Substation secondary equipment fault positioning method based on space-time diagram convolutional network model

Abstract

The invention provides a transformer substation secondary equipment fault positioning method based on a space-time diagram convolutional network model, and the method comprises the steps: extracting feature information based on the historical fault data of transformer substation secondary equipment, and arranging the operation state of the secondary equipment, the SV / GOOSE signal receiving state and a sampling value according to a time sequence to generate a fault feature set; based on the change trend of the fault feature set in the time sequence, performing multi-modal feature fusion on the fault feature data; constructing an STGCN model based on the fault features; historical fault samples are used for training an STGCN model, features highly related to faults are extracted through data preprocessing and feature screening, an optimized feature set is constructed, the fault positioning precision of the model is continuously improved, and the association mapping relation between fault feature information and fault categories is comprehensively established; and in combination with a fault inference rule, the feature set is input into the STGCN model, the secondary equipment fault is accurately positioned by using the space-time diagram convolution capability of the model, and the function of improving the accuracy and efficiency of transformer substation secondary equipment fault diagnosis is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of substation secondary equipment, and in particular relates to a substation secondary equipment fault location method based on a spatiotemporal graph convolutional network model. Background Art

[0002] In modern power systems, substation secondary equipment undertakes key monitoring, measurement, protection and regulation tasks, and is a core component to ensure the safe, stable and economical operation of the power system. Secondary equipment is responsible for collecting and transmitting a large amount of real-time information of the power system, and remotely operating, protecting and automating the primary equipment in the substation. Its stable operation is crucial to the reliability of the power system. However, with the continuous expansion of the scale of the power system and the improvement of the automation level, the types and number of secondary equipment have increased significantly, and the equipment structure and functions have become more complex, which has brought new technical challenges to the fault diagnosis and location of secondary equipment.

[0003] Traditional secondary equipment fault diagnosis and location methods usually rely on the experience of operation and maintenance personnel or the support of equipment manufacturers. Especially for complex or occasional faults, it is often difficult to quickly determine the accurate fault location through experience. For less experienced operation and maintenance personnel, the risk of misdiagnosis is higher, which can easily lead to carrying the wrong maintenance equipment, affecting the efficiency of fault handling, and may even delay the protection of primary equipment, thereby affecting the safe operation of the entire power system. Therefore, there is an urgent need for a more scientific and efficient fault diagnosis and location method that can quickly and accurately identify secondary equipment faults, reduce the burden on operation and maintenance personnel, and improve the intelligent operation and maintenance level of substations.

[0004] In recent years, with the continuous development of big data technology and artificial intelligence algorithms, data-driven intelligent fault diagnosis methods have gradually been applied to fault location of secondary equipment. In particular, the introduction of the Spatial-Temporal Graph Convolutional Network (STGCN) model provides a new solution to the problem of fault location with spatiotemporal characteristics in complex systems. STGCN can effectively process time series and spatial information, and accurately locate faults by analyzing the spatiotemporal correlation characteristics between different devices. This method can not only greatly improve the positioning accuracy, but also shorten the fault diagnosis time and improve the stability and reliability of the power system. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a substation secondary equipment fault location method based on a spatiotemporal graph convolutional network model, so as to improve the accuracy and efficiency of substation secondary equipment fault diagnosis.

[0006] The technical solution adopted by the present invention to solve the above technical problems is: a substation secondary equipment fault location method based on a spatiotemporal graph convolutional network model, comprising the following steps: S1: Obtain historical data of secondary equipment, construct a fault feature set including operating status information, SV / GOOSE receiving status information and sampling values; sort the fault feature data in time series and correspond them to the corresponding secondary equipment faults one by one; S2: Extract and filter high-correlation fault features and construct a filtered fault feature set; S3: Perform multi-modal feature fusion processing on the data of the fault feature set based on the time series to obtain fault feature fusion data; S4: Construct an STGCN model consisting of three layers of 1D-CNN networks and one layer of GCN network to simultaneously learn the spatial and temporal features of graph data; divide the fault feature fusion data into a training set and a test set. The training set is used for model learning, and the test set is used to evaluate the performance and accuracy of the model. S5: Set a dynamic threshold for the amount of fault feature information that is adaptive to weather conditions to detect secondary equipment failures; when a secondary equipment failure is detected, diagnose and locate the fault location based on the fault reasoning rules; if the reasoning rules cannot accurately locate the fault location, input the fault feature fusion data into the STGCN model, and use the model to identify and locate the fault location of the secondary equipment.

[0007] According to the above scheme, in step S1, the operating status information of the secondary equipment includes the self-test status of the merging unit, line protection and intelligent terminal, which is used to reflect the equipment operating status through multi-dimensional data integration, support accurate fault location and early warning, and effectively improve the safety and reliability of the system.

