Fault diagnosis method for secondary system of intelligent substation and related device

Abstract

The invention provides a fault diagnosis method for a secondary system of an intelligent substation and a related device, and the method comprises the steps: analyzing an SCD file of the intelligent substation, and building an adjacency list of each secondary device in the secondary system; constructing a fault component set of suspicious fault components based on the plurality of adjacency tables and the alarm information of the secondary system; and on the basis of preset fault feature information and the fault element set, predicting and outputting the suspicious fault element with the fault through a neural network model. According to the method, a fault element set is determined through a fault positioning method combining an adjacency list and skyline query, and then suspicious fault elements in the fault element set are accurately positioned through a probabilistic neural network (PNN). The interference of the fault feature information with low correlation degree on fault positioning is reduced, the value of the fault feature quantity with high correlation degree is highlighted, and the accuracy of fault positioning is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of fault diagnosis of smart substations, and in particular to a fault diagnosis method and related devices for a secondary system of a smart substation. Background Art

[0002] The secondary system of a smart substation is an integrated system composed of multiple secondary devices, which covers all monitoring, control and protection functions in the substation. The communication between secondary devices is changed from a hard loop formed by traditional physical connections to a virtual loop connected by optical cables. Therefore, the transmission input and output of the device time signal are no longer one-to-one corresponding. Therefore, after the system issues a fault or alarm message, it is impossible to judge the abnormal device according to the traditional substation method. Under the existing technology, when a communication failure occurs in the network, the message subscriber issues a link interruption alarm, and determines the physical components related to the faulty link by analyzing the link alarm information; or based on the analysis of SV and GOOSE messages, combined with traffic control, by analyzing the monitoring of the secondary system network information flow, establish protection criteria for information flow abnormalities, and issue abnormal alarm information. Among some current technical means, such as the method of obtaining the fault probability by using the Bayesian formula algorithm, first, the fault probability of each component is obtained based on the fault feature information and historical experience, and then the Bayesian formula is used to obtain the fault probability of each component under the current conditions, and the component with the highest probability is determined as the faulty component; second, a fault model based on the faulty component-alarm information directed bipartite graph is established to express the correlation between the faulty component and the alarm information in the form of a matrix, and the Bayesian algorithm is used to calculate the fault probability of each suspicious component in the form of a ratio to determine the faulty component. However, the effect of using the Bayesian algorithm depends largely on the historical fault probability of the component and the Bayesian protection node.

[0003] At present, the method of judging faults based on the virtual circuit information processing of smart substations still has the following problems: (1) The current monitoring and analysis of secondary system fault-related messages can only determine the approximate area where the fault circuit is located, and cannot accurately determine the specific location of the fault. (2) Due to the large number of IED devices in smart substations, the connection of optical cables becomes complicated when the secondary system is networked. In addition, there is a situation where one optical cable constitutes several virtual circuits, and the types and quantities of messages generated become very complicated. In the analysis process, many fault feature quantities with low fault correlation are added, which easily leads to the neglect of fault feature quantities with high correlation, affecting the efficiency of diagnosis. Summary of the invention

[0004] The present disclosure aims to at least solve the above-mentioned technical problems existing in the prior art.

[0005] To this end, an object of the present disclosure is to propose a fault diagnosis method for a secondary system of a smart substation, the fault diagnosis method for a secondary system of a smart substation comprising:

[0006] Parse the SCD file of the smart substation and establish an adjacency table for each secondary device in the secondary system;

[0007] constructing a fault component set of suspected fault components based on a plurality of said adjacency tables and alarm information of the secondary system;

[0008] Based on the preset fault feature information and the faulty component set, the suspected faulty component that has failed is predicted and outputted through a neural network model.

