Secondary circuit fault diagnosis method and system of relay protection device

Abstract

The invention relates to the technical field of power equipment, and particularly discloses a secondary circuit fault diagnosis method and system for a relay protection device, and the method comprises the steps: obtaining node power parameters of a secondary circuit of the relay protection device, and screening out abnormal nodes of the secondary circuit according to the node power parameters; obtaining the fault characteristics of the abnormal nodes of the secondary circuit, and determining the fault type of the secondary circuit according to the fault characteristics of the abnormal nodes of the secondary circuit; and establishing a fault maintenance model, inputting the fault type of the secondary circuit into the fault diagnosis model, and obtaining a maintenance strategy corresponding to the fault type. According to the invention, the fault of the secondary circuit of the relay protection device can be accurately detected, the fault is diagnosed in time, a maintenance strategy is output, hidden dangers are eliminated in time, and safe operation of a power system is ensured.

Description

Technical Field

[0001] The present application relates to the technical field of electric power equipment, and more specifically, to a secondary circuit fault diagnosis method and system for a relay protection device. Background Art

[0002] The secondary circuit is an electrical circuit that monitors, controls, measures, regulates and protects the operation of the primary equipment. The circuit is composed of measuring instruments, relays, control and signal elements, automatic devices, relay protection devices, current and voltage transformers, etc. connected according to certain requirements. Relay protection equipment is an important part of the power system and plays a key and decisive role in ensuring the safe and economical operation of the power system and preventing accidents from occurring and expanding. In recent years, hidden dangers in secondary circuits such as AC current, voltage or switching quantity have caused accidents of misoperation of protection equipment.

[0003] The actual operation of the power grid shows that the hidden fault defects in the secondary circuit of the relay protection are one of the causes of the relay protection system accidents. However, due to the complex wiring of the secondary circuit of the system, it is very difficult to carry out reasonable and effective secondary circuit maintenance. Summary of the invention

[0004] The present invention provides a secondary circuit fault diagnosis method and system for a relay protection device, which is used to solve the problem in the prior art that the secondary circuit of the relay protection device cannot timely and effectively diagnose and detect faults, including:

[0005] Obtain node power parameters of the secondary circuit of the relay protection device, and screen out abnormal nodes of the secondary circuit according to the node power parameters;

[0006] Obtaining fault characteristics of abnormal nodes in the secondary circuit, and determining the fault type of the secondary circuit according to the fault characteristics of the abnormal nodes in the secondary circuit;

[0007] A fault maintenance model is established, the fault type of the secondary circuit is input into the fault diagnosis model, and the maintenance strategy corresponding to the fault type is obtained.

[0008] Furthermore, screening out abnormal nodes of the secondary circuit according to the node power parameters includes:

[0009] Obtaining the voltage value of each node of the secondary circuit of the relay protection device, and determining the voltage stability parameter according to the voltage value of each node of the secondary circuit of the relay protection device;

[0010] Nodes whose voltage values ​​are greater than the voltage stability parameter are screened out according to the voltage stability parameter, the difference between the node whose voltage value is greater than the voltage stability parameter and each adjacent node is calculated, and the average value of the difference is calculated according to the difference between the node whose voltage value is greater than the voltage stability parameter and each adjacent node;

[0011] It is determined whether the average value of the difference is greater than a first preset threshold value. If the average value of the difference is greater than the first preset threshold value, the node whose average value of the difference is greater than the first preset threshold value is determined as an abnormal node.

[0012] Furthermore, the voltage stability parameter is determined according to the voltage value of each node of the secondary circuit of the relay protection device, including:

[0013] Determine the average voltage value of all nodes according to the voltage value of each node of the secondary circuit of the relay protection device, and determine the initial voltage stability parameter according to the average voltage value of all nodes;

[0014] Obtain the ambient temperature of the secondary circuit of the relay protection device and calculate the difference between the ambient temperature and the preset standard ambient temperature;

[0015] The difference between the ambient temperature and the preset standard ambient temperature is normalized, and the initial voltage stability parameter is corrected according to the difference between the ambient temperature after the normalization and the preset standard ambient temperature to obtain the voltage stability parameter.