[0008] According to the above scheme, in step S1, the SV / GOOSE message reception status information includes the message reception status of the merging unit, the protection device and the intelligent terminal, which is used to judge the abnormality of the sampling value and the switch quantity; when an event occurs in the device, the GOOSE data set is immediately updated and the data frames are sent at specific time intervals: first, the second and third frames are sent at intervals T1, and then the fourth and fifth frames are sent at intervals T2 and T3, where T2 is twice T1 and T3 is twice T2; after sending 5 frames, the sending interval is restored to T0, and it is converted to the heartbeat message state, and the message survival time is twice T0; if the receiver does not receive the message within 4 times T0, it is determined that the connection is interrupted and a link break alarm is triggered.

[0009] According to the above scheme, in step S2, the specific steps are: S21: Preprocess the historical data and eliminate the influence of dimension by normalization; S22: The Pearson correlation coefficient is used to analyze the linear correlation between each feature and the fault, remove the low-correlation features, retain the high-correlation features, and construct a new fault feature set.

[0010] According to the above scheme, in step S3, the specific steps are: S31: construct a fault feature fusion weight matrix according to the data values, change trends and change rates of the fault feature set in the historical data; S32: Multiply the fault feature set by the fault feature fusion weight matrix to obtain fault feature fusion data.

[0011] According to the above scheme, in step S4, the 1D-CNN network is used to perform a convolution operation on the time dimension of the data to extract time series information; the 1D-CNN network includes two convolution layers and a flattening operation, each convolution layer includes a convolution operation and a pooling operation; after the second pooling operation, a fully connected layer is also included to flatten the high-dimensional data into one-dimensional data; the specific steps are: The output feature matrix of the previous layer is used as the input feature matrix of the current layer. The local patterns in the input features are extracted through the weight function. Nonlinearity is introduced through the activation function to obtain the output of the current layer, that is, the feature map or activation value of the layer.

[0012] According to the above scheme, in step S4, the GCN network updates the feature representation of each node by processing the data after the convolution operation, combining spatial convolution with the information of adjacent nodes aggregated by the graph structure, and is used to extract the spatial structural relationship of the data to process the nonlinear features in the multivariate time series; the specific steps are: The output feature matrix of the previous layer is multiplied by the weight matrix to obtain the learnable parameters of the graph convolution layer, and is multiplied by the adjacency matrix and normalized to obtain the connection relationship between the nodes in the feature graph. After adjusting the output of the network through the bias top, nonlinearity is introduced through the activation function to obtain the output feature matrix of the current layer.

[0013] According to the above scheme, in step S5, the specific steps are: S51: adaptively setting a dynamic threshold of the number of fault characteristic information according to the basic threshold and weather influencing factors to improve the sensitivity of detecting secondary equipment faults; when the total number of fault characteristic information exceeds the set threshold, triggering the fault location function; S52: Locate the fault location through the secondary equipment fault inference rule; if it fails, extract the filtered fault feature set obtained in step S2, fuse it according to step S3 and input it into the STGCN model trained in step S4 to obtain the final secondary equipment fault location result.

[0014] Substation secondary equipment fault location system based on spatiotemporal graph convolutional network model, The data acquisition submodule is used to obtain the historical data of the secondary equipment, build a fault feature set including the operating status information, SV / GOOSE receiving status information and sampling values; sort the fault feature data according to the time series and correspond them one by one with the corresponding secondary equipment faults; The data screening submodule is used to extract and screen the fault features with high correlation and construct the screened fault feature set; The model training and testing submodule is used to build an STGCN model including three layers of 1D-CNN networks and one layer of GCN network to simultaneously learn the spatial and temporal features of graph data; the data in the fault feature set is divided into a training set and a test set, the training set is used for model learning, and the test set is used to evaluate the performance and accuracy of the model; The fault location submodule is used to set the threshold of the number of fault feature information to detect secondary equipment faults. When a secondary equipment fault is detected, the fault location is diagnosed and located according to the fault reasoning rules. If the reasoning rules cannot accurately locate the fault location, the fault feature set is input into the STGCN model to identify and locate the fault location of the secondary equipment through the model.

[0015] The STGCN model for fault location of substation secondary equipment includes multiple superimposed 1D-CNN networks for learning and capturing the temporal dependencies between data variables, and a GCN network for extracting the spatial dependencies between data variables; it also includes a fully connected layer for outputting the final results.

