Power distribution system operation and maintenance management method and system based on data fusion analysis technology

Abstract

The invention discloses a power distribution system operation and maintenance management method based on a data fusion analysis technology, and relates to the field of operation and maintenance management, and the method comprises the steps: obtaining a campus information distribution diagram and historical power utilization information; extracting campus electrical devices; constructing to obtain a campus line topological graph; screening out a plurality of key campus electrical devices; marking a key feeder terminal device; acquiring key terminal information of a key feeder terminal device; performing fault positioning in the campus line topological graph based on the line fault judgment matrix to obtain a plurality of first fault sections; extracting a plurality of fault topology sub-graphs; and performing fault positioning on all the fault topology sub-graphs based on a fault section positioning model to obtain a plurality of second fault sections, and correcting all the first fault sections by using all the second fault sections to obtain a line fault section. According to the invention, accurate fault positioning of the distribution line can be effectively realized.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of operation and maintenance management, and in particular, to a distribution system operation and maintenance management method and system based on data fusion analysis technology. Background Art

[0002] With the development of social economy, the process of electricity marketization continues to deepen, the number of electricity users has exploded, and the stability requirements for the distribution system are getting higher and higher. Therefore, once a fault occurs in the distribution system, if the fault cannot be located and repaired in time, it will have a serious impact on industrial production, residents' lives and other aspects. However, as the demand for electricity continues to grow, the network scale of the distribution system has gradually expanded and its structure has become more and more complex, making it more difficult to locate the fault of the distribution system and taking longer time.

[0003] In the traditional distribution system operation and maintenance management method, manual inspection and troubleshooting of the electrical equipment of the distribution system are mainly relied on. However, due to the complex structure of the distribution system and the large number of electrical equipment, relying on manual troubleshooting not only wastes manpower and material resources, but is also prone to omissions. If the faulty equipment is not promptly found and repaired or replaced, errors may occur in the power status data uploaded by the power system equipment, making it difficult to locate the power system fault in a timely manner based on the power status data. In addition, in the traditional distribution system operation and maintenance management method, although the power status data of the power system can be collected and monitored in real time through intelligent equipment, the analysis of the power status data still needs to rely on manual analysis. Therefore, when a power system fails, it is difficult to quickly and accurately locate the fault in the power system in a timely manner, which may cause serious social impact. Summary of the invention

[0004] The embodiments of the present application provide a distribution system operation and maintenance management method and system based on data fusion analysis technology, which are used to solve the problem that it is difficult to quickly and accurately locate faults in the distribution system in the prior art.

[0005] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions:

[0006] In a first aspect, a distribution system operation and maintenance management method based on data fusion analysis technology is provided, the method comprising:

[0007] Obtaining a campus information distribution map and historical electricity usage information of a target campus, wherein the campus information distribution map includes a campus line distribution map;

[0008] Extracting all campus electrical devices in the campus power distribution lines of the target campus from the campus line distribution map;

[0009] Performing line topology analysis on the campus line distribution map to obtain device connection relationships between all campus electrical devices, taking all campus electrical devices as line nodes, and constructing a campus line topology map based on the device connection relationships, wherein the campus electrical devices include feeder terminal devices;

[0010] Analyze the device key coefficients of all the campus electrical devices in combination with the historical power consumption information and the campus line topology map, and select a number of the campus electrical devices as key campus electrical devices from all the campus electrical devices according to the device key coefficients;

[0011] If the device connection relationship exists between any of the feeder terminal devices and any of the key campus electrical devices, a redundant sensor pre-installed at the feeder terminal device is enabled, and the feeder terminal device with the redundant sensor enabled is used as a key feeder terminal device;

[0012] Acquire key terminal information of all the key feeder terminal devices, and edge terminal information of all other devices among the feeder terminal devices except the key feeder terminal devices;

[0013] Based on the campus line topology map, the key terminal information and the edge terminal information are integrated to construct a line fault judgment matrix, and based on the line fault judgment matrix, fault location is performed in the campus line topology map to obtain several first fault sections in the campus line topology map;

[0014] Extracting a plurality of fault topology subgraphs from the campus line topology graph according to all the first fault sections;

[0015] Building a fault section location model based on the graph neural network model, using the fault section location model to locate the fault in all the fault topology subgraphs, and obtaining several second fault sections in the campus line topology map;

[0016] All of the second fault sections are used to correct all of the first fault sections to obtain several line fault sections of the campus power distribution line.

[0017] Optionally, the historical electricity usage information includes historical electricity usage and historical electricity usage duration, the campus information distribution map further includes a campus building distribution map, and combining the historical electricity usage information and the campus line topology map to analyze the device key coefficients of all campus electrical devices, and selecting a number of campus electrical devices as key campus electrical devices from all campus electrical devices according to all the device key coefficients includes the following steps:

[0018] Divide the target campus into regions according to the campus building distribution map to obtain multiple campus electricity consumption areas;

[0019] Combining the historical power consumption and the historical power consumption duration, dividing the regional power consumption levels for all the campus power consumption areas;

[0020] Position matching is performed between the campus line distribution map and the campus building distribution map to obtain device area locations of all campus electrical devices;

[0021] For any campus electrical device, an initial device critical coefficient is allocated to the campus electrical device according to the regional power consumption level corresponding to the device regional location;

[0022] Calculating the node centrality of the campus electrical devices according to the device connection relationship;

[0023] Correcting the initial device critical coefficient to a device critical coefficient using the node centrality;

[0024] A number of campus electrical components whose component critical coefficients are greater than or equal to a preset coefficient threshold are marked as critical campus electrical components.

[0025] Optionally, based on the campus line topology map, the key terminal information and the edge terminal information are integrated to construct a line fault judgment matrix, and fault location is performed in the campus line topology map based on the line fault judgment matrix to obtain the first fault section of the campus line topology map, including the following steps:

[0026] For any of the key feeder terminal devices, calculating the information difference between the key terminal information collected by the redundant sensor in the key feeder terminal device and the key terminal information collected by other sensors in the key feeder terminal device except the redundant sensor, to obtain a plurality of key terminal information differences;

[0027] If the absolute value of any difference of the key terminal information is greater than or equal to a preset difference threshold, it is determined that abnormal terminal information exists in the key terminal information;

[0028] If the absolute values ​​of all the key terminal information differences are less than the difference threshold, it is determined that there is no abnormal terminal information in the key terminal information;

[0029] If there is abnormal terminal information in the key terminal information, selecting the key terminal information collected by the redundant sensor as the target terminal information;

[0030] Performing data fusion on the target terminal information and the edge terminal information to obtain target feeder terminal information;

[0031] Building a line fault judgment matrix in combination with the campus line topology map and all the target feeder terminal information, and locating several primary fault sections in the campus line topology map based on the line fault judgment matrix;

[0032] For any of the primary fault sections, performing information verification on the target terminal information based on the primary fault section and using an information verification function;

[0033] If the information verification result shows that there is no information error in the target terminal information, it is determined that the primary fault section is the first fault section of the campus line topology map;

[0034] If the information verification result shows that the target terminal information has information errors, the target terminal information is updated according to all other information in the key terminal information except the target terminal information to obtain the reference terminal information;

[0035] The reference terminal information and the edge terminal information are combined to perform fault location in the campus line topology map to obtain a plurality of first fault sections in the campus line topology map.

[0036] Optionally, the step of building a line fault judgment matrix in combination with the campus line topology map and all the target feeder terminal information, and locating a number of primary fault sections in the campus line topology map based on the line fault judgment matrix comprises the following steps:

[0037] Acquire electrical parameters of all campus electrical devices according to the target feeder terminal information, and analyze the power direction of all campus electrical devices in combination with the electrical parameters and the topological structure type of the campus line topology diagram;

[0038] Based on the campus line topology diagram, a campus line description matrix of the campus power distribution line is constructed in combination with the line power direction and the device connection relationship;

[0039] According to the electrical parameters and using a threshold method, device fault information in the target feeder terminal information is obtained, and a campus fault information matrix of the campus power distribution line is constructed by combining the target feeder terminal information and the campus line topology map;

[0040] Combining the campus line description matrix and the campus fault information matrix to construct a line fault judgment matrix;

[0041] According to the line fault judgment matrix and using preset fault location rules, fault location is performed in the campus line topology map to obtain several primary fault sections of the campus line topology map.