[0016] Furthermore, the initial voltage stability parameter is corrected according to the difference between the normalized ambient temperature and the preset standard ambient temperature, including:

[0017] The initial voltage stability parameter is corrected according to the voltage stability parameter correction formula, and the voltage stability parameter correction formula is specifically:

[0018]

[0019] Among them, S is the voltage stability parameter, S α is the preset standard voltage stability parameter, T is the difference between the normalized ambient temperature and the preset standard ambient temperature, T α It is the preset standard temperature difference.

[0020] Further, determining the fault type of the secondary circuit according to the fault characteristics of the abnormal node of the secondary circuit includes:

[0021] Acquire historical fault data of the secondary circuit of the relay protection device, wherein the historical fault data includes historical fault characteristics and fault types, and filter out key fault characteristics from the historical fault characteristics;

[0022] Mining frequent item sets of historical fault data based on apriori algorithm, and determining strong association rules based on frequent item sets of historical fault data;

[0023] The fault type of the secondary circuit of the relay protection device is determined according to the strong association rules of historical fault data.

[0024] Furthermore, the method of mining frequent itemsets of historical fault data based on the apriori algorithm and determining strong association rules according to the frequent itemsets of historical fault data includes:

[0025] Preprocess the historical fault data to obtain discretized historical fault data;

[0026] Set a minimum support threshold, and mine key fault features whose support is greater than or equal to the minimum support threshold based on the fault type of historical fault data;

[0027] A minimum confidence threshold is set, and key fault features with confidence greater than or equal to the minimum confidence threshold are mined from key fault features with support greater than or equal to the minimum support threshold according to the fault type of historical fault data to obtain strong association rules.

[0028] Furthermore, the screening out of key fault features in historical fault features includes:

[0029] Obtain the historical fault characteristics of the secondary circuit of the relay protection device, and calculate the correlation coefficient between any two historical fault characteristics based on the Pearson correlation coefficient;

[0030] Obtaining a correlation coefficient threshold, determining an initial correlation coefficient according to the correlation coefficient between any two historical fault features, respectively obtaining risk coefficients of the two historical fault features, and correcting the correlation coefficient threshold according to the risk coefficients of the two historical fault features;

[0031] One of the two historical fault features that is greater than the correlation coefficient threshold is extracted, and the remaining fault feature is determined as the key fault feature.

[0032] Furthermore, the risk coefficients of the two historical fault features are obtained respectively, and the correlation coefficient threshold is corrected according to the risk coefficients of the two historical fault features, including:

[0033] Obtaining the number of fault occurrences of each historical fault feature, and determining the fault occurrence rate of each historical fault feature according to the number of fault occurrences of each historical fault feature;

[0034] Obtaining the fault severity of each historical fault feature, and calculating the ratio of the fault severity of each historical fault feature to the corresponding fault occurrence rate;

[0035] Determine the risk coefficient of the historical fault feature according to the ratio of the fault severity of each historical fault feature to the corresponding fault occurrence rate, obtain the risk coefficients of two historical fault features, add the risk coefficients of the two historical fault features and perform normalization processing to obtain a threshold correction value;

[0036] The threshold correction value is multiplied by the correlation coefficient threshold to complete the correction of the correlation coefficient threshold.

[0037] Furthermore, the fault repair model is established, the fault type of the secondary circuit is input into the fault diagnosis model, and the repair strategy corresponding to the fault type is obtained, including:

[0038] Obtain historical fault maintenance data of the secondary circuit of the relay protection device, and determine the fault type and corresponding maintenance strategy according to the historical fault maintenance data of the secondary circuit of the relay protection device;

[0039] Preprocess the fault types and corresponding maintenance strategies, and establish a training sample set based on the preprocessed fault types and corresponding maintenance strategies;

[0040] An initial fault repair model is established and trained according to the training sample set, and the trained initial fault repair model is determined as the fault repair model;

[0041] The fault type of the secondary circuit of the relay protection device is obtained, the fault type is input into the fault maintenance model, and the maintenance strategy of the fault type is obtained.

[0042] In order to achieve the above object, the present invention also provides a secondary circuit fault diagnosis system of a relay protection device, comprising:

[0043] The first module is used to obtain the node power parameters of the secondary circuit of the relay protection device and screen out abnormal nodes of the secondary circuit according to the node power parameters;

[0044] The second module is used to obtain the fault characteristics of the abnormal nodes of the secondary circuit, and determine the fault type of the secondary circuit according to the fault characteristics of the abnormal nodes of the secondary circuit;

[0045] The third module is used to establish a fault maintenance model, input the fault type of the secondary circuit into the fault diagnosis model, and obtain the maintenance strategy corresponding to the fault type.