[0016] The beneficial effects of the present invention are: 1. The method for locating faults of secondary equipment in a substation based on a spatiotemporal graph convolutional network model of the present invention extracts feature information based on historical fault data of secondary equipment in the substation, arranges the operating status, SV / GOOSE signal receiving status and sampling values ​​of the secondary equipment in a time series, and generates a fault feature set; based on the changing trend of the fault feature set in the time series, multimodal feature fusion is performed on the fault feature data; based on these fault features, a spatiotemporal graph convolutional network model (STGCN) is constructed; the STGCN model is trained using historical fault samples, and features highly correlated with the fault are extracted through data preprocessing and feature screening, an optimized feature set is constructed, the fault location accuracy of the model is continuously improved, and a correlation mapping relationship between fault feature information and fault categories is comprehensively established; in combination with fault inference rules, the feature set is input into the STGCN model, and the spatiotemporal graph convolution capability of the model is used to accurately locate the faults of the secondary equipment, thereby realizing the function of improving the accuracy and efficiency of fault diagnosis of secondary equipment in the substation.

[0017] 2. The present invention greatly improves the efficiency and accuracy of fault location through automated reasoning and training of deep learning models, providing solid technical support for the safe and reliable operation of the power system.

[0018] 3. The present invention solves the problem that there are many types of secondary equipment in substations and fault diagnosis and maintenance are overly dependent on the experience of operation and maintenance personnel or manufacturer's technical support; it reduces misdiagnosis caused by insufficient experience of operation and maintenance personnel and avoids carrying wrong maintenance equipment, thereby improving the efficiency of timely handling of faults and ensuring safe production, economical operation and stable power supply of the power system.

[0019] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 is a flow chart of an embodiment of the present invention.

[0022] Figure 2 It is a structural diagram of a 1D-CNN network according to an embodiment of the present invention.

[0023] Figure 3 4 is a structural diagram of a GCN network according to an embodiment of the present invention.

[0024] Figure 4 It is a structural diagram of the STGCN neural network model of an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0026] Example 1 See also Figure 1 ,The specific steps of the substation secondary equipment fault location method based on the spatiotemporal graph convolutional network model are as follows: S1: Obtain historical data of secondary equipment, construct a fault feature set including operating status information, SV / GOOSE receiving status information and sampling values; sort the fault feature data in time series and correspond them to the corresponding secondary equipment faults one by one; S2: Extract and filter high-correlation fault features and construct a filtered fault feature set; S3: Perform multi-modal feature fusion processing on the data of the fault feature set based on the time series to obtain fault feature fusion data; S4: Construct an STGCN model including three layers of 1D-CNN network and one layer of GCN network to simultaneously learn the spatial and temporal features of graph data; divide the fault feature fusion data into a training set and a test set, the training set is used for model learning, and the test set is used to evaluate the performance and accuracy of the model; obtain the trained STGCN model; S5: Set a dynamic threshold for the number of fault feature information that is adaptive to weather conditions to detect secondary equipment failures; when a secondary equipment failure is detected, diagnose and locate the fault location based on the fault reasoning rules; if the reasoning rules cannot accurately locate the fault location, input the fault feature fusion data into the trained STGCN model, and use the model to identify and locate the fault location of the secondary equipment.

[0027] Furthermore, in step S1, the operating status information of the secondary equipment includes the self-test status of the merging unit, line protection and intelligent terminal, which is used to reflect the operating status of the equipment through multi-dimensional data integration, support accurate fault location and early warning, and effectively improve the safety and reliability of the system.

[0028] In step S1, the SV / GOOSE message reception status information includes the message reception status of the merging unit, protection device and intelligent terminal, which is used to judge the abnormality of the sampling value and the switch quantity; when an event occurs in the device, the GOOSE data set is immediately updated and the data frames are sent at specific time intervals: first, the second and third frames are sent at intervals T1, and then the fourth and fifth frames are sent at intervals T2 and T3, where T2 is twice T1 and T3 is twice T2; after sending 5 frames, the sending interval is restored to T0 and converted to the heartbeat message state, and the message survival time is twice T0; if the receiver does not receive the message within 4 times T0, it is determined that the connection is interrupted and a link break alarm is triggered.

[0029] In step S2, the specific steps are: S21: Preprocess the historical data and eliminate the influence of dimension by normalization; S22: The Pearson correlation coefficient is used to analyze the linear correlation between each feature and the fault, remove the low-correlation features, retain the high-correlation features, and construct a new fault feature set.

[0030] In step S3, the specific steps are: S31: construct a fault feature fusion weight matrix according to the data values, change trends and change rates of the fault feature set in the historical data; S32: Multiply the fault feature set by the fault feature fusion weight matrix to obtain fault feature fusion data.