[0042] Optionally, the campus electrical equipment further includes a main power distribution device, a secondary power distribution device, and campus power equipment, and the information verification of the target terminal information based on the primary fault section and using an information verification function includes the following steps:

[0043] converting the primary fault section into a primary fault section matrix according to the line fault judgment matrix;

[0044] Taking the primary fault section as the center point, the campus line topology diagram is divided into an upstream section and a downstream section, wherein the upstream section is connected to the main power distribution equipment, and the downstream section is connected to the campus power equipment;

[0045] Taking the campus line topology as a reference, obtaining the power distribution status values ​​of all the secondary power distribution equipment according to the campus fault information matrix, wherein the status power distribution values ​​include the first power distribution status value of the upstream section and the second power distribution status value of the downstream section;

[0046] Analyze the status values ​​of all line sections in the campus line topology map according to all the primary fault sections to obtain a plurality of section status values, wherein the section status values ​​include an upstream section status value and a downstream section status value;

[0047] Integrate all the upstream segment status values ​​and all the downstream segment status values ​​to obtain an upstream total status value and a downstream total status value respectively;

[0048] The primary fault section matrix, the power distribution status value, the upstream section status value, the downstream section status value, the upstream total status value and the downstream total status value are input into the information verification function to obtain the primary fault verification matrix. The information verification function is as follows:

[0049]

[0050] Where i is a matrix element in the primary fault section matrix, x represents the upstream line, y represents the downstream line, D x represents the first power distribution state value, D y represents the second power distribution state value, Indicates the upstream total status value, Represents the total downstream status value, N x and N y represents the total number of the secondary power distribution devices in the upstream line x and the downstream line y, respectively, x and M y represents the total number of all the line segments in the upstream line x and the downstream line y, respectively, Q i，x represents the upstream segment status value of all the route segments in the upstream route x, Qi，y represents the downstream segment state value of all the line segments in the downstream line y, and Π represents a logical operation or operation;

[0051] If the primary fault check matrix and the primary fault section matrix are equal matrices, it is determined that there is no information error in the target terminal information;

[0052] If the primary fault check matrix and the primary fault section matrix are not equal matrices, it is determined that there is an information error in the target terminal information.

[0053] Optionally, extracting a plurality of fault topology subgraphs from the campus line topology map according to the first fault section comprises the following steps:

[0054] Marking the line nodes for faults according to the section positions of all the first fault sections in the campus line topology map to obtain a plurality of the first fault line nodes;

[0055] Performing node aggregation on the first fault line node to obtain a plurality of fault line node sets;

[0056] A plurality of fault topology subgraphs are extracted from the campus line topology graph according to all the fault line node sets.

[0057] Optionally, the fault section location model is constructed based on the graph neural network model, and the fault section location model is used to locate the fault in all the fault topology subgraphs to obtain several second fault sections in the campus line topology map, including the following steps:

[0058] A fault section location model is constructed based on a graph neural network model, wherein the fault section location model includes a fault feature extraction module, a fault feature weighting module, a feature dimension transformation module and a fault classification learning module. The fault feature extraction module is constructed based on a spatiotemporal graph neural network model, the fault feature weighting module is constructed based on a graph attention network model, the feature dimension transformation module is constructed based on a one-dimensional convolutional neural network model, and the fault classification learning module is constructed based on a full convolutional neural network model.

[0059] The fault section location model is trained using a pre-constructed fault location training set, and the fault topology subgraphs are sequentially input into the fault section location model for fault location, thereby obtaining a plurality of second fault sections in the campus power distribution line.

[0060] Optionally, sequentially inputting the fault topology subgraphs into the fault section location model to perform fault location, and obtaining a plurality of second fault sections in the campus power distribution line comprises the following steps:

[0061] Input the fault topology subgraph into the fault feature extraction module of the fault section location model to perform convolution operation on the fault topology subgraph in the time and space scale to obtain the fault time and space features of the fault topology subgraph;

[0062] The fault spatiotemporal features are sequentially input into the fault feature weighting module to calculate the attention coefficient, and weights are assigned to the fault spatiotemporal features according to the attention coefficient calculation results;

[0063] Performing weighted fusion on the fault spatiotemporal features after weight allocation to obtain fault fusion features;

[0064] The fault fusion features are input into the feature dimension transformation module for feature mapping, and the fault fusion features after feature mapping are input into the fault classification learning module for classification learning to obtain several second fault sections in the campus line topology map.

[0065] Optionally, the method of using all the second fault sections to correct all the first fault sections to obtain several line fault sections of the campus power distribution line comprises the following steps:

[0066] Marking the line node for fault according to the position of the second fault section in the campus line topology map to obtain a second fault line node;

[0067] Analyze whether the second fault line node coincides with the first fault line node according to the campus line topology map;

[0068] If the second fault line node coincides with the first fault line node, marking the second fault section corresponding to the coincident second fault line node as a topological line fault section;

[0069] All the topological line fault sections are position-matched with the campus line distribution map, and several line fault sections in the campus line distribution map are located according to the position matching structure.

[0070] In a second aspect, the present application provides a distribution system operation and maintenance management system based on data fusion analysis technology, characterized in that it includes:

[0071] a memory configured to store instructions; and

[0072] The processor is configured to call the instruction from the memory and to implement the method for distribution system operation and maintenance management based on data fusion analysis technology according to any one of the first aspects when executing the instruction.

[0073] Through the above technical scheme, the present application uses historical electricity consumption information and campus building distribution map to screen out key campus electrical devices, marks the feeder terminal devices connected to the key campus electrical devices as key feeder terminal devices, and enables the redundant sensors pre-installed in the key feeder terminal devices. The redundant sensors are used to perform self-inspection on the key feeder terminal devices, which can effectively detect whether there are faulty devices in the key feeder terminal devices. While ensuring the reliability of the key terminal information, the key feeder terminal devices can also be detected. The matrix method is used to first locate the fault of the line in the distribution system to obtain the first fault section. On the basis of the first fault section, the graph neural network model is used to correct the first fault section to obtain a more accurate line fault section. In summary, the present invention not only solves the problem that the prior art is difficult to quickly and accurately locate the fault of the distribution system, but also reduces the waste of power resources to a certain extent and improves the utilization rate of power resources.

[0074] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 A flow chart of a distribution system operation and maintenance management method based on data fusion analysis technology provided in an embodiment of the present application;

[0076] Figure 2 This is an example diagram of a campus line topology map provided in an embodiment of the present application. DETAILED DESCRIPTION

[0077] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0078] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0079] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0080] Figure 1 The flowchart of a method for power distribution system operation and maintenance management based on data fusion analysis technology according to an embodiment of the present application is schematically shown. Figure 1 As shown, the embodiment of the present application provides a method for distribution system operation and maintenance management based on data fusion analysis technology, which may include the following steps:

[0081] S101. Obtain a campus information distribution map and historical electricity usage information of a target campus, wherein the campus information distribution map includes a campus line distribution map.

[0082] In this embodiment, the campus information distribution map includes a campus line distribution map and a campus building distribution map. The campus line distribution map refers to the distribution network plan of the target campus, including multiple feeder terminal devices, main distribution equipment, secondary distribution equipment, campus power equipment and other electrical devices, as well as the connection lines between the electrical devices. Among them, the feeder terminal unit (abbreviated as FTU) has remote control, telemetry, telesignaling, and fault detection functions, and can provide the operation status of the distribution system and various parameters and information required for monitoring and control, including switch status, power parameters, interphase faults, ground faults, and parameters during faults. The main distribution equipment refers to the main distribution box, which is used to connect the collection branch line loop to the trunk line to realize the distribution and control of electricity. The secondary distribution equipment includes a primary distribution box, a secondary distribution box, and a tertiary distribution box, which is responsible for distributing the power output of the main distribution box to various levels of campus power equipment in turn, such as computers, air conditioners, experimental equipment (such as electric thermostats, mass spectrometers, nuclear magnetic resonance instruments), etc. on campus. The campus building distribution map refers to the floor plan of the target campus, including the location distribution of all buildings in the target campus, such as teaching buildings, laboratories, canteens, etc. The historical electricity consumption information includes the historical electricity consumption and historical electricity consumption duration of each teaching building in the target campus and the classrooms, offices, laboratories and other areas in the teaching building. The historical electricity consumption is the historical average daily electricity consumption, and the historical electricity consumption duration is the historical average daily electricity consumption duration. For example, the average daily electricity consumption of classroom 306 in the first teaching building is 7.52kWh, and the average daily electricity consumption duration is 12 hours.

