accurate as possible within the feasible range.

[0074] Although the present invention is disclosed as above in terms of preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art may make possible changes and modifications without departing from the spirit and scope of the present invention. Therefore, any modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention shall fall within the scope of protection defined by the claims of the present invention.

[0075] Although the present invention is disclosed as above with preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art may make possible changes and modifications without departing from the spirit and scope of the present invention. Therefore, any modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention shall fall within the protection scope defined by the claims of the present invention.

Claims

1. A method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis, characterized in that: include: Step 1: Perform correlation analysis on the collected data based on the Pearson correlation coefficient method to obtain a correlation coefficient matrix; Step 2: Perform correlation analysis on the correlation coefficient matrix based on the KMeans clustering algorithm, and obtain the critical value of the cluster with a larger correlation coefficient as the feature threshold; Step 3: Use the LightGBM algorithm to identify anomalies in real-time data and obtain an abnormal measurement point sequence; Step 4: Based on the characteristic threshold and the correlation coefficient matrix, the influence sequence of the abnormal measurement point sequence is obtained, the correlation coefficient weight is calculated, and the final root cause measurement point position is obtained.

2. The method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis according to claim 1 is characterized in that: Before step 1, First, clean the collected data to remove outliers and null values.

3. The method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis according to claim 1 is characterized in that: The cluster analysis steps of step 2 are as follows: Based on the KMeans clustering algorithm, the correlation coefficient matrix is ​​clustered into two categories of data. First, two data are selected as the initial cluster centers, and the Euclidean distance of other collected data from the initial cluster center is calculated. These data are classified into the cluster where the nearest cluster center point is located. The average value of the data points of each class where the cluster center point is located is calculated and used as the new cluster center point until the cluster center no longer changes. The cluster with a larger correlation coefficient is output, and its boundary value is used as the feature threshold.

4. The method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis according to claim 1 is characterized in that: The steps 2 and 3 also include: Based on the correlation coefficient matrix, for different adjustment variables, data with correlation coefficients greater than the characteristic threshold are screened as influence sequences.

5. The method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis according to claim 4 is characterized in that: In step 4, By building a working condition identification model, it is possible to determine whether the real-time data is abnormal.

6. The method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis according to claim 4 is characterized in that: The step 4 comprises: Step 41: first collect the operating data of the power plant system under different operating conditions for a period of time, manually remove the abnormal data, and build a working condition recognition model based on the open source toolkit Lightgbm algorithm; Step 42: input the real-time data into the operating condition identification model, and output the predicted operating condition and predicted probability corresponding to the current data; if the probability is greater than the set threshold, the predicted operating condition is correct, otherwise the predicted operating condition is wrong and the current real-time data is not within the normal operating condition range.

7. The method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis according to claim 6 is characterized in that: The step 4 also includes: Step 43: find the correlation sequence greater than the characteristic threshold, obtain a measuring point sequence that meets the requirements, calculate the correlation coefficient weights of other measuring points with each measuring point, and take the maximum value as the final root cause measuring point.

8. A nuclear power system operation abnormality root cause location system based on correlation analysis, characterized in that: The method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis as described in any one of claims 1 to 7 is adopted, and the locating system comprises: The acquisition system is used to perform correlation analysis on the acquired data based on the Pearson correlation coefficient method to obtain a correlation coefficient matrix; An analysis module is used to perform correlation analysis on the correlation coefficient matrix based on a KMeans clustering algorithm, and obtain a critical value of a cluster with a larger correlation coefficient as a feature threshold; The recognition module is used to identify anomalies in real-time data using the LightGBM algorithm and obtain an abnormal measurement point sequence; The calculation module is used to obtain the influence sequence of the abnormal measurement point sequence based on the characteristic threshold and the correlation coefficient matrix, calculate the correlation coefficient weight and obtain the final root cause measurement point position.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and the programs or instructions are executed by the processor to implement the method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the method for locating the root cause of abnormal operation of a nuclear power system based on correlation analysis as described in any one of claims 1 to 7 is implemented.

Images