[0031] In step S4, the 1D-CNN network is used to perform a convolution operation on the time dimension of the data to extract time series information; the 1D-CNN network includes two convolution layers and a flattening operation, each convolution layer includes a convolution operation and a pooling operation; after the second pooling operation, a fully connected layer is also included to flatten the high-dimensional data into one-dimensional data; the specific steps are: The output feature matrix of the previous layer is used as the input feature matrix of the current layer. The local patterns in the input features are extracted through the weight function. Nonlinearity is introduced through the activation function to obtain the output of the current layer, that is, the feature map or activation value of the layer.

[0032] In step S4, the GCN network updates the feature representation of each node by processing the data after the convolution operation, combining spatial convolution with the information of adjacent nodes aggregated by the graph structure, and is used to extract the spatial structural relationship of the data to process the nonlinear features in the multivariate time series; the specific steps are: The output feature matrix of the previous layer is multiplied by the weight matrix to obtain the learnable parameters of the graph convolution layer, and is multiplied by the adjacency matrix and normalized to obtain the connection relationship between the nodes in the feature graph. After adjusting the output of the network through the bias top, nonlinearity is introduced through the activation function to obtain the output feature matrix of the current layer.

[0033] In step S5, the specific steps are: S51: adaptively setting a dynamic threshold of the number of fault characteristic information according to the basic threshold and weather influencing factors to improve the sensitivity of detecting secondary equipment faults; when the total number of fault characteristic information exceeds the set threshold, triggering the fault location function; S52: Locate the fault location through the secondary equipment fault inference rule; if it fails, extract the filtered fault feature set obtained in step S2, fuse it according to step S3 and input it into the STGCN model trained in step S4 to obtain the final secondary equipment fault location result.

[0034] This embodiment selects the operating status of secondary equipment, SV / GOOSE information receiving status and sampling value based on the substation fault inference rules, constructs a fault feature set, and forms a complete fault feature representation by matching the fault type code. Combined with a large amount of historical fault data of secondary equipment, it is proposed to use the spatiotemporal graph convolutional neural network (STGCN) model for training to establish a comprehensive association mapping relationship between fault feature information and fault categories, thereby achieving accurate positioning of secondary equipment faults, effectively shortening the positioning time, and significantly improving the accuracy of fault positioning.

[0035] Example 2 The steps of this embodiment are the same as those of embodiment 1, except that each step is applied to a specific example. Specifically, the following steps are included: S1: Select the characteristic information of the fault type to form the characteristic information set of the secondary equipment fault section X i The selection of secondary equipment fault characteristic information should be based on multi-dimensional data such as equipment operating status, instrument readings, indicator light status, message reception, voltage and current sampling values, and historical alarm information, so as to comprehensively and accurately identify faults. The above fault characteristic information can be classified according to whether the device issues an abnormal alarm, the abnormal conditions of sampling and switching quantities, and the actual sampling values. Therefore, the fault information is divided into the operating status information of the secondary equipment X ZTi 、SV / GOOSE (sampled value / generic object-oriented substation event) receiving status information X SGi , sampling value X CYi , sort the fault feature information in time series and correspond them to the corresponding secondary equipment faults one by one.

[0036] Operating status information of secondary equipment X ZTi Summarizes the self-test status of the merging unit, line protection and intelligent terminal, such as self-test abnormality T , Synchronization exception S and device lockout A When the monitoring host receives these characteristic information, the element at the corresponding position is "1", otherwise it is "0". The fault feature set formed by these information reflects the operating status of the equipment through multi-dimensional data integration, supports accurate fault location and early warning, and effectively improves the safety and reliability of the system.

[0037] The SV / GOOSE message reception information of the secondary equipment is an important basis for judging the abnormalities of the sampling values ​​and switch quantities. When an event occurs in the equipment (such as protection action), the GOOSE data set is immediately updated and the data frames are sent at specific time intervals: first, the 2nd and 3rd frames are sent at intervals T1, and then the 4th and 5th frames are sent at intervals T2 and T3, where T2 is twice T1 and T3 is twice T2. After completing 5 frames, the sending interval is restored to T0 and it is converted to the heartbeat message state. The message survival time is twice T0. If the receiver does not receive the message within 4 times T0, it is determined that the connection is interrupted and a link break alarm is triggered. SV / GOOSE reception status information X SGi It integrates the message receiving status of the merging unit, protection device, intelligent terminal and other devices. If no message is received, X SGi The corresponding position in is 1, otherwise it is 0. Incorporating this information into the fault feature set can effectively improve the accuracy and universality of the model.

[0038] Sample value XCYi Represents the three-phase voltage and current sampling data of the dual channels of the protection device.