[0083] S102. Extract all campus electrical devices in the campus power distribution lines of the target campus from the campus line distribution map.

[0084] In this embodiment, campus electrical devices such as circuit breakers, section switches, interconnecting switches and distribution switch monitoring terminals (FTU) are extracted from the campus line distribution diagram. Drawing analysis software can be used to extract electrical devices, for example, EasyEDA (Jialichuang EDA), Eplan (electrical design software), etc.

[0085] S103. Perform line topology analysis on the campus line distribution map to obtain the device connection relationship between all campus electrical devices, take all campus electrical devices as line nodes, and construct a campus line topology map based on the device connection relationship. The campus electrical devices include feeder terminal devices.

[0086] The path between any two campus electrical devices is found by using tree search method, shortest path algorithm, node elimination method and other algorithms. Specifically, taking Dijkstra algorithm in the shortest path algorithm as an example, a campus electrical device in the campus line distribution map is randomly selected as the starting node, and two sets are initialized, namely the first set containing the shortest path nodes and the second set containing the undetermined shortest path nodes. Initially, the first set only contains the starting node, and all campus electrical devices except the campus electrical device as the starting node are input into the second set as the undetermined shortest path nodes. A distance array is initialized to record the shortest path estimate from the starting node to each node. Initially, the distances of all nodes except the starting node are set to infinity. The undetermined shortest path node A closest to the starting node is selected from the second set, added to the first set, and the distance estimate from node A to all nodes in the second set is updated. If the distance to a certain node through the undetermined shortest path node A is shorter than the known shortest distance, then update the distance estimate of the node and record the path information. Repeat the above steps of selecting the undetermined shortest path node and updating the distance estimate until the second set is empty, that is, all nodes have found the shortest path. By recording the nodes directly connected to each node on the shortest path, a shortest path tree from the starting node to all other nodes can be constructed, thereby identifying the device connection relationship between campus electrical devices in the campus line distribution map. Taking all campus electrical devices in the campus line distribution map as line nodes and device connection relationships as edges, a campus line topology map based on the campus line distribution map can be obtained.

[0087] At the same time, each campus electrical device can be numbered according to the distance between each campus electrical device and the main power supply in the distribution network, such as No. 1 circuit breaker, No. 2 circuit breaker, No. 3 section switch, No. 4 section switch, No. 5 section switch, etc. In addition, the method for calculating the distance between each campus electrical device and the main power supply in the distribution network includes Hadoop (distributed system infrastructure), breadth-first search algorithm, shortest path algorithm, etc. Taking the breadth-first search algorithm as an example, the main power supply is taken as the source node, starting from the source node, and expanding outward layer by layer, while calculating the number of edges passed between the source node and other nodes in the campus line topology map, and using the number of edges to measure the distance between each campus electrical device and the main power supply. If there are just a plurality of campus electrical devices and the number of edges (i.e., distance) between the main power supply is equal, then random numbering is performed. The purpose of allocating numbers is to distinguish different campus electrical devices, so that when facilitating subsequent fault location, the campus electrical device with fault can be quickly located according to the number.

[0088] By constructing a campus line topology map, the complex relationship between campus electrical devices in the campus line distribution map can be simplified into a topology map, which is convenient for subsequent analysis of the importance of each campus electrical device. At the same time, the fault propagation path can be determined through the device connection relationship between campus electrical devices. When a campus electrical device fails, the area affected by the fault can be identified by tracing the path of current flow, which helps to quickly locate the source of the fault.

[0089] S104. Analyze the device critical coefficients of all campus electrical devices in combination with the historical electricity consumption information and the campus line topology map, and select a number of campus electrical devices as key campus electrical devices from all campus electrical devices based on the device critical coefficients.

[0090] In this embodiment, the campus building distribution map refers to a plan view of the target campus, including all buildings in the target campus, such as teaching buildings, laboratories, canteens, etc. The target campus is divided into multiple power consumption areas according to the campus building distribution map. Specifically, each building is divided into a power consumption area, such as the first teaching building is power consumption area No. 1, and the canteen is power consumption area No. 2.

[0091] According to the historical power consumption and historical power consumption duration of each power consumption area, the regional power consumption level is divided for each power consumption area. After the level division of each power consumption area is completed, the campus line distribution map is matched with the campus building distribution map to obtain the corresponding position of each campus electrical device in the campus building distribution map, for example, the No. 16 secondary power distribution equipment is in the No. 6 power consumption area. Specifically, the coordinate system and size of the campus line distribution map and the campus building distribution map are unified, and the device coordinates of each campus electrical device are matched with the coordinate range of the campus power consumption area in the campus building distribution map. If the coordinates of the campus electrical device are within the coordinate range of the power consumption area, the campus power consumption area corresponding to the campus electrical device in the campus building distribution map is obtained, thereby obtaining the device area position of the campus electrical device. Since it is only necessary to allocate the initial device key coefficient for the campus electrical device in the campus power consumption area according to the regional power consumption level of the campus power consumption area, it is not necessary to obtain the precise position of the campus electrical device in the campus building distribution map, and it is only necessary to determine the campus power consumption area where each campus electrical device is located in the campus building distribution map.

[0092] After obtaining the corresponding levels of all campus electrical devices, an initial device critical coefficient is assigned to each campus electrical device according to the regional electricity consumption level corresponding to each campus electrical device. The node centrality of each campus electrical device is calculated based on the connection relationship between the line node corresponding to each campus electrical device and other line nodes in the campus line topology map. The node centrality includes the degree centrality, eigenvector centrality, betweenness centrality and closeness centrality of the line node. The degree centrality depends on the node degree. The degree centrality, eigenvector centrality, betweenness centrality and closeness centrality are weighted averaged to obtain the average centrality. The initial device critical coefficient is corrected according to the average centrality of each campus electrical device to obtain the device critical coefficient of each campus electrical device. After obtaining the device critical coefficients of all campus electrical devices, the campus electrical devices whose device critical coefficients are greater than or equal to the preset coefficient threshold are marked as critical campus electrical devices.

[0093] S105. If there is a device connection relationship between any feeder terminal device and any key campus electrical device, a redundant sensor pre-installed at the feeder terminal device is enabled, and the feeder terminal device with the redundant sensor enabled is used as a key feeder terminal device.

[0094] In this embodiment, if there is a device connection relationship between the feeder terminal device and the key campus electrical device, it means that the information monitored by the feeder terminal device comes from the key campus electrical device. Therefore, once the sensor inside the feeder terminal device fails, it may cause errors in the key terminal information monitored by the feeder terminal device. The positioning result obtained by subsequent fault positioning based on the erroneous key terminal information may also be erroneous. Therefore, it is necessary to monitor whether the feeder terminal device connected to the key campus electrical device is faulty. Specifically, a group of redundant sensors are pre-installed in each feeder terminal device. The redundant sensors are almost identical to the original basic sensors inside the feeder terminal device in terms of sensor type, sensor model, sensor performance, etc. If it is monitored that there is a device connection relationship between the feeder terminal device and the key campus electrical devices, the redundant sensors inside the feeder terminal device will be immediately enabled, and the feeder terminal device will be marked as a key feeder terminal device. In the subsequent process of the key feeder terminal device monitoring the information of the distribution system, two sets of key terminal information of the same type but possibly different data will be obtained. For example, both sets of key terminal information contain information such as phase current, phase voltage, active power and reactive power, but the specific values ​​of this information may be different, or even differ greatly, but the information type is the same. Based on the information difference between the above-mentioned information of the same type, it can be detected whether there is a device failure in the key feeder terminal device.

[0095] S106. Acquire key terminal information of all key feeder terminal devices and edge terminal information of all feeder terminal devices except the key feeder terminal devices.