[0009] In some embodiments, parsing the SCD file of the smart substation and establishing an adjacency table for each secondary device in the secondary system includes:

[0010] Parse the SCD file of the smart substation to determine the topological relationship of the physical circuit and the topological relationship of the virtual circuit between each secondary device;

[0011] Based on the topological relationship of the physical circuit and the topological relationship of the virtual circuit, an adjacency table of each of the secondary devices is established.

[0012] In some embodiments, constructing a faulty component set of suspected faulty components based on the plurality of adjacency tables and the alarm information of the secondary system includes:

[0013] Determine, based on the plurality of adjacency tables and the alarm information of the secondary system, a union of the sets of physical components corresponding to the physical circuit or virtual circuit where the alarm occurs;

[0014] Obtaining a union of sets of physical components corresponding to physical circuits or virtual circuits for which no alarm has occurred;

[0015] A faulty component set of suspected faulty components is constructed based on the union of the sets of physical components corresponding to the physical circuits or virtual circuits where alarms occur and the union of the sets of physical components corresponding to the physical circuits or virtual circuits where no alarms occur.

[0016] In some embodiments, the predicting and outputting the suspected faulty component that has failed based on the preset fault feature information and the faulty component set through a neural network model includes:

[0017] Based on the preset fault feature information, a fault feature set is constructed;

[0018] Determining a fault feature quantity based on the fault feature set and the fault component set;

[0019] The suspected faulty component that has failed is predicted and outputted through a neural network model based on the fault feature quantity.

[0020] In some embodiments, the preset fault characteristic information includes at least equipment operation self-check status information, real-time status monitoring information and communication link status information.

[0021] In some embodiments, predicting the suspected faulty component that has failed based on the fault feature through a neural network model includes:

[0022] After inputting the fault feature quantity into the neural network model, an expected output matrix is ​​output;

[0023] The suspected faulty element that has failed is determined based on the accuracy of the expected output matrix.

[0024] In some embodiments, the neural network model is built based on the number of fault training, the number of fault characteristic quantities, and the number of fault classification modes, wherein the number of fault classification modes is determined based on the number of suspected fault components in the fault component set.

[0025] Another object of the present disclosure is to provide a fault diagnosis device for a secondary system of a smart substation, comprising:

[0026] The adjacency table establishment module is used to parse the SCD file of the smart substation and establish the adjacency table of each secondary device in the secondary system;

[0027] A fault component set building module, used to build a fault component set of suspected fault components based on a plurality of said adjacency tables and the alarm information of the secondary system;

[0028] The fault component output module is used to predict and output the suspected faulty component that has failed based on preset fault feature information and the faulty component set through a neural network model.

[0029] Another object of the present disclosure is to provide a storage medium storing a computer program, wherein the computer program implements the steps of the above method when executed by a processor.

[0030] Another object of the present disclosure is to provide an electronic device, comprising at least a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of the above method when executing the computer program in the memory.

[0031] The present disclosure provides a fault diagnosis method and related device for a secondary system of a smart substation, which has the following beneficial effects:

[0032] The fault diagnosis method for the secondary system of the intelligent substation proposed in the present invention stores the connection information of the components in the form of an adjacency list, reduces the interference of low-suspicion fault components, improves the calculation speed of establishing the fault area, and is suitable for large-scale power grid fault component set searches; three types of fault information, namely, self-test status information of secondary equipment, real-time status monitoring information, and communication channel status information, are used to screen fault feature vectors, and a probabilistic neural network is used to perform iterative operations on the fault component set, which reduces the interference of fault feature quantities with low correlation and realizes accurate identification of fault components. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in 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 recorded in the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0034] Figure 1 is a flowchart of the steps of the fault diagnosis method of the secondary system of the smart substation in the embodiment of the present disclosure;

[0035] Figure 2 is a flowchart of the steps of the fault diagnosis method of the secondary system of the smart substation in the embodiment of the present disclosure;

[0036] Figure 3 is a flowchart of the steps of the fault diagnosis method of the secondary system of the smart substation in the embodiment of the present disclosure;