[0039] Fault Signature Set X i As shown in (6), the secondary equipment operation status information X ZTi 、SV / GOOSE receiving status information X SGi , sampling value X CYi As shown in (7), (8) and (9) respectively.

[0040] (6) (7) (8) (9) In the formula, Indicates i The feature set of a fault event, Indicates the operating status information of the secondary equipment. Indicates the SV / GOOSE message receiving status. is the sampling value of the secondary equipment. The total number of fault events is N ,in k , i , j are the number of merging units, protection devices and intelligent terminal devices respectively. , , Corresponding merge unit a , protective device b , Smart Terminal c Self-check information, including abnormal status G , Synchronization exception H ,atresia L Etc. When a fault occurs, the value of the abnormal position of the self-check information is 1, otherwise it is 0. SV / GOOSE receiving status set Indicates the message receiving status of the merging unit, measurement and control device, busbar / line protection, and intelligent terminal. The total number of messages is all , For the i The receiving status of the message, the subscription of the message n The device receives the status E When a fault causes a link break, the secondary device j No message received x ,but Exj is 1, otherwise it is 0. Sample value For dual-channel three-phase voltage and current sampling of the protection device, channel 1 and channel 2 are C 1 and C 2, I , U Indicates three-phase current and voltage.

[0041] S2: Extract and screen fault features. First, normalize the historical data to eliminate the influence of different dimensions. Then use the Pearson correlation coefficient to analyze the linear correlation between each feature and the fault result, screen out features with low correlation, retain features with high correlation, and build a streamlined fault feature set.

[0042] In order to improve the accuracy of the model and solve the problem of inconsistent data dimensions, the Min-Max normalization method is used to process the fault feature data. The conversion function of Min-Max normalization is shown in formula (1).

[0043] (1) In the formula X max and X min are the maximum and minimum values ​​in the data set, respectively.

[0044] In the process of fault location, the Pearson correlation coefficient formula is used to quantitatively evaluate the linear correlation between each fault feature and the fault result, so as to clarify the relationship between the feature and the fault and provide a basis for feature screening.

[0045] (2) Where: is the correlation coefficient between each factor; and For the i The values ​​of the two factors for each data point; and is the mean of the two factors; n is the number of data points.

[0046] The Pearson correlation coefficient can be used to screen out low-correlation fault features, improve the applicability of the invention, reduce the amount of data input and improve analysis accuracy.

[0047] S3: Perform multi-modal feature fusion processing on the data of the fault feature set based on the time series to obtain fault feature fusion data; the specific steps are: S31: construct a fault feature fusion weight matrix according to the data values, change trends and change rates of the fault feature set in the historical data; Assume that the data in the fault feature set is ; a is a constant greater than 1; fault characteristic over-limit coefficient for:

[0048] Let b be a constant less than 1, Indicates that the fault characteristics are The amount of change within a period; the coefficient of change trend for:

[0049] set up is the fault feature basic coefficient, which is adjusted according to the importance of the fault feature and is usually set to 1; then the fault feature fusion coefficient for:

[0050] The fusion coefficient of the fault feature is obtained by multiplying the three, which highlights the importance of the value and change trend of the fault feature in a certain period of time, which is conducive to improving the model's recognition rate of abnormal changes in the fault feature.

[0051] The fault feature fusion coefficients corresponding to all fault features are combined to obtain the fault feature fusion weight matrix.

[0052] S32: Multiply the fault feature set by the fault feature fusion weight matrix to obtain fault feature fusion data.

[0053] S4: Build the corresponding STGCN model, select part of the fault feature fusion data for training the model, and use the rest of the fault feature fusion data as a test set to verify the model performance.

[0054] The traditional GCN graph embedding method performs well in spatial relationship learning, but has limited ability to capture temporal dependencies. Figure 4 As shown, this embodiment adopts the STGCN module, which consists of three layers of one-dimensional convolutional neural network 1D-CNN and one layer of GCN, and can simultaneously learn the spatial and temporal features of graph data. Among them, 1D-CNN is used to extract time series information, and GCN is used to capture spatial structural relationships. Through the coordinated operation of these two operations, STGCN can effectively model the spatiotemporal dependencies in the data, thereby more accurately predicting and analyzing the spatiotemporal dynamics of graph structure data.

[0055] In STGCN, parameter sharing between different channels is non-parallel. This design choice helps to maintain the independence of graph structure learning, thereby enhancing the generalization ability and interpretability of the model.