[0096] In this embodiment, the key terminal information of all key feeder terminal devices is obtained, and the key terminal information includes information such as phase current, phase voltage, active power and reactive power, as well as edge terminal information of other feeder terminal devices that are not connected to key campus electrical devices. The edge terminal information also includes information such as phase current, phase voltage, active power and reactive power.

[0097] S107. Based on the campus line topology map, the key terminal information and the edge terminal information are integrated to construct a line fault judgment matrix, and the fault is located in the campus line topology map based on the line fault judgment matrix to obtain several first fault sections in the campus line topology map.

[0098] In this embodiment, for any key feeder terminal device, the information difference between the key terminal information collected by the redundant sensor inside the key feeder terminal device and the key terminal information collected by other sensors in the key feeder terminal device except the redundant sensor is calculated to obtain multiple key terminal information differences. According to the key terminal information difference, it is judged whether there is abnormal terminal information in the key terminal information. If there is abnormal terminal information in the key terminal information, the key terminal information collected by the redundant sensor is first selected as the target terminal information. This is because the redundant sensor is rarely used and the probability of failure is also small. Therefore, the key terminal information collected by the redundant sensor is first used as the target terminal information. Of course, the sensor with a fault may also be a redundant sensor, so the target terminal information collected by the redundant sensor will be verified using the information verification function later.

[0099] The target terminal information and edge terminal information are merged to obtain the complete feeder terminal information of the distribution system, that is, the target feeder terminal information. Then, based on the campus line topology map, the campus line description matrix and the campus fault information matrix are constructed according to the target feeder terminal information. The matrix product of the campus line description matrix and the campus fault information matrix is ​​normalized to obtain the line fault judgment matrix. The line fault judgment matrix is ​​used to locate the fault in the campus line topology map to obtain several primary fault sections located in the campus line topology map. The primary fault section is verified using the information verification function. If the verification result shows that there is no information error in the target terminal information, the primary fault section can be directly determined to be the first fault section of the campus line topology map.

[0100] S108. Extract several fault topology sub-graphs from the campus line topology graph according to all first fault sections.

[0101] In this embodiment, according to the first fault section located in the campus line topology map, the line nodes located in the first fault section are marked as faults to obtain multiple first fault line nodes, and adjacent fault nodes are aggregated to obtain several fault line node sets. Commonly used node aggregation methods include DBSCAN (density-based clustering algorithm) algorithm and spectral clustering algorithm, etc., and several fault topology subgraphs are extracted from the campus line topology map according to all several fault line node sets.

[0102] S109. Construct a fault section location model based on the graph neural network model, use the fault section location model to locate the fault in all fault topology subgraphs, and obtain several second fault sections in the campus line topology map.

[0103] In this embodiment, a fault section location model is constructed based on a graph neural network model. The fault section location model includes a fault feature extraction module, a fault feature weighting module, a feature dimension transformation module and a fault classification learning module. The fault feature extraction module is constructed based on a spatiotemporal graph neural network model, the fault feature weighting module is constructed based on a graph attention network model, the feature dimension transformation module is constructed based on a one-dimensional convolutional neural network model, and the fault classification learning module is constructed based on a full convolutional neural network model. The fault feature extraction module is used to capture the spatial correlation between nodes and the front-to-back correlation between fault topology subgraphs at different times. The fault feature weighting module is used to assign weights to fault features of different dimensions according to the idea of ​​learning attention weights, and to perform feature fusion on fault features that have completed weight assignment. The feature dimension transformation module is used to extract features and transform dimensions of fault features. The fault classification learning module is used to map the extracted high-dimensional fault features to a low-dimensional space containing fault section information for classification learning. Finally, the maximum activation value (argmax) obtained by feature classification through the Softmax function is the second fault section.

[0104] S110. All the first fault sections are corrected using all the second fault sections to obtain several line fault sections of the campus power distribution line.

[0105] In this embodiment, the line node is marked as faulty according to the position of the second fault section in the campus line topology map to obtain the second fault line node, and the second fault line node is analyzed according to the campus line topology map to see whether it coincides with the first fault line node. If the second fault line node coincides with the first fault line node, the second fault section corresponding to the coincident second fault line node is marked as a topological line fault section, and all topological line fault sections are positionally matched with the campus line distribution map, and several line fault sections in the campus line distribution map are located according to the position matching results.

[0106] In one embodiment, the historical electricity usage information includes historical electricity usage and historical electricity usage duration, and the campus information distribution map further includes a campus building distribution map. The device key coefficients of all campus electrical devices are analyzed in combination with the historical electricity usage information and the campus line topology map. The steps of selecting a number of campus electrical devices as key campus electrical devices from all campus electrical devices according to the device key coefficients include the following:

[0107] Divide the target campus into regions according to the campus building distribution map to obtain multiple campus electricity consumption areas;

[0108] Combine historical electricity consumption and historical electricity consumption duration to divide all campus electricity consumption areas into regional electricity consumption levels;

[0109] Match the campus line distribution map with the campus building distribution map to obtain the device area locations of all campus electrical devices;

[0110] For any campus electrical device, an initial device criticality factor is assigned to the campus electrical device according to the regional power consumption level corresponding to the device's regional location;

[0111] Calculate the node centrality of campus electrical devices based on device connection relationships;

[0112] Using node centrality, the initial device critical coefficient is corrected to the device critical coefficient;

[0113] Several campus electrical devices whose device criticality coefficients are greater than or equal to a preset coefficient threshold are marked as critical campus electrical devices.

[0114] In this embodiment, the campus building distribution map refers to a plan view of the target campus, including all buildings in the target campus, such as teaching buildings, laboratories, canteens, etc. The target campus is divided into multiple power consumption areas according to the campus building distribution map. Specifically, each building is divided into a power consumption area, such as the first teaching building is power consumption area No. 1, and the canteen is power consumption area No. 2.

[0115] The regional electricity consumption level is divided for each electricity consumption area according to the historical electricity consumption and historical electricity consumption duration of each electricity consumption area. Specifically, the electricity consumption area with a historical electricity consumption greater than a preset first electricity consumption threshold and a historical electricity consumption duration greater than the preset first electricity consumption duration threshold is divided into a first-level electricity consumption area; the electricity consumption area with a historical electricity consumption greater than the first electricity consumption threshold or a historical electricity consumption duration greater than the first electricity consumption duration threshold is divided into a second-level electricity consumption area; the electricity consumption area with a historical electricity consumption less than or equal to the first electricity consumption threshold and greater than the preset second electricity consumption threshold, and a historical electricity consumption duration less than the first electricity consumption duration threshold is divided into a second-level electricity consumption area. The power consumption areas whose long threshold is greater than the preset second power consumption duration threshold are divided into third-level power consumption areas, the power consumption areas whose historical power consumption is less than or equal to the first power consumption threshold and greater than the second power consumption threshold, or the historical power consumption duration is less than the first power consumption threshold and greater than the second power consumption duration threshold are divided into fourth-level power consumption areas, and the power consumption areas whose historical power consumption is less than the second power consumption threshold and the historical power consumption duration is less than the second power consumption threshold are divided into fifth-level power consumption areas, among which the first power consumption threshold is greater than the second power consumption threshold, and the first power consumption duration threshold is greater than the second power consumption duration threshold.

[0116] After completing the level division of each power consumption area, the campus line distribution map is matched with the campus building distribution map to obtain the corresponding position of each campus electrical device in the campus building distribution map, for example, the No. 16 secondary distribution equipment is in the No. 6 power consumption area. Specifically, the campus line distribution map and the campus building distribution map are unified in coordinate system and size, and the device coordinates of each campus electrical device are matched with the coordinate range of the campus power consumption area in the campus building distribution map. If the coordinates of the campus electrical device are within the coordinate range of the power consumption area, the campus power consumption area corresponding to the campus electrical device in the campus building distribution map is obtained, thereby obtaining the device area position of the campus electrical device. Since it is only necessary to allocate the initial device key coefficient for the campus electrical device in the campus power consumption area according to the regional power consumption level of the campus power consumption area, it is not necessary to obtain the precise position of the campus electrical device in the campus building distribution map, and it is only necessary to determine the campus power consumption area where each campus electrical device is located in the campus building distribution map.