[0037] Figure 4 is a flowchart of the steps of the fault diagnosis method of the secondary system of the smart substation in the embodiment of the present disclosure;

[0038] Figure 5 is a physical loop topology diagram of the secondary system of the smart substation in the embodiment of the present disclosure;

[0039] Figure 6 is a virtual circuit topology diagram of the secondary system of the smart substation in the embodiment of the present disclosure;

[0040] Figure 7 It is a schematic diagram of the storage format of the adjacency table data unit of the secondary system of the smart substation in the embodiment of the present disclosure;

[0041] Figure 8 It is a schematic diagram of the adjacency of each secondary device of the secondary system of the smart substation in the embodiment of the present disclosure;

[0042] Fig. 9 is a schematic diagram of fault characteristic quantities of a fault component set G of a secondary system of a smart substation in an embodiment of the present disclosure;

[0043] Fig.10 It is a diagram of the neural network structure in the embodiment of the present disclosure. DETAILED DESCRIPTION

[0044] The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings, but are not intended to limit the present disclosure.

[0045] It should be understood that various modifications may be made to the embodiments disclosed herein. Therefore, the above description should not be considered as limiting, but merely as an example of an embodiment. Other modifications within the scope and spirit of the present disclosure will occur to those skilled in the art.

[0046] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the general description of the present disclosure given above and the detailed description of the embodiments given below, serve to explain the principles of the present disclosure.

[0047] These and other characteristics of the present disclosure will become apparent from the following description of a preferred form of embodiment given as a non-limiting example, with reference to the attached drawings.

[0048] It should also be understood that, although the present disclosure has been described with reference to some specific examples, those skilled in the art will be able to realize many other equivalent forms of the present disclosure that have the features described in the claims and are therefore within the scope of protection defined thereby.

[0049] The above and other aspects, features and advantages of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings.

[0050] Specific embodiments of the present disclosure are described hereinafter with reference to the accompanying drawings; however, it should be understood that the disclosed embodiments are merely examples of the present disclosure, which may be implemented in a variety of ways. Well-known and / or repeated functions and structures are not described in detail to avoid obscuring the present disclosure with unnecessary or redundant details. Therefore, the specific structural and functional details disclosed herein are not intended to be limiting, but merely serve as a basis and representative basis for the claims to teach those skilled in the art to use the present disclosure in a variety of ways with substantially any suitable detailed structure.

[0051] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0052] This specification may use the phrases "in one embodiment," "in another embodiment," "in a further embodiment," or "in other embodiments," all of which may refer to one or more of the same or different embodiments according to the present disclosure.

[0053] The first embodiment of the present disclosure provides a fault diagnosis method for a secondary system of a smart substation, such as Figure 1-Figure 10 As shown, the fault diagnosis method of the secondary system of the smart substation includes:

[0054] S100: Parse the SCD file of the smart substation and establish an adjacency table for each secondary device in the secondary system.

[0055] Specifically include:

[0056] S101: Parse the SCD file of the smart substation to determine the topological relationship of the physical circuits and the topological relationship of the virtual circuits between the secondary devices.

[0057] The SCD file of a smart substation, full name Substation Configuration Description, is a standardized file format used to describe the configuration and communication settings of a smart substation. The SCD file contains detailed information such as the substation topology, equipment information, communication configuration, and protection parameters. Therefore, by parsing the SCD file of a smart substation, the topological relationship of the physical circuit and the topological relationship of the virtual circuit between the secondary devices in the secondary system can be determined.

[0058] Taking a 220kV bay secondary system as an example, by parsing the SCD file of the smart substation, we can get the following: Figure 5 The topological relationship diagram of the physical circuit shown in Figure 6 The topological relationship diagram of the virtual circuit shown.

[0059] S102: Based on the topological relationship of the physical circuit and the topological relationship of the virtual circuit, establish an adjacency list for each of the secondary devices.