[0056] 1D-CNN is a model built based on biological visual perception mechanisms, which can perform supervised and unsupervised learning. 1D-CNN utilizes the convolution kernel parameter sharing of the hidden layer and the sparsity of the inter-layer connection. With a small amount of computation, it can extract deep local features from high-dimensional data and generate effective representations through convolution layers and pooling layers. The network structure of 1D-CNN usually contains two convolution layers and a flattening operation. Each convolution layer consists of a convolution operation and a pooling operation. After the second pooling operation, the fully connected layer can be used to flatten the high-dimensional data into one-dimensional data for easier subsequent processing. The 1D-CNN structure is shown in the attached figure. Figure 2 shown.

[0057] The time dependency within the node is extracted by using the 1D-CNN in the STGCN model. This embodiment only performs convolution operations on the time dimension of the data. The specific method is as follows:

[0058] Where: For the l The output of the layer is the feature map or activation value of this layer; It is an activation function, which introduces nonlinearity to ensure that the neural network can fit complex functions; is a weight matrix used to extract local patterns in input features; It is The output of the layer is also l The input of the layer.

[0059] In the GCN module of the STGCN model, convolutional neural networks are used to extract spatial dependencies of data, aiming to process nonlinear features in multivariate time series. By processing the data after the convolution operation, the GCN module aggregates the information of adjacent nodes to update the feature representation of each node. This is achieved by combining spatial convolution with graph structure.

[0060]

[0061] Where: It is l The output feature matrix of the layer represents the feature representation of all nodes in the graph at this layer; It is an activation function, which can introduce nonlinearity; It is a normalized degree matrix, which mainly prevents numerical instability and weight bias; is the adjacency matrix, which represents the connection relationship between nodes in the graph; is the output feature matrix of the previous layer; It is l The weight matrix of the layer, i.e., the learnable parameters of the graph convolutional layer; It is l The bias top of the layer is used to adjust the output of the network during calculation. The GCN structure is shown in the attached figure. Figure 3 shown.

[0062] S5: When a secondary device fails, the fault inference rule is first used to determine the location of the fault. If the reasoning cannot accurately locate the fault, the fault feature set is input into the model to further locate the secondary device fault with the help of the model. The specific steps are: S51: Adaptively set a dynamic threshold for the number of fault feature information based on the basic threshold and weather influencing factors to improve the sensitivity of detecting secondary equipment faults; when the total number of fault feature information exceeds the set dynamic threshold, trigger the fault location function.

[0063] Assume that the weather factor coefficient for:

[0064] Assume the basic threshold is , then the dynamic threshold for:

[0065] When weather conditions are severe, the threshold will automatically decrease to increase the sensitivity of fault detection.

[0066] S52: First try to locate the fault through the secondary equipment fault inference rule. If it fails, extract the filtered and fused feature information and sampling values ​​to form a feature set. X i , and input it into the trained STGCN fault localization model to obtain the final localization result. Some inference rules are shown in Table 1.

[0067] Table 1 Partial inference rules serial number Fault type Feature information 1 Merging unit DSP or sampling DSP module failure Merging unit sampling abnormality, merging unit synchronization abnormality, merging unit / protection SV total alarm, protection lockout, etc. 2 Merge unit configuration error Board configuration error, GOOSE configuration file error, merge unit / protection lockout, etc. 3 Smart terminal configuration error Input wire error, GOOSE configuration file error, board configuration error, intelligent terminal locked, etc. 4 Intelligent terminal power board failure Smart terminal power failure alarm 5 The power module of the merging unit is faulty. Merging unit power failure alarm 6 Intelligent terminal I / O board failure Merging unit / measurement and control / intelligent terminal / protection GOOSE communication interruption, merging unit / intelligent terminal / protection GOOSE general alarm, etc. 7 Line protection configuration error SV / GOOSE configuration file error, board configuration error, version error alarm, protection lockout, etc. 8 Line protection I / O, SV, GOOSE plug-in failure Protection SV / GOOSE general alarm, intelligent terminal GOOSE general alarm, protection SV / GOOSE interruption, protection interlock, reclosing interlock, etc. 9 Line protection power plug failure Line protection power failure alarm It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0068] Example 3 This embodiment is used to implement the principle of the above method embodiment to construct a substation secondary equipment fault location system based on a spatiotemporal graph convolutional network model, including a data acquisition submodule, a data screening submodule, a model training and testing submodule, and a fault location submodule; The data acquisition submodule is used to obtain the historical data of the secondary equipment, build a fault feature set including the operating status information, SV / GOOSE receiving status information and sampling values; sort the fault feature data according to the time series and correspond them one by one with the corresponding secondary equipment faults; The data screening submodule is used to extract and screen the fault features with high correlation and construct the screened fault feature set; The model training and testing submodule is used to build an STGCN model including three layers of 1D-CNN networks and one layer of GCN network to simultaneously learn the spatial and temporal features of graph data; the data in the fault feature set is divided into a training set and a test set, the training set is used for model learning, and the test set is used to evaluate the performance and accuracy of the model; The fault location submodule is used to set the threshold of the number of fault feature information to detect secondary equipment faults. When a secondary equipment fault is detected, the fault location is diagnosed and located according to the fault reasoning rules. If the reasoning rules cannot accurately locate the fault location, the fault feature set is input into the STGCN model to identify and locate the fault location of the secondary equipment through the model.