[0046] The beneficial effects of the present invention are:

[0047] By applying the above technical scheme, the present invention locates the abnormal nodes of the secondary circuit of the relay protection device and mines the fault type of the secondary circuit through the fault characteristics of the abnormal nodes. It can accurately and timely discover the hidden faults of the secondary circuit of the relay protection device, and at the same time, process the hidden faults based on the fault maintenance model to obtain the corresponding maintenance strategy, thereby effectively improving the stability of the secondary circuit of the relay protection device. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 The overall flow chart of a secondary circuit fault diagnosis method of a relay protection device proposed in an embodiment of the present invention is shown;

[0050] Figure 2 A structural schematic diagram of a secondary circuit fault diagnosis system of a relay protection device proposed in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0052] The present application provides a secondary circuit fault diagnosis method for a relay protection device, such as Figure 1 As shown, including:

[0053] S101, obtaining node power parameters of the secondary circuit of the relay protection device, and screening out abnormal nodes of the secondary circuit according to the node power parameters;

[0054] In some embodiments of the present application, the method of screening out abnormal nodes in the secondary circuit based on the node power parameters includes: obtaining the voltage values ​​of each node of the secondary circuit of the relay protection device, and determining the voltage stability parameter according to the voltage values ​​of each node of the secondary circuit of the relay protection device; screening out nodes whose voltage values ​​are greater than the voltage stability parameter according to the voltage stability parameter, calculating the difference between the node greater than the voltage stability parameter and each adjacent node, and calculating the difference average value according to the difference between the node greater than the voltage stability parameter and each adjacent node; judging whether the difference average value is greater than a first preset threshold value, if the difference average value is greater than the first preset threshold value, determining the node whose difference average value is greater than the first preset threshold value as an abnormal node.

[0055] In this embodiment, nodes whose voltage is greater than the voltage stability parameter are screened out through the voltage value of each node in the secondary circuit, the difference between the voltage of the node greater than the voltage stability parameter and the voltage of the adjacent node is calculated and the average value of the difference is obtained, and the node whose average value of the difference is greater than the first preset threshold is determined as an abnormal node.

[0056] In some embodiments of the present application, the method of determining the voltage stability parameter based on the voltage value of each node of the secondary circuit of the relay protection device includes: determining the average voltage value of all nodes based on the voltage value of each node of the secondary circuit of the relay protection device, and determining the initial voltage stability parameter based on the average voltage value of all nodes; obtaining the ambient temperature of the secondary circuit of the relay protection device, and calculating the difference between the ambient temperature and the preset standard ambient temperature; normalizing the difference between the ambient temperature and the preset standard ambient temperature, and correcting the initial voltage stability parameter based on the difference between the normalized ambient temperature and the preset standard ambient temperature to obtain the voltage stability parameter.

[0057] In this embodiment, the average voltage value of all nodes in the secondary circuit is determined as the initial voltage temperature parameter. The difference between the ambient temperature and the preset standard ambient temperature is normalized, and the difference range between the ambient temperature and the preset standard ambient temperature is limited to [1, 2]. The corrected voltage stability parameter is obtained by taking the difference between the ambient temperature and the preset standard ambient temperature after normalization.

[0058] In some embodiments of the present application, the correcting the initial voltage stability parameter according to the difference between the normalized ambient temperature and the preset standard ambient temperature includes: correcting the initial voltage stability parameter according to a voltage stability parameter correction formula, wherein the voltage stability parameter correction formula is specifically:

[0059]

[0060] Among them, S is the voltage stability parameter, S α is the preset standard voltage stability parameter, T is the difference between the normalized ambient temperature and the preset standard ambient temperature, T α It is the preset standard temperature difference.

[0061] S102, obtaining a fault feature of an abnormal node of the secondary circuit, and determining a fault type of the secondary circuit according to the fault feature of the abnormal node of the secondary circuit;

[0062] In some embodiments of the present application, determining the fault type of the secondary circuit based on the fault characteristics of the abnormal node of the secondary circuit includes: obtaining historical fault data of the secondary circuit of the relay protection device, the historical fault data including historical fault characteristics and fault types, and screening out key fault characteristics in the historical fault characteristics; mining frequent item sets of the historical fault data based on the apriori algorithm, and determining strong association rules based on the frequent item sets of the historical fault data; determining the fault type of the secondary circuit of the relay protection device based on the strong association rules of the historical fault data.