[0060] Specifically, after the topological relationship of the physical loop and the topological relationship of the virtual loop between the secondary devices are determined in step S101, in this step, an adjacency table of each secondary device is established based on the topological relationship of the physical loop and the topological relationship of the virtual loop. Figure 7 As shown, the adjacency list includes a data field and a linked list field. The data field includes the device number and the device name. The linked list field is stored in a sequential structure and is set to adjvex, portH, cable, portT, circuit and nextae in sequence, where adjvex represents the position of the vertex Vi in the circuit in the adjacency list; portH is the port number connected to the starting point of the optical cable; cable is the number of the connected optical cable; portT is the port number connected to the end of the optical cable; circuit is the virtual circuit number between the two device ports; nextae is a pointer or link from the adjacent point to the next adjacent vertex.

[0061] Taking the above-mentioned 220kV bay secondary system as an example, the adjacency table of each secondary device is shown in Figure 8. Among them, the numbers represent the corresponding physical elements (devices), such as 0 represents the merging unit; 1 represents the busbar protection; 2 represents the switch; 3 represents the measurement and control device; 4 represents the intelligent terminal. Taking the merging unit as an example, the 1-A port of the merging unit (0) is physically connected to the 1-A port of the busbar protection (1) through the optical cable L2, and the two devices transmit information through the virtual link J2, and the direction is from the merging unit to the busbar protection; the 2-A port of the merging unit is physically connected to the 1-A port of the switch (2) through the optical cable L1, and the two devices transmit data through the virtual loop J1, and the direction is from the merging unit to the switch.

[0062] S200: Constructing a faulty component set of suspected faulty components based on the plurality of adjacency tables and alarm information of the secondary system.

[0063] Step S200 is a skyline search method based on an adjacency list and specifically includes:

[0064] S201: Based on the plurality of adjacency tables and alarm information of the secondary system, determine a union of sets of physical components corresponding to the physical circuit or virtual circuit where an alarm occurs.

[0065] The adjacency table here is determined based on step S100. Taking the alarm information issued by the virtual circuit as an example, the alarm information of the virtual circuit here refers to the information that the message subscriber issues a link interruption alarm. If multiple virtual circuits have alarms, each virtual circuit has a corresponding physical component set. In step S201, the physical component set corresponding to each virtual circuit that has an alarm is combined, and the combined set contains all the physical component sets corresponding to all the virtual circuits that have an alarm.

[0066] S202: Obtain a union of sets of physical components corresponding to physical circuits or virtual circuits for which no alarm has occurred.

[0067] After determining the union of the sets of physical components corresponding to the virtual circuits where alarms have occurred based on the multiple adjacency lists and the alarm information of the virtual circuits through the above-mentioned step S201, in this step, the union of the sets of physical components corresponding to the virtual circuits where no alarms have occurred is obtained, and the union includes all the sets of physical components corresponding to all the virtual circuits where no alarms have occurred.

[0068] S203: constructing a faulty component set of suspected faulty components based on the union of the sets of physical components corresponding to the physical circuits or virtual circuits generating alarms and the union of the sets of physical components corresponding to the physical circuits or virtual circuits not generating alarms.

[0069] After obtaining the union of the sets of physical components corresponding to the virtual circuits that have not generated an alarm in the above step S202, in this step, a fault component set of suspected fault components is constructed based on the union of the sets of physical components corresponding to the virtual circuits that have generated an alarm and the union of the sets of physical components corresponding to the virtual circuits that have not generated an alarm. Specifically, the union of the sets of physical components corresponding to the virtual circuits that have generated an alarm is subtracted from the union of the sets of physical components corresponding to the virtual circuits that have not generated an alarm to obtain the fault component set of suspected fault components.