[0069] Each sub-module is mainly used to implement each step of the method embodiment, which will not be described in detail here.

[0070] Example 4 This embodiment is used to implement the principles of the above-mentioned method embodiment to construct a STGCN model for substation secondary equipment fault location, including multiple superimposed 1D-CNN networks for learning and capturing the temporal dependencies between data variables, and a GCN network for extracting the spatial dependencies between data variables; it also includes a fully connected layer for outputting the final result.

[0071] It should be pointed out that, according to the needs of implementation, the various steps / components described in this application can be split into more steps / components, and two or more steps / components or partial operations of steps / components can be combined into new steps / components to achieve the purpose of the present invention.

[0072] This embodiment also includes a processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate with each other through the communication bus; a computer program is stored in the memory, and when the program is executed by the processor, the processor executes the steps of the substation secondary equipment fault location method based on the spatiotemporal graph convolutional network model.

[0073] This embodiment also provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, enables the processor to implement a substation secondary equipment fault location method based on a spatiotemporal graph convolutional network model.

[0074] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware.

[0075] Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0076] The present application is described with reference to the flowchart of the method and computer program product according to Embodiment 1 of the present application and the block diagram of the system according to Embodiment 3. It should be understood that each process or box in the flowchart or block diagram, and the combination of processes or boxes in the flowchart or block diagram can be implemented by computer program instructions.

[0077] These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process Figure 1 A process or multiple processes or boxes Figure 1 A substation secondary equipment fault location system based on a spatiotemporal graph convolutional network model with functions specified in a box or multiple boxes.

[0078] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes or boxes Figure 1 A function specified in one or more boxes.

[0079] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes or boxes Figure 1 The steps of the substation secondary equipment fault location method based on the spatiotemporal graph convolutional network model are specified in a box or multiple boxes.

[0080] The above embodiments are only used to illustrate the design ideas and features of the present invention, and their purpose is to enable those skilled in the art to understand the content of the present invention and implement it accordingly. The protection scope of the present invention is not limited to the above embodiments. Therefore, any equivalent changes or modifications made based on the principles and design ideas disclosed by the present invention are within the protection scope of the present invention.

Claims

1. A substation secondary equipment fault location method based on a spatiotemporal graph convolutional network model, characterized by: The following steps are involved: S1: Obtain historical data of secondary equipment, construct a fault feature set including operating status information, SV / GOOSE receiving status information and sampling values; sort the fault feature data in time series and correspond them to the corresponding secondary equipment faults one by one; S2: Extract and filter high-correlation fault features and construct a filtered fault feature set; S3: Perform multi-modal feature fusion processing on the data of the fault feature set based on the time series to obtain fault feature fusion data; S4: Construct an STGCN model consisting of three layers of 1D-CNN networks and one layer of GCN network to simultaneously learn the spatial and temporal features of feature map data; The fault feature fusion data is divided into a training set and a test set. The training set is used for model learning, and the test set is used to evaluate the performance and accuracy of the model. The trained STGCN model is obtained. S5: Set a dynamic threshold for the number of fault feature information that is adaptive to weather conditions to detect secondary equipment failures; when a secondary equipment failure is detected, diagnose and locate the fault location based on the fault reasoning rules; if the reasoning rules cannot accurately locate the fault location, input the fault feature fusion data into the trained STGCN model, and use the model to identify and locate the fault location of the secondary equipment.

2. The method for locating faults of secondary equipment in a substation based on a spatiotemporal graph convolutional network model according to claim 1 is characterized in that: In step S1, the operating status information of the secondary equipment includes the self-test status of the merging unit, line protection and intelligent terminal, which is used to reflect the equipment operating status through multi-dimensional data integration, support accurate fault location and early warning, and effectively improve the safety and reliability of the system.