[0063] In some embodiments of the present application, the apriori algorithm is used to mine frequent item sets of historical fault data, and strong association rules are determined based on the frequent item sets of historical fault data, including: preprocessing the historical fault data to obtain discretized historical fault data; setting a minimum support threshold, and mining key fault features with support greater than or equal to the minimum support threshold according to the fault type of the historical fault data; setting a minimum confidence threshold, and mining key fault features with confidence greater than or equal to the minimum confidence threshold among the key fault features with support greater than or equal to the minimum support threshold according to the fault type of the historical fault data, to obtain strong association rules.

[0064] In this embodiment, the historical fault characteristics are the historical defect data of the secondary circuit. By performing data mining on the key fault characteristics of the historical fault data, strong association rules are obtained. The fault type is obtained through the strong association rules, and a fault handling plan is provided to the operation and maintenance personnel to improve the maintenance efficiency.

[0065] In some embodiments of the present application, the screening out of key fault features in historical fault features includes: obtaining historical fault features of the secondary circuit of the relay protection device, calculating the correlation coefficient between any two historical fault features based on the Pearson correlation coefficient; obtaining a correlation coefficient threshold, determining an initial correlation coefficient according to the correlation coefficient between any two historical fault features, respectively obtaining risk coefficients of the two historical fault features, and correcting the correlation coefficient threshold according to the risk coefficients of the two historical fault features; extracting one of the two historical fault features that is greater than the correlation coefficient threshold, and determining the remaining fault features as key fault features.

[0066] In this embodiment, the correlation analysis method is used to prune different fault features. The linear correlation between historical fault features is calculated by the Pearson correlation coefficient. Fault features with a Pearson coefficient higher than the minimum threshold are highly linearly correlated. It is necessary to reduce the dimension of the number of features for subsequent association rule mining. The correlation coefficient threshold is corrected by the risk coefficient of the historical fault features to prevent excessive data pruning.

[0067] In some embodiments of the present application, the risk coefficients of two historical fault features are obtained respectively, and the correlation coefficient threshold is corrected according to the risk coefficients of the two historical fault features, including: obtaining the number of fault occurrences of each historical fault feature, and determining the fault incidence rate of each historical fault feature according to the number of fault occurrences of each historical fault feature; obtaining the fault severity of each historical fault feature, and calculating the ratio of the fault severity of each historical fault feature to the corresponding fault incidence rate; determining the risk coefficient of the historical fault feature according to the ratio of the fault severity of each historical fault feature to the corresponding fault incidence rate, obtaining the risk coefficients of two historical fault features, adding the risk coefficients of the two historical fault features and then normalizing them to obtain a threshold correction value; multiplying the threshold correction value by the correlation coefficient threshold to complete the correction of the correlation coefficient threshold.

[0068] In this embodiment, the severity corresponding to the fault characteristics is summarized in combination with the relevant regulations, guidance and equipment expert experience of the power grid company, and the risk coefficient is established through the fault occurrence rate of the fault characteristics and the severity of the corresponding fault. The risk coefficients of two historical fault characteristics are added and normalized, and the threshold correction value is limited to the range of [1, 2]. The correlation coefficient threshold is corrected by the threshold correction value. The higher the risk coefficient, the higher the corresponding correlation coefficient threshold. The fault characteristics with high risk coefficients are retained by the threshold correction value to prevent excessive data pruning.

[0069] S103, establishing a fault maintenance model, inputting the fault type of the secondary circuit into the fault diagnosis model, and obtaining a maintenance strategy corresponding to the fault type.

[0070] In some embodiments of the present application, the establishment of a fault maintenance model, inputting the fault type of the secondary circuit into a fault diagnosis model, and obtaining a maintenance strategy corresponding to the fault type, includes: obtaining historical fault maintenance data of the secondary circuit of the relay protection device, and determining the fault type and the corresponding maintenance strategy based on the historical fault maintenance data of the secondary circuit of the relay protection device; preprocessing the fault type and the corresponding maintenance strategy, and establishing a training sample set based on the preprocessed fault type and the corresponding maintenance strategy; establishing an initial fault maintenance model based on the training sample set and training it, and determining the trained initial fault maintenance model as the fault maintenance model; obtaining the fault type of the secondary circuit of the relay protection device, inputting the fault type into the fault maintenance model, and obtaining the maintenance strategy for the fault type.