[0117] After obtaining the corresponding levels of all campus electrical devices, an initial device critical coefficient is assigned to each campus electrical device according to the regional electricity consumption level corresponding to each campus electrical device. Among them, the initial device critical coefficient assigned to the campus electrical devices located in the first-level electricity consumption area is the largest, followed by the second-level electricity consumption area, the third-level electricity consumption area, and the fourth-level electricity consumption area, and the fifth-level electricity consumption area is the smallest. For example, the initial device critical coefficient assigned to the campus electrical devices in the first-level electricity consumption area is 1, the campus electrical devices in the second-level electricity consumption area is 0.8, the campus electrical devices in the third-level electricity consumption area is 0.6, the campus electrical devices in the fourth-level electricity consumption area is 0.4, and the campus electrical devices in the fifth-level electricity consumption area is 0.2.

[0118] The node centrality of each campus electrical device is calculated based on the connection relationship between the line node corresponding to each campus electrical device and other line nodes in the campus line topology map. The node centrality includes the degree centrality, eigenvector centrality, betweenness centrality and closeness centrality of the line node. The degree centrality depends on the node degree, which refers to the number of node edges connected to the line node. The eigenvector centrality depends on the node degree of the neighboring node. The larger the node degree of the neighboring node, the higher the eigenvector centrality of the line node, which means that the line node is more important. The betweenness centrality measures the extent to which a line node is located on the shortest path between other node pairs. The line node with high betweenness centrality plays a key role in information transmission, resource flow, etc., which means that the line node with high betweenness centrality is more important. The closeness centrality is based on the sum of the shortest paths from the line node to all other line nodes in the network. The smaller the sum of the shortest paths, the higher the closeness centrality of the line node, which also means that the line node is more important. Calculate the degree centrality, eigenvector centrality, betweenness centrality and closeness centrality of all line nodes, perform weighted average on the above degree centrality, eigenvector centrality, betweenness centrality and closeness centrality to obtain average centrality, correct the initial device critical coefficient according to the average centrality of each campus electrical device, and obtain the device critical coefficient of each campus electrical device. After obtaining the device critical coefficients of all campus electrical devices, mark the campus electrical devices whose device critical coefficients are greater than or equal to the preset coefficient threshold as critical campus electrical devices.

[0119] In one embodiment, based on the campus line topology map, the key terminal information and the edge terminal information are integrated to construct a line fault judgment matrix, and the fault is located in the campus line topology map based on the line fault judgment matrix, and the first fault section of the campus line topology map is obtained, which includes the following steps:

[0120] For any key feeder terminal device, calculating the information difference between the key terminal information collected by the redundant sensor in the key feeder terminal device and the key terminal information collected by other sensors in the key feeder terminal device except the redundant sensor, to obtain a plurality of key terminal information differences;

[0121] If the absolute value of any key terminal information difference is greater than or equal to the preset difference threshold, it is determined that abnormal terminal information exists in the key terminal information;

[0122] If the absolute values ​​of all key terminal information differences are less than the difference threshold, it is determined that there is no abnormal terminal information in the key terminal information;

[0123] If there is abnormal terminal information in the key terminal information, the key terminal information collected by the redundant sensor is selected as the target terminal information;

[0124] The target terminal information and the edge terminal information are data-fused to obtain the target feeder terminal information;

[0125] A line fault judgment matrix is ​​constructed by combining the campus line topology map and all target feeder terminal information, and several primary fault sections are located in the campus line topology map based on the line fault judgment matrix;

[0126] For any primary fault section, information verification is performed on the target terminal information based on the primary fault section and using an information verification function;

[0127] If the information verification result shows that there is no information error in the target terminal information, the primary fault section is determined to be the first fault section of the campus line topology map;

[0128] If the information verification result shows that the target terminal information has information errors, the target terminal information is updated according to all other information in the key terminal information except the target terminal information to obtain the reference terminal information;

[0129] The reference terminal information and the edge terminal information are combined to locate the fault in the campus line topology map to obtain the first fault section of the campus line topology map.

[0130] In this embodiment, for any key feeder terminal device, the information difference between the key terminal information collected by the redundant sensor inside the key feeder terminal device and the key terminal information collected by other sensors in the key feeder terminal device except the redundant sensor is calculated to obtain multiple key terminal information differences. For example, the key terminal information collected by the redundant sensor is phase current a1, phase voltage b1, etc., and the key terminal information collected by other sensors (basic sensors in the key feeder terminal device) is phase current a2, phase voltage b2, etc., then the phase current a1 is subtracted from the phase current a2, and the phase voltage b1 is subtracted from the phase voltage b2. This is because the redundant sensor and the basic sensor are consistent in model, type, and performance, and are located In the same key feeder terminal device, therefore, theoretically, the key terminal information collected by the redundant sensor and the basic sensor should be equal or the information difference should be negligible, that is, the absolute value of the difference between all key terminal information is less than the difference threshold. If the difference between the information collected by the two is large, that is, the absolute value of the key terminal information difference is greater than or equal to the preset difference threshold, it means that there is a sensor failure in the redundant sensor or the basic sensor. Therefore, it is determined that there is abnormal terminal information in the key terminal information, and the key feeder terminal device is marked as an abnormal feeder terminal device, and the number of the abnormal feeder terminal device is uploaded to the distribution system management platform, reminding the staff of the distribution system management platform to promptly repair the abnormal feeder terminal device.

[0131] If there is abnormal terminal information in the key terminal information, the key terminal information collected by the redundant sensor is first selected as the target terminal information. This is because the redundant sensor is rarely used and the probability of failure is also small, so the key terminal information collected by the redundant sensor is first used as the target terminal information. Of course, the faulty sensor may also be a redundant sensor, so the target terminal information collected by the redundant sensor will be verified using the information verification function later.

[0132] The target terminal information and the edge terminal information are merged to obtain the complete feeder terminal information of the distribution system, that is, the target feeder terminal information. Then, based on the campus line topology map, the campus line description matrix and the campus fault information matrix are constructed according to the target feeder terminal information. The line fault judgment matrix is ​​obtained after the matrix product of the campus line description matrix and the campus fault information matrix is ​​normalized. The line fault judgment matrix is ​​used to locate the fault in the campus line topology map to obtain several primary fault sections located in the campus line topology map. The primary fault section is verified using the information verification function. If the verification result shows that there is no information error in the target terminal information, the primary fault section can be directly determined to be the first fault section of the campus line topology map. If the information verification result shows that there is an information error in the target terminal information, it means that the redundant sensor is faulty. Therefore, the target terminal information needs to be replaced with the key terminal information collected by the basic sensor. The target terminal information after the replacement is named the reference terminal information. In other words, the reference terminal information is the key terminal information collected by other sensors in the key feeder terminal device except the redundant sensor. Then, the same fault section location steps are performed, the benchmark terminal information and the edge terminal information are data-fused to obtain the fused terminal information, and a line fault judgment matrix is ​​constructed in combination with the campus line topology map and all the fused terminal information. Based on the line fault judgment matrix, several second primary fault sections are located in the campus line topology map, and the benchmark terminal information is verified according to the obtained primary fault sections and using the information verification function. Similarly, if the verification result shows that there is no information error in the benchmark terminal information, the second primary fault section is output as the first fault section. If the verification result shows that there is an information error in the benchmark terminal information, it means that the basic sensor in the key feeder terminal device has also failed. At this time, it is necessary to upload the number of the key feeder terminal device to the distribution system management platform again, and output an alarm message to remind the staff of the distribution system management platform to immediately go to the location of the abnormal feeder terminal device and immediately repair the abnormal feeder terminal device.

[0133] In one embodiment, a line fault judgment matrix is ​​constructed by combining the campus line topology map and all target feeder terminal information, and locating several primary fault sections in the campus line topology map based on the line fault judgment matrix includes the following steps:

[0134] The electrical parameters of all campus electrical devices are obtained according to the target feeder terminal information, and the power direction of all campus electrical devices is analyzed by combining the electrical parameters and the topological structure type of the campus line topology diagram;

[0135] Based on the campus line topology diagram, the campus line description matrix of the campus distribution line is constructed in combination with the line power direction and device connection relationship;

[0136] According to electrical parameters and using the threshold method, the device fault information in the target feeder terminal information is obtained, and the campus fault information matrix of the campus distribution line is constructed by combining the target feeder terminal information and the campus line topology map;

[0137] Combine the campus line description matrix and campus fault information matrix to build a line fault judgment matrix;

[0138] According to the line fault judgment matrix and using the preset fault location rules, fault location is performed in the campus line topology map to obtain several primary fault sections in the campus line topology map.