3. The method for locating faults of secondary equipment in a substation based on a spatiotemporal graph convolutional network model according to claim 1 is characterized in that: In the step S1, the SV / GOOSE message reception status information includes the message reception status of the merging unit, the protection device and the intelligent terminal, which is used to judge the abnormality of the sampling value and the switching value; When an event occurs on the device, the GOOSE data set is immediately updated and data frames are sent at specific time intervals: first, the second and third frames are sent at intervals of T1, and then the fourth and fifth frames are sent at intervals of T2 and T3, where T2 is twice T1 and T3 is twice T2; after sending 5 frames, the sending interval is restored to T0 and it is converted to the heartbeat message state, and the message survival time is twice T0; if the receiver does not receive the message within 4 times T0, it is determined that the connection is interrupted and a link break alarm is triggered.

4. The method for locating faults of secondary equipment in a substation based on a spatiotemporal graph convolutional network model according to claim 1 is characterized in that: In the step S2, the specific steps are: S21: Preprocess the historical data and eliminate the influence of dimension by normalization; S22: The Pearson correlation coefficient is used to analyze the linear correlation between each feature and the fault, remove the low-correlation features, retain the high-correlation features, and construct a new fault feature set.

5. The method for locating faults of secondary equipment in a substation based on a spatiotemporal graph convolutional network model according to claim 1 is characterized in that: In the step S3, the specific steps are: S31: construct a fault feature fusion weight matrix according to the data values, change trends and change rates of the fault feature set in the historical data; S32: Multiply the fault feature set by the fault feature fusion weight matrix to obtain fault feature fusion data.

6. The method for locating faults of secondary equipment in a substation based on a spatiotemporal graph convolutional network model according to claim 1 is characterized in that: In step S4, the 1D-CNN network is used to perform a convolution operation on the time dimension of the data to extract time series information; the 1D-CNN network includes two convolution layers and a flattening operation, each convolution layer includes a convolution operation and a pooling operation; after the second pooling operation, a fully connected layer is also included to flatten the high-dimensional data into one-dimensional data; the specific steps are: The output feature matrix of the previous layer is used as the input feature matrix of the current layer. The local patterns in the input features are extracted through the weight function. Nonlinearity is introduced through the activation function to obtain the output of the current layer, that is, the feature map or activation value of the layer.

7. The method for locating faults of secondary equipment in a substation based on a spatiotemporal graph convolutional network model according to claim 1 is characterized in that: In step S4, the GCN network updates the feature representation of each node by processing the data after the convolution operation, combining spatial convolution with the information of adjacent nodes aggregated by the graph structure, and is used to extract the spatial structural relationship of the data to process the nonlinear features in the multivariate time series; The specific steps are: The output feature matrix of the previous layer is multiplied by the weight matrix to obtain the learnable parameters of the graph convolution layer, and is multiplied by the adjacency matrix and normalized to obtain the connection relationship between the nodes in the feature graph. After adjusting the output of the network through the bias top, nonlinearity is introduced through the activation function to obtain the output feature matrix of the current layer.

8. The method for locating faults of secondary equipment in a substation based on a spatiotemporal graph convolutional network model according to claim 1 is characterized in that: In the step S5, the specific steps are: S51: adaptively setting a dynamic threshold of the number of fault characteristic information according to the basic threshold and weather influencing factors to improve the sensitivity of detecting secondary equipment faults; when the total number of fault characteristic information exceeds the set threshold, triggering the fault location function; S52: Locate the fault location through the secondary equipment fault inference rule; if it fails, extract the filtered fault feature set obtained in step S2, fuse it according to step S3 and input it into the STGCN model trained in step S4 to obtain the final secondary equipment fault location result.

9. A substation secondary equipment fault location system based on a spatiotemporal graph convolutional network model, characterized by: The data acquisition submodule is used to obtain the historical data of the secondary equipment, build a fault feature set including the operating status information, SV / GOOSE receiving status information and sampling values; sort the fault feature data according to the time series and correspond them one by one with the corresponding secondary equipment faults; The data screening submodule is used to extract and screen the fault features with high correlation and construct the screened fault feature set; The model training and testing submodule is used to build an STGCN model consisting of three layers of 1D-CNN networks and one layer of GCN network to simultaneously learn the spatial and temporal features of graph data; The data in the fault feature set is divided into a training set and a test set. The training set is used for model learning, and the test set is used to evaluate the performance and accuracy of the model. The fault location submodule is used to set the threshold of the number of fault feature information to detect secondary equipment faults. When a secondary equipment fault is detected, the fault location is diagnosed and located according to the fault reasoning rules. If the reasoning rules cannot accurately locate the fault location, the fault feature set is input into the STGCN model to identify and locate the fault location of the secondary equipment through the model.

10. The STGCN model for fault location of secondary equipment in substations is characterized by: It includes multiple superimposed 1D-CNN networks for learning and capturing the temporal dependencies between data variables, and GCN networks for extracting the spatial dependencies between data variables; it also includes a fully connected layer for outputting the final result.

Images