[0071] In this embodiment, a fault maintenance model is established based on a deep learning neural network, and the fault type of the secondary circuit of the relay protection device is input into the fault maintenance model to obtain a corresponding maintenance strategy.

[0072] Based on the same technical concept, such as Figure 2As shown, the present invention also provides a secondary circuit fault diagnosis system for a relay protection device, comprising:

[0073] The first module is used to obtain the node power parameters of the secondary circuit of the relay protection device, and screen out the abnormal nodes of the secondary circuit according to the node power parameters; the second module is used to obtain the fault characteristics of the abnormal nodes of the secondary circuit, and determine the fault type of the secondary circuit according to the fault characteristics of the abnormal nodes of the secondary circuit; the third module is used to establish a fault maintenance model, input the fault type of the secondary circuit into the fault diagnosis model, and obtain the maintenance strategy corresponding to the fault type.

[0074] By applying the above technical scheme, the present invention obtains the node power parameters of the secondary circuit of the relay protection device, and screens out the abnormal nodes of the secondary circuit according to the node power parameters; obtains the fault characteristics of the abnormal nodes of the secondary circuit, and determines the fault type of the secondary circuit according to the fault characteristics of the abnormal nodes of the secondary circuit; establishes a fault maintenance model, inputs the fault type of the secondary circuit into the fault diagnosis model, and obtains the maintenance strategy corresponding to the fault type. The present invention can accurately detect the fault of the secondary circuit of the relay protection device, diagnose the fault in time and output the maintenance strategy, eliminate the hidden danger in time, and ensure the safe operation of the power system.

[0075] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present invention.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A secondary circuit fault diagnosis method for a relay protection device, It is characterized in that include: Obtain node power parameters of the secondary circuit of the relay protection device, and screen out abnormal nodes of the secondary circuit according to the node power parameters; Obtaining fault characteristics of abnormal nodes in the secondary circuit, and determining the fault type of the secondary circuit according to the fault characteristics of the abnormal nodes in the secondary circuit; A fault maintenance model is established, the fault type of the secondary circuit is input into the fault diagnosis model, and the maintenance strategy corresponding to the fault type is obtained.

2. The secondary circuit fault diagnosis method of the relay protection device according to claim 1, It is characterized in that The method of screening out abnormal nodes of the secondary circuit according to the node power parameters includes: Obtaining the voltage value of each node of the secondary circuit of the relay protection device, and determining the voltage stability parameter according to the voltage value of each node of the secondary circuit of the relay protection device; Nodes whose voltage values ​​are greater than the voltage stability parameter are screened out according to the voltage stability parameter, the difference between the node whose voltage value is greater than the voltage stability parameter and each adjacent node is calculated, and the average value of the difference is calculated according to the difference between the node whose voltage value is greater than the voltage stability parameter and each adjacent node; It is determined whether the average value of the difference is greater than a first preset threshold value. If the average value of the difference is greater than the first preset threshold value, the node whose average value of the difference is greater than the first preset threshold value is determined as an abnormal node.

3. The secondary circuit fault diagnosis method of the relay protection device according to claim 2, It is characterized in that Determining the voltage stability parameter according to the voltage value of each node of the secondary circuit of the relay protection device includes: Determine the average voltage value of all nodes according to the voltage value of each node of the secondary circuit of the relay protection device, and determine the initial voltage stability parameter according to the average voltage value of all nodes; Obtain the ambient temperature of the secondary circuit of the relay protection device and calculate the difference between the ambient temperature and the preset standard ambient temperature; The difference between the ambient temperature and the preset standard ambient temperature is normalized, and the initial voltage stability parameter is corrected according to the difference between the ambient temperature after the normalization and the preset standard ambient temperature to obtain the voltage stability parameter.

4. The secondary circuit fault diagnosis method of the relay protection device according to claim 3, It is characterized in that The step of correcting the initial voltage stability parameter according to the difference between the normalized ambient temperature and the preset standard ambient temperature includes: The initial voltage stability parameter is corrected according to the voltage stability parameter correction formula, and the voltage stability parameter correction formula is specifically: Among them, S is the voltage stability parameter, S α is the preset standard voltage stability parameter, T is the difference between the normalized ambient temperature and the preset standard ambient temperature, T α It is the preset standard temperature difference.