[0070] For example, taking the above 220kV bay secondary system as an example, when the virtual circuit J i , J j , J k When multiple virtual circuits are alarmed, the steps of the skyline search method based on the adjacency table are as follows:

[0071] 1. Establish all virtual circuits J where alarms occur i , J j , J k The corresponding physical component set P i , P j , P k , and find their union P b ;

[0072] P b =Pi ∪P j ∪P k ;

[0073] 2. Query the virtual circuit J that has not issued an alarm message x The set of physical components P x , because of the virtual circuit J X Normal, so the established fault component set G should be the alarm component set P b Subtract the normal circuit physical component set P x ,Right now

[0074] G=(P i ∪P j ∪P k )-(P i ∪P j ∪P k )∩P x ;

[0075] 3. Repeat step 2 and query all normal virtual circuits to establish the fault component set G as follows:

[0076] G=(P i ∪P j ∪P k )-(P i ∪P j ∪P k )∩P x ∩P y ∩···P n ;

[0077] Among them, P y , P n J is a normal virtual circuit y and J n A set of physical components.

[0078] In a specific embodiment, when the virtual circuit J2 issues an alarm message, the physical circuit corresponding to the virtual circuit is queried through the adjacency table, and all its physical components are obtained as follows: ML, 1-A, L2, PM, 1-A, so the fault component set is G = {ML, 1-A, L2, PM, 1-A}.

[0079] S300: Based on the preset fault feature information and the fault component set, the suspected faulty component is predicted and outputted through a neural network model.

[0080] Specifically include:

[0081] S301: Constructing a fault feature set based on preset fault feature information.

[0082] The preset fault characteristic information includes at least equipment operation self-check status information, real-time status monitoring information and communication link status information. Specifically, equipment operation self-check status information refers to the self-check and diagnosis information performed by the equipment during startup or operation, including at least status indicator lights, sensor readings and CPU usage, i.e., self-check alarm information. Real-time status monitoring information includes at least performance indicators, error and exception reports, maintenance reminders, software updates and patches, and user interface feedback, such as: received light intensity, transmitted light intensity, CPU temperature. Communication link status information refers to data used to describe the current status and performance indicators of a link in a communication system. Communication link status information includes at least link connectivity and link status notifications, such as link alarm information.

[0083] Fault signature set X i It can be expressed as follows: X i ={X ZJi ,X CYi ,X SGi ,}, where i=1,2,…N.

[0084] Among them, X i represents the fault feature set of the i-th fault, X ZJi Refers to the self-check information of the equipment. If an alarm is detected, the value is 1, otherwise it is 0; X CYi Refers to the sampling value information of real-time status monitoring, such as the light intensity information sent and received by the optical cable port, and the operating temperature information of each device; X SGi Refers to the status information of the communication link. It is assigned a value of 1 when communication is normal, otherwise it is assigned a value of 0.

[0085] S302: Determine a fault feature quantity based on the fault feature set and the fault component set.

[0086] After the fault feature set is constructed based on the preset fault feature information in the above step S301, in this step, the fault feature quantity is determined based on the fault feature set and the fault component set.

[0087] For example, taking the above 220 kV bay secondary system as an example, if the fault component set is G = {ML, 1-A, L2, PM, 1-A}, the fault characteristic quantity is determined, such as Fig. 9 shown.

[0088] S303: Predicting and outputting the suspected faulty component based on the fault feature through a neural network model.

[0089] After the fault feature quantity is determined based on the fault feature set and the faulty component set in the above step S302, in this step, the suspected faulty component that has failed is predicted and outputted through a neural network model based on the fault feature quantity.

[0090] The neural network model here is built based on the number of fault training, the number of fault characteristic quantities, and the number of fault classification modes, wherein the number of fault training refers to the number of training times, the number of fault characteristic quantities is determined based on step S302, and the number of fault classification modes is determined based on the number of suspected fault components in the fault component set.