[0139] In this embodiment, the feeder terminal unit (FTU) is an intelligent terminal device specially designed for the power distribution system. It collects key data such as voltage and current in the power distribution system in real time through built-in sensors and data processing modules. These data are preliminarily processed, such as filtering and calibration, to improve the reliability of the data, and then used to calculate information such as phase difference. Therefore, the electrical parameters of all campus electrical devices can be directly extracted from the target feeder terminal information. The electrical parameters include parameters such as current, voltage, and phase difference. According to the topological structure type of the campus line topology diagram, the flow direction of current and voltage is analyzed. According to the flow direction of current and voltage, current, voltage, phase difference and the power calculation formula, the power direction can be analyzed. The power calculation formula is P=UIcosθ, U is voltage, I is current, θ is the phase difference between voltage and current, if the calculated power is positive, the power is in the positive direction, if the calculated power is negative, the power is in the negative direction. After calculating the power direction of all line nodes in the campus line topology, if the line node power is in the positive direction and there is a device connection relationship with other line nodes, the line node Dij=1 is defined. In other cases, the line node Dij=0 is defined. After all line nodes are defined, the campus line description matrix is ​​obtained.

[0140] When a line node with a current greater than the preset current threshold appears, it indicates that a fault has occurred in the power distribution system. When a fault occurs in the power distribution system, the power flow direction changes. The FTU installed at each node will upload three logic signals of "1, 0, -1" according to whether a fault current is detected and whether the direction of the fault current is the same as the positive direction of the network. 1, 0, -1 respectively indicate that a forward fault overcurrent flows through the line node, there is no fault overcurrent in the line node, and a reverse fault overcurrent flows through the line node. After obtaining the fault conditions of all line nodes, a campus fault information matrix is ​​constructed according to the fault conditions. The campus fault information matrix and the campus line description matrix are combined to obtain a line fault judgment matrix. The line fault judgment matrix is ​​as follows:

[0141]

[0142] Among them, P ij is the line fault judgment matrix between line node i and line node j, D ij is the campus line description matrix between line node i and line node j, G i1 is the campus fault information matrix between line node i and line node j.

[0143] According to the line fault judgment matrix and using the preset fault location rules, fault location is performed in the campus line topology map to obtain several primary fault sections in the campus line topology map. The preset fault location rules include: (1) for j with Pii=1 and Pij=1, Pjj=0 or -1 (j≠i); (2) for j with Pii=-1 and Pji=1, Pjj=0 (j≠i); (3) for j with Pii=0 and Pij=1, Pjj=-1 (j≠i); If any of the above three conditions are met and there is no T-connected section between line node i and line node j, it can be determined that the feeder section formed by line node i and line node j is the primary fault section. If any one of the above three conditions is met, and there is a T-connected section between line node i and line node j, for example, line node i is connected to line node j and is also connected to line node f, then continue to judge whether any one of the above three conditions is met between line node i and line node f. If it is judged that any one of the above three conditions is also met between line node i and line node f, then the T-connected section between line node i and line node j is determined to be the primary fault section.

[0144] Reference Figure 2 , the arrow direction in the figure is the specified positive direction, Z is the main distribution equipment, S is the campus power equipment, 1-7 represents the node number, (1)-(7) represents the section number, and the campus line description matrix is ​​as follows:

[0145]

[0146] Assuming that section (3) is the primary fault section, the campus fault information matrix is ​​as follows:

[0147] G=[1 1 1 -1 0 0 0] T

[0148] Here, T represents the transpose of the matrix.

[0149] Thus, the line fault judgment matrix can be obtained as follows:

[0150]

[0151] The line fault judgment matrix is ​​judged by using the preset fault location rule. P33=1, P34=1, P44=-1. The section between line node 3 and line node 4 meets the above condition (1). However, since the section between line node 3 and line node 4 is a T-connected section, it is necessary to further judge whether there is a fault between line node 3 and line node 7. Since P33=1, P37=1, P77=0, the above condition (1) is met, so there is also a fault between line node 3 and line node 7. According to the fault location rule, it can be judged that section (3) is the primary fault section, which is consistent with the assumption. Therefore, the matrix method can be used to locate the fault in the campus line topology map.

[0152] In one embodiment, the campus electrical equipment further includes a main power distribution device, a secondary power distribution device, and campus power equipment. Based on the primary fault section and using the information verification function to verify the target terminal information includes the following steps:

[0153] The primary fault section is converted into a primary fault section matrix according to the line fault judgment matrix;

[0154] The campus line topology is divided into an upstream section and a downstream section with the primary fault section as the center point. The upstream section is connected to the main power distribution equipment, and the downstream section is connected to the campus power equipment.

[0155] Based on the campus line topology map, the power distribution status values ​​of all secondary power distribution equipment are obtained according to the campus fault information matrix. The status distribution value includes the first power distribution status value of the upstream section and the second power distribution status value of the downstream section.

[0156] Analyze the status values ​​of all line sections in the campus line topology according to all primary fault sections, and obtain multiple section status values, wherein the section status values ​​include an upstream section status value and a downstream section status value;

[0157] Integrate all upstream section status values ​​and all downstream section status values ​​to obtain an upstream total status value and a downstream total status value respectively;

[0158] The primary fault section matrix, the power distribution status value, the upstream section status value, the downstream section status value, the upstream total status value and the downstream total status value are input into the information verification function to obtain the primary fault verification matrix. The information verification function is as follows:

[0159]

[0160] Where i is the matrix element in the primary fault section matrix, x represents the upstream line, y represents the downstream line, and D x Indicates the first power distribution state value, D y Indicates the second power distribution state value, Indicates the total status value of the upstream. Indicates the total downstream status value, N x and N y denotes the total number of secondary distribution equipment in the upstream line x and the downstream line y, respectively, M x and M y represents the total number of all line sections in the upstream line x and the downstream line y, respectively, Q i，x Indicates the upstream segment status value of all line segments in the upstream line x, Q i，y represents the downstream segment state value of all the line segments in the downstream line y, and Π represents a logical operation or operation;

[0161] If the primary fault check matrix and the primary fault section matrix are equal matrices, it is determined that there is no information error in the target terminal information;

[0162] If the primary fault check matrix and the primary fault section matrix are not equal matrices, it is determined that there is information error in the target terminal information.

[0163] In this embodiment, a partial matrix corresponding to the primary fault section in the line fault matrix is ​​extracted, namely the primary fault section matrix. For example, section (3) is the primary fault section, and its corresponding primary fault section matrix is ​​as follows:

[0164] G=[1 1 1 -1 0 0 0] T

[0165] Use the fault section as the demarcation point to change the campus line topology Figure 1 Divide into two parts, the part of the topology connected to the main power distribution equipment is named the upstream section, and the part of the topology connected to the campus power equipment is named the downstream section. Figure 2 Assuming that the faulty section is section (3), the upstream sections include section (1), section (2), section (5), and section (6), and the downstream sections are section (4), section (5), and section (7).

[0166] The distribution status values ​​of all secondary power distribution equipment are obtained according to the campus fault information matrix. The distribution status value refers to whether the secondary power distribution equipment is connected to the main power distribution equipment. If it is disconnected from the main power distribution equipment, the secondary power distribution equipment cannot distribute power to other electrical devices. At this time, the distribution status value is 0. Otherwise, the distribution status value is 1. The first distribution status value refers to whether there is a secondary power distribution equipment disconnected from the main power distribution equipment in the upstream section. If so, the distribution status value is 0, and if not, it is 1. The second distribution status value refers to whether there is a secondary power distribution equipment disconnected from the main power distribution equipment in the downstream section. If so, the distribution status value is 0, and if not, it is 1. The section status value refers to the three logic signals of "1, 0, -1". 1 indicates that a forward fault overcurrent flows through the line node, and the corresponding section status value is also 1. 0 indicates that there is no fault overcurrent in the line node, and the corresponding section status value is also 0. -1 indicates that a reverse fault overcurrent flows through the line node, and the corresponding section status value is also -1. For example, if a forward fault overcurrent flows through line node 1, the section status value of section 1 is 1. For the convenience of distinction, the section status value of the upstream section is named the upstream section status value, and the section status value of the downstream section is named the downstream section status value. All upstream section status values ​​are integrated to obtain the upstream total status value, and all downstream section status values ​​are integrated to obtain the downstream total status value, that is, the upstream total status value contains all upstream section status values, and the downstream total status value contains all downstream section status values.