5. The secondary circuit fault diagnosis method of the relay protection device according to claim 1, It is characterized in that Determining the fault type of the secondary circuit according to the fault characteristics of the abnormal node of the secondary circuit includes: Acquire historical fault data of the secondary circuit of the relay protection device, wherein the historical fault data includes historical fault characteristics and fault types, and filter out key fault characteristics from the historical fault characteristics; Mining frequent item sets of historical fault data based on apriori algorithm, and determining strong association rules based on frequent item sets of historical fault data; The fault type of the secondary circuit of the relay protection device is determined according to the strong association rules of historical fault data.

6. The secondary circuit fault diagnosis method of the relay protection device according to claim 5, It is characterized in that The method of mining frequent item sets of historical fault data based on the apriori algorithm and determining strong association rules according to the frequent item sets of historical fault data includes: Preprocess the historical fault data to obtain discretized historical fault data; Set a minimum support threshold, and mine key fault features whose support is greater than or equal to the minimum support threshold based on the fault type of historical fault data; A minimum confidence threshold is set, and key fault features with confidence greater than or equal to the minimum confidence threshold are mined from key fault features with support greater than or equal to the minimum support threshold according to the fault type of historical fault data to obtain strong association rules.

7. The secondary circuit fault diagnosis method of the relay protection device according to claim 5, It is characterized in that The key fault features among the historical fault features are screened out, including: Obtain the historical fault characteristics of the secondary circuit of the relay protection device, and calculate the correlation coefficient between any two historical fault characteristics based on the Pearson correlation coefficient; Obtaining a correlation coefficient threshold, determining an initial correlation coefficient according to the correlation coefficient between any two historical fault features, respectively obtaining risk coefficients of the two historical fault features, and correcting the correlation coefficient threshold according to the risk coefficients of the two historical fault features; One of the two historical fault features that is greater than the correlation coefficient threshold is extracted, and the remaining fault feature is determined as the key fault feature.

8. The secondary circuit fault diagnosis method of the relay protection device according to claim 7, It is characterized in that The step of respectively obtaining the risk coefficients of the two historical fault features and correcting the correlation coefficient threshold according to the risk coefficients of the two historical fault features includes: Obtaining the number of fault occurrences of each historical fault feature, and determining the fault occurrence rate of each historical fault feature according to the number of fault occurrences of each historical fault feature; Obtaining the fault severity of each historical fault feature, and calculating the ratio of the fault severity of each historical fault feature to the corresponding fault occurrence rate; Determine the risk coefficient of the historical fault feature according to the ratio of the fault severity of each historical fault feature to the corresponding fault occurrence rate, obtain the risk coefficients of two historical fault features, add the risk coefficients of the two historical fault features and perform normalization processing to obtain a threshold correction value; The threshold correction value is multiplied by the correlation coefficient threshold to complete the correction of the correlation coefficient threshold.

9. The secondary circuit fault diagnosis method of the relay protection device according to claim 1, It is characterized in that The fault repair model is established, the fault type of the secondary circuit is input into the fault diagnosis model, and the repair strategy corresponding to the fault type is obtained, including: Obtain historical fault maintenance data of the secondary circuit of the relay protection device, and determine the fault type and corresponding maintenance strategy according to the historical fault maintenance data of the secondary circuit of the relay protection device; Preprocess the fault types and corresponding maintenance strategies, and establish a training sample set based on the preprocessed fault types and corresponding maintenance strategies; An initial fault repair model is established and trained according to the training sample set, and the trained initial fault repair model is determined as the fault repair model; The fault type of the secondary circuit of the relay protection device is obtained, the fault type is input into the fault maintenance model, and the maintenance strategy of the fault type is obtained.

10. A secondary circuit fault diagnosis system for a relay protection device, It is characterized in that include: The first module is used to obtain the node power parameters of the secondary circuit of the relay protection device and screen out abnormal nodes of the secondary circuit according to the node power parameters; The second module is used to obtain the fault characteristics of the abnormal nodes of the secondary circuit, and determine the fault type of the secondary circuit according to the fault characteristics of the abnormal nodes of the secondary circuit; The third module is used to establish a fault maintenance model, input the fault type of the secondary circuit into the fault diagnosis model, and obtain the maintenance strategy corresponding to the fault type.

Images