[0091] For example, the fault component set G={ML, 1-A, L2, PM, 1-A} in step S302 is used as an example for explanation. It can be seen from the local fault component set G={ML, 1-A, L2, PM, 1-A} that the number of fault components is 3 (ML, L2, PM respectively), so there are 3 fault classification modes. The neural network is constructed based on the number of fault training, the number of fault feature quantities, and the number of fault classification modes. It has a total of 4 layers, such as Fig.10 shown.

[0092] The neural network structure includes input layer, sample layer, cumulative summation layer and output layer. The first layer is the input layer, which inputs the fault feature quantity into the network. The number of neurons is consistent with the fault feature quantity, which is 9. The second layer is the sample layer. The number of neurons in this layer is consistent with the number of sample vectors in the input layer, which is 90. The third layer is the cumulative summation layer. The number of neurons is consistent with the number of suspected fault components, which is 3. The fourth layer is the output layer, which is responsible for outputting the class with the highest probability value. Since the neural network classifies the physical components of the fault component set, the suspected component with the highest probability of failure will be output. The control personnel are responsible for storing the original data and diagnostic results in the database every time a fault occurs, forming the original record of the fault, and then comparing and screening the records of the suspected components in the database according to the fault type and fault location attributes (fault component attributes) to form the fault record of the suspected component. At the same time, the fault feature quantity and fault location (fault component) are extracted from the record as the input and target quantity of the neural network. This is the formation of the sample. In this way, m fault feature quantities and their corresponding 1 fault position (faulty component) are extracted in sequence from the fault records of n suspected faulty components, forming an n*m input matrix and an n*1 expected output matrix. This matrix is ​​continuously iterated through the neural network so that its output continuously approaches the expected output matrix, completing the training of the neural network.

[0093] Further, predicting and outputting the suspected faulty component based on the fault feature through a neural network model specifically includes:

[0094] S3031: After inputting the fault feature quantity into the neural network model, an expected output matrix is ​​output.

[0095] S3032: Determine the suspected faulty element that has failed based on the accuracy of the expected output matrix.

[0096] After the fault feature quantity is input into the neural network model and the expected output matrix is ​​output through the above step S3031, in this step, the suspected faulty component that has failed is determined based on the accuracy of the expected output matrix. Among them, in the neural network, the accuracy of the expected output matrix usually refers to the accuracy of the model prediction, that is, the degree of consistency between the model output and the actual target value. Accuracy is a key indicator to measure the performance of the classification model. It indicates the proportion of the number of samples correctly predicted by the model to the total number of samples. The suspected faulty component that has failed output here is the suspected faulty component with the highest probability of failure.

[0097] The present invention discloses a fault diagnosis method for the secondary system of a smart substation. First, a fault location method combining an adjacency table and a skyline query is used to determine a fault component set, and then a probabilistic neural network (PNN) is used to accurately locate the components in the fault component set. This method reduces the interference of low-correlation fault feature information on fault location, highlights the value of high-correlation fault feature information, and improves the accuracy of fault location.

[0098] Based on the same inventive concept as the first embodiment above, the second embodiment of the present disclosure provides a fault diagnosis device for a secondary system of a smart substation, comprising:

[0099] The adjacency table establishment module is used to parse the SCD file of the smart substation and establish the adjacency table of each secondary device in the secondary system;

[0100] A fault component set building module, used to build a fault component set of suspected fault components based on a plurality of said adjacency tables and the alarm information of the secondary system;

[0101] The fault component output module is used to predict and output the suspected faulty component that has failed based on preset fault feature information and the faulty component set through a neural network model.

[0102] Furthermore, the adjacency table building module includes:

[0103] A topology relationship determination unit is used to parse the SCD file of the smart substation and determine the topology relationship of the physical circuit and the topology relationship of the virtual circuit between each secondary device;

[0104] The adjacency table establishing unit is used to establish an adjacency table of each of the secondary devices based on the topological relationship of the physical circuit and the topological relationship of the virtual circuit.