[0167] The primary fault section matrix, the power distribution status value, the upstream section status value, the downstream section status value, the upstream total status value and the downstream total status value are input into the information verification function. If the output result of the information verification function, i.e., the primary fault check matrix, is an equal matrix with the primary fault section matrix, then it is determined that there is no information error in the target terminal information. If the primary fault check matrix is ​​not an equal matrix with the primary fault section matrix, then it is determined that there is an information error in the target terminal information. An equal matrix means that the rows and columns between matrices are the same, and the corresponding elements are all equal. Assume that the fault information of the above section (3) is distorted and becomes the following distorted matrix:

[0168] g=[1 0 1 -1 0 1 0] T

[0169] The distortion fault judgment matrix is ​​constructed according to the distortion matrix. The distortion fault judgment matrix is ​​as follows:

[0170]

[0171] According to the preset fault location rules, the distortion fault judgment matrix is ​​analyzed, and the fault sections are obtained as section (1), section (3), and section (6). Sections (1), section (3), and section (6) are converted into primary fault section matrices and input into the primary fault check matrix. The primary fault check matrix is ​​obtained as follows:

[0172] T=[1 0 0 -1 0 0 0] T

[0173] Since the matrix g and the matrix T are not equal matrices, it means that the fault information of section (3) is distorted, which is consistent with the assumption.

[0174] In one embodiment, extracting a plurality of fault topology subgraphs from a campus line topology graph according to a first fault section comprises the following steps:

[0175] Marking the line nodes for faults according to the section positions of all first fault sections in the campus line topology map to obtain a plurality of first fault line nodes;

[0176] Performing node aggregation on the first fault line node to obtain a plurality of fault line node sets;

[0177] Several fault topology subgraphs are extracted from the campus line topology graph according to all fault line node sets.

[0178] In this embodiment, according to the first fault section located in the campus line topology map, the line nodes located in the first fault section are marked as faults to obtain multiple first fault line nodes, and the adjacent fault nodes are aggregated to obtain several fault line node sets. Common node aggregation methods include DBSCAN (density-based clustering algorithm), spectral clustering algorithm and topological clustering algorithm. Taking the topological clustering algorithm as an example, the node values ​​are updated by traversing the adjacency list, the mutual relationship between the nodes is determined, and clustering is performed based on these relationships. In topological clustering, nodes with close distances can be regarded as the same cluster or community, thereby realizing node aggregation and obtaining several fault line node sets. For each fault line node set, all line nodes and edges of the campus line topology map are traversed. If the line node belongs to the currently processed fault line node set, it is added to the fault topology subgraph. At the same time, if the two line nodes connected by the edge belong to the current fault line node set, the edge is also added to the fault topology subgraph, so that the fault topology subgraph of all fault line node sets can be obtained.

[0179] In one embodiment, a fault section location model is constructed based on a graph neural network model, and the fault section location model is used to locate the fault in all fault topology subgraphs to obtain several second fault sections in the campus line topology map, including the following steps:

[0180] A fault section location model is constructed based on the graph neural network model. The fault section location model includes a fault feature extraction module, a fault feature weighting module, a feature dimension transformation module and a fault classification learning module. The fault feature extraction module is constructed based on the spatiotemporal graph neural network model, the fault feature weighting module is constructed based on the graph attention network model, the feature dimension transformation module is constructed based on the one-dimensional convolutional neural network model, and the fault classification learning module is constructed based on the full convolutional neural network model.

[0181] The fault section location model is trained using a pre-constructed fault location training set, and the fault topology subgraphs are sequentially input into the fault section location model for fault location, thus obtaining several second fault sections in the campus power distribution line.

[0182] In this embodiment, the spatiotemporal graph neural network (ST-GNN) is a graph neural network model specifically used to process spatiotemporal data. It combines the two dimensions of space and time and can effectively capture the spatiotemporal dependency in the data. The structure of ST-GNN mainly includes a graph neural network (GNN) and a sequence model (such as RNN, LSTM, etc.). GNN updates the line node features through a message passing mechanism, aggregates the information of the neighbor nodes of the line node through a graph convolution operation, and learns the spatial dependency between the line nodes to obtain the fault space feature. Then, the time feature of the fault topology subgraph can be extracted through a recurrent neural network model (RNN) or a long short-term memory network model (LSTM). Taking RNN as an example, RNN uses a cyclic structure to enable the network to remember previous information and adapt to the time dependency of sequence data, so that the time feature of the fault topology subgraph can be extracted to obtain the fault time feature. The graph attention network model includes an input layer, an attention layer, an aggregation layer, and an output layer. The input layer is used for inputting the spatiotemporal features of faults. The attention layer learns the relationship between nodes by calculating the attention coefficients between nodes to obtain the attention coefficients. The aggregation layer uses the attention coefficients to weightedly aggregate the features of neighboring nodes to obtain fault fusion features. The output layer is used to output fault fusion features. The one-dimensional convolutional neural network model mainly includes convolutional layers and pooling layers. After the fault fusion features are input into the convolutional layer of the one-dimensional convolutional neural network for convolution operation, the output of the convolutional layer is downsampled using the pooling layer to reduce the dimension and redundant information of the data. After the fault fusion features are input into the one-dimensional convolutional neural network model, multiple feature maps are generated after multiple convolutional layers and pooling layers. The multiple feature maps are spliced ​​and input into the full convolutional neural network model for feature classification. The fully convolutional neural network (FCN) is a special convolutional neural network structure. All fully connected layers are replaced by convolutional layers. The convolutional layers in the fully convolutional neural network are used to perform convolution operations on the input high-dimensional fault features, that is, the fault fusion features that complete the feature mapping, to extract local features. By stacking multiple convolutional layers, higher-level feature representations are gradually extracted. Then, downsampling operations are performed through the pooling layer to further reduce the feature dimension while retaining key information. After the features are mapped to the low-dimensional space, the maximum activation value obtained after the Softmax function is the second fault segment.

[0183] The pre-built fault location training set contains the historical campus line topology map with the fault section marked in advance. The fault location training set is used to train the fault section location model. At the same time, a suitable loss function (such as cross entropy) is selected to evaluate the model performance, and optimizers such as Adam or SGD are selected for model training. The model parameters are updated through the back propagation algorithm, and the loss and accuracy during the training process are monitored. During the model training process, the model parameters of the fault section location model are continuously adjusted, such as the number of convolutional layers, the selection of activation functions, etc., until the preset maximum number of training times is reached and the model training is completed.

[0184] The fault topology subgraphs are sequentially input into the fault section location model for fault location, and several second fault sections in the campus power distribution line are obtained. Specifically, the fault feature extraction module is used to capture the spatial correlation between the line nodes in the fault topology subgraph and the front-to-back correlation between the fault topology subgraphs at different times. Then, the fault feature weighting module is used to assign weights to fault features of different dimensions according to the idea of ​​learning attention weights, and the fault features that have completed the weight assignment are feature fused. The feature dimension transformation module is used to extract and transform the fault features. The fault classification learning module is used to map the extracted high-dimensional fault features to the low-dimensional space containing the fault section information for classification learning. Finally, the maximum activation value (argmax) obtained after the Softmax function is the second fault section.

[0185] In one embodiment, the fault topology subgraphs are sequentially input into the fault section location model to locate the fault, and obtaining a plurality of second fault sections in the campus power distribution line includes the following steps:

[0186] The fault topology subgraphs are sequentially input into the fault feature extraction module of the fault section location model to perform convolution operations on the fault topology subgraphs in the time and space scales to obtain the fault time and space features of the fault topology subgraphs;

[0187] The fault spatiotemporal features are input into the fault feature weighting module to calculate the attention coefficient, and the fault spatiotemporal features are assigned weights according to the calculation results of the attention coefficient;

[0188] Perform weighted fusion on the fault spatiotemporal features that have completed weight allocation to obtain fault fusion features;

[0189] The fault fusion features are input into the feature dimension transformation module for feature mapping, and the fault fusion features after feature mapping are input into the fault classification learning module for classification learning to obtain several second fault sections in the campus line topology map.

[0190] In this embodiment, each fault topology subgraph is input into the fault feature extraction module, and a graph convolution method using Chebyshev polynomials as convolution kernels can be used to capture the spatial correlation features of the fault topology subgraph, i.e., fault space features. At the same time, a two-dimensional convolution operation is introduced on the time series axis to merge the information of adjacent time steps, so as to obtain sequence features that can reflect dynamic spatiotemporal characteristics, i.e., fault time features. The fault space features are integrated with the fault time features to obtain fault spatiotemporal features. The fault spatiotemporal features are input into the fault feature weighting module to assign weights. Specifically, the graph attention network model (GAT) performs a linear transformation on the fault spatiotemporal features of each line node, maps it to a higher dimension, obtains the feature vectors of all line nodes, and then concatenates the feature vectors of the line nodes and performs an inner product with a learnable vector, and then obtains the attention coefficient through an activation function (such as LeakyReLU). Finally, GAT performs a weighted summation of the features of the line nodes according to the calculated attention coefficient to obtain the fault fusion feature. The fault fusion features are input into the feature dimension transformation module for feature mapping. Specifically, the convolution kernel of the one-dimensional convolutional neural network (1D-CNN) slides upward along the sequence axis of the fault fusion features. Each translation will perform weighted summation on the elements in the corresponding sequence window. Then, the data after the convolution operation is nonlinearly mapped to extract features. Finally, the sub-features extracted by each convolution kernel are spliced ​​to obtain the fault fusion features that complete the feature mapping. Finally, the fault fusion features that complete the feature mapping are input into the fault classification learning module. The fault classification learning module is the last link of the fault section location model, which is used to map the extracted high-dimensional fault features to the low-dimensional space containing the fault section information and perform classification learning through the Softmax function, that is, feature classification is performed on the fault fusion features that complete the feature mapping to obtain the fault location result, which is the second fault section.

[0191] In one embodiment, using all the second fault sections to correct all the first fault sections to obtain several line fault sections of the campus power distribution line includes the following steps:

[0192] Mark the line nodes for faults according to the position of the second fault section in the campus line topology map to obtain the second fault line nodes;

[0193] Analyze whether the second fault line node coincides with the first fault line node according to the campus line topology map;

[0194] If the second fault line node coincides with the first fault line node, the second fault section corresponding to the coincident second fault line node is marked as a topological line fault section;

[0195] All topological line fault sections are matched with the campus line distribution map, and several line fault sections in the campus line distribution map are located according to the position matching results.

[0196] In this embodiment, according to the second fault section located in the campus line topology map, the line nodes located in the second fault section are marked as faults to obtain multiple second fault line nodes. According to the position information of the line nodes corresponding to the first fault line node and the second fault line node in the campus line topology map, it is determined whether there is a second fault line node and the first fault line node. If the two coincide, it means that the campus electrical device corresponding to the line node is likely to be faulty. Therefore, the second fault section corresponding to the coincident second fault line node is marked as a topological line fault section. The reason for marking the topological line fault section according to the second fault section is that the second fault section located based on the graph neural network model is more accurate than the first fault section located based on the matrix method. The positions of all the topological line fault sections finally obtained are matched with the campus line distribution map to obtain the actual fault positions of all the topological line fault sections in the target campus, that is, several line fault sections in the campus line distribution map. All the obtained line fault sections are marked in the campus line distribution map, and the marked campus line distribution map and the campus electrical device numbers corresponding to the line nodes contained in the topological line fault sections are uploaded to the power distribution system management platform. The staff of the subsequent power distribution system management platform can determine the fault area according to the marked campus line distribution map, and determine the faulty campus electrical device according to the uploaded campus electrical device numbers, which greatly saves manpower. At the same time, since the staff can quickly obtain the location of the faulty campus electrical device and repair it in time, it greatly saves electricity resources to a certain extent. This is because the faulty campus electrical device cannot continue to work even if a large amount of electricity is transmitted, resulting in a waste of electricity resources. In addition, if the faulty campus electrical device is an important equipment in the distribution system, such as a distribution box, then if it is not repaired in time, it is very likely to cause safety problems such as short circuit and overload. In severe cases, it may cause damage to electrical equipment or even cause serious consequences such as fire. It may also cause the entire power system to be unable to operate normally for a long time, affecting normal life and production activities.

[0197] In addition, if the second fault line node does not overlap with the first fault line node, the second fault line node and the first fault line node will be marked as suspected fault nodes. If, during the subsequent fault location process of the campus distribution line, the suspected fault node is again marked as the second fault line node or the first fault line node, it is determined that the campus electrical device corresponding to the suspected fault node is faulty, and its number is also uploaded to the distribution system management platform. The staff of the distribution system management platform will inspect and repair it according to the number.

[0198] The present application also discloses a distribution system operation and maintenance management system based on data fusion analysis technology, which is characterized by comprising:

[0199] a memory configured to store instructions; and

[0200] A processor is configured to call instructions from a memory and implement the method for distribution system operation and maintenance management based on data fusion analysis technology according to any of the above items when executing the instructions.

[0201] Among them, the processor can adopt a central processing unit (CPU). Of course, according to actual usage, other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. can also be adopted. The general-purpose processor can adopt a microprocessor or any conventional processor, etc., and this application does not impose any restrictions on this.

[0202] Among them, the memory can be an internal storage unit of a computer device, such as a hard disk or memory of a computer device, or an external storage device of a computer device, such as a plug-in hard disk, a smart memory card (SMC), a secure digital card (SD) or a flash memory card (FC) equipped on the computer device, etc., and the memory can also be a combination of an internal storage unit and an external storage device of a computer device. The memory is used to store computer programs and other programs and data required by the computer device. The memory can also be used to temporarily store data that has been output or is to be output, and this application does not impose any restrictions on this.

[0203] An embodiment of the present application also provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute the above-mentioned method for distribution system operation and maintenance management based on data fusion analysis technology.

[0204] 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 adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt 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.) that contain computer-usable program code.

[0205] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. 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 generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0206] 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 and / or boxes Figure 1 A function specified in one or more boxes.

[0207] 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 and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0208] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0209] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0210] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0211] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0212] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A distribution system operation and maintenance management method based on data fusion analysis technology, characterized in that: The method comprises the following steps: Obtaining a campus information distribution map and historical electricity usage information of a target campus, wherein the campus information distribution map includes a campus line distribution map; Extracting all campus electrical devices in the campus power distribution lines of the target campus from the campus line distribution map; Performing line topology analysis on the campus line distribution map to obtain device connection relationships between all campus electrical devices, taking all campus electrical devices as line nodes, and constructing a campus line topology map based on the device connection relationships, wherein the campus electrical devices include feeder terminal devices; Analyze the device key coefficients of all the campus electrical devices in combination with the historical power consumption information and the campus line topology map, and select a number of the campus electrical devices as key campus electrical devices from all the campus electrical devices according to the device key coefficients; If the device connection relationship exists between any of the feeder terminal devices and any of the key campus electrical devices, a redundant sensor pre-installed at the feeder terminal device is enabled, and the feeder terminal device with the redundant sensor enabled is used as a key feeder terminal device; Acquire key terminal information of all the key feeder terminal devices, and edge terminal information of all other devices among the feeder terminal devices except the key feeder terminal devices; Based on the campus line topology map, the key terminal information and the edge terminal information are integrated to construct a line fault judgment matrix, and based on the line fault judgment matrix, fault location is performed in the campus line topology map to obtain several first fault sections in the campus line topology map; Extracting a plurality of fault topology subgraphs from the campus line topology graph according to all the first fault sections; Building a fault section location model based on the graph neural network model, using the fault section location model to locate the fault in all the fault topology subgraphs, and obtaining several second fault sections in the campus line topology map; All of the first fault sections are corrected using all of the second fault sections to obtain several line fault sections of the campus power distribution line.

2. The method according to claim 1, characterized in that