[0105] Furthermore, the fault component set building block includes:

[0106] A first determining unit, configured to determine, based on the plurality of adjacency tables and the alarm information of the secondary system, a union of sets of physical components corresponding to the physical circuit or virtual circuit where the alarm occurs;

[0107] A second determining unit is used to obtain a union of sets of physical elements corresponding to physical circuits or virtual circuits for which no alarm has occurred;

[0108] The fault component set construction unit is used to construct a fault component set of suspected fault components based on the union of the sets of physical components corresponding to the physical circuits or virtual circuits where alarms occur and the union of the sets of physical components corresponding to the physical circuits or virtual circuits where no alarms occur.

[0109] Furthermore, the fault component output module includes:

[0110] A fault feature set building unit, used to build a fault feature set based on preset fault feature information;

[0111] A fault characteristic quantity determination unit, configured to determine a fault characteristic quantity based on the fault characteristic set and the fault component set;

[0112] The fault component output unit is used to predict and output the suspected faulty component based on the fault feature through a neural network model.

[0113] Furthermore, the fault feature set construction unit includes a fault feature information determination subunit, which is used to determine the fault feature information based on equipment operation self-check status information, real-time status monitoring information and communication link status information.

[0114] Furthermore, the fault component output unit includes:

[0115] An expected output matrix output subunit, used for inputting the fault feature quantity into the neural network model and then outputting an expected output matrix;

[0116] The suspected faulty element determination subunit is used to determine the suspected faulty element that has failed based on the accuracy of the expected output matrix.

[0117] Furthermore, the faulty component output unit includes a neural network building subunit, which is used to build based on the number of fault training, the number of fault characteristic quantities, and the number of fault classification modes, wherein the number of fault classification modes is determined based on the number of suspected faulty components in the faulty component set.

[0118] In this embodiment, a fault location method combining an adjacency list and a skyline query is first used to determine a fault component set, and then the components in the fault component set are accurately located using a probabilistic neural network (PNN). This reduces the interference of low-correlation fault feature information on fault location, highlights the value of high-correlation fault feature quantities, and improves the accuracy of fault location.

[0119] A third embodiment of the present disclosure provides a storage medium storing a computer program. When the computer program is executed by a processor, the steps of implementing the above method include:

[0120] S11: Parse the SCD file of the smart substation and establish an adjacency table for each secondary device in the secondary system;

[0121] S12: constructing a faulty component set of suspected faulty components based on the plurality of adjacency tables and the alarm information of the secondary system;

[0122] S13: Based on the preset fault feature information and the fault component set, the suspected faulty component is predicted and outputted through a neural network model.

[0123] Of course, other steps of the control method can also be used to implement the above embodiment.

[0124] In this embodiment, a fault location method combining an adjacency list and a skyline query is first used to determine a fault component set, and then the components in the fault component set are accurately located using a probabilistic neural network (PNN). This reduces the interference of low-correlation fault feature information on fault location, highlights the value of high-correlation fault feature quantities, and improves the accuracy of fault location.

[0125] A fourth embodiment of the present disclosure provides an electronic device, the electronic device comprising at least a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the above method when executing the computer program on the memory, specifically including:

[0126] S21: Parse the SCD file of the smart substation and establish an adjacency table for each secondary device in the secondary system;

[0127] S22: constructing a faulty component set of suspected faulty components based on the plurality of adjacency tables and the alarm information of the secondary system;

[0128] S23: Based on the preset fault feature information and the fault component set, the suspected faulty component is predicted and outputted through a neural network model.

[0129] In this embodiment, a fault location method combining an adjacency list and a skyline query is first used to determine a fault component set, and then the components in the fault component set are accurately located using a probabilistic neural network (PNN). This reduces the interference of "low correlation" fault feature information on fault location, highlights the value of "high correlation" fault feature information, and improves the accuracy of fault location.

[0130] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific fault diagnosis method of the secondary system of the intelligent substation of each functional unit and module is only for the convenience of distinguishing each other, and is not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0131] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0132] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can 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 this application.

[0133] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0134] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0135] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0136] If the integrated module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiment when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0137] In addition, the features of the embodiments shown in the drawings of the present application or the various embodiments mentioned in this specification are not necessarily understood as independent embodiments. Instead, each feature described in one example of an embodiment can be combined with one or more other desired features from other embodiments to produce other embodiments not described in words or with reference to the drawings.

[0138] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A fault diagnosis method for a secondary system of an intelligent substation, characterized in that: include: Parse the SCD file of the smart substation and establish an adjacency table for each secondary device in the secondary system; constructing a fault component set of suspected fault components based on a plurality of said adjacency tables and alarm information of the secondary system; Based on the preset fault feature information and the faulty component set, the suspected faulty component that has failed is predicted and outputted through a neural network model.

2. The fault diagnosis method for the secondary system of the smart substation according to claim 1 is characterized in that: The step of parsing the SCD file of the smart substation and establishing an adjacency table for each secondary device in the secondary system includes: Parse the SCD file of the smart substation to determine the topological relationship of the physical circuit and the topological relationship of the virtual circuit between each secondary device; Based on the topological relationship of the physical circuit and the topological relationship of the virtual circuit, an adjacency table of each of the secondary devices is established.

3. The fault diagnosis method for the secondary system of the smart substation according to claim 1 is characterized in that: The constructing a fault component set of suspected fault components based on the plurality of adjacency tables and the alarm information of the secondary system comprises: Determine, based on the plurality of adjacency tables and the alarm information of the secondary system, a union of the sets of physical components corresponding to the physical circuit or virtual circuit where the alarm occurs; Obtaining a union of sets of physical components corresponding to physical circuits or virtual circuits for which no alarm has occurred; A faulty component set of suspected faulty components is constructed based on the union of the sets of physical components corresponding to the physical circuits or virtual circuits where alarms occur and the union of the sets of physical components corresponding to the physical circuits or virtual circuits where no alarms occur.

4. The fault diagnosis method for the secondary system of the smart substation according to claim 1 is characterized in that: The method of predicting and outputting the suspected faulty component that has failed based on the preset fault feature information and the faulty component set through a neural network model includes: Based on the preset fault feature information, a fault feature set is constructed; Determining a fault feature quantity based on the fault feature set and the fault component set; The suspected faulty component that has failed is predicted and outputted through a neural network model based on the fault feature quantity.

5. The fault diagnosis method for the secondary system of the smart substation according to claim 4 is characterized in that: The preset fault characteristic information includes at least equipment operation self-check status information, real-time status monitoring information and communication link status information.

6. The fault diagnosis method for the secondary system of the smart substation according to claim 4 is characterized in that: The suspected faulty component that is predicted to have a fault by a neural network model based on the fault characteristic quantity includes: After inputting the fault feature quantity into the neural network model, an expected output matrix is ​​output; The suspected faulty element that has failed is determined based on the accuracy of the expected output matrix.

7. The fault diagnosis method for the secondary system of the smart substation according to claim 4, characterized in that: The neural network model is built based on the number of fault training, the number of fault characteristic quantities, and the number of fault classification modes, wherein the number of fault classification modes is determined based on the number of suspected fault components in the fault component set.

8. A fault diagnosis device for a secondary system of an intelligent substation, characterized in that: include: The adjacency table establishment module is used to parse the SCD file of the smart substation and establish the adjacency table of each secondary device in the secondary system; A fault component set building module, used to build a fault component set of suspected fault components based on a plurality of said adjacency tables and the alarm information of the secondary system; The fault component output module is used to predict and output the suspected faulty component that has failed based on preset fault feature information and the faulty component set through a neural network model.

9. A storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. An electronic device, comprising at least a memory and a processor, wherein a computer program is stored in the memory, wherein: The processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program on the memory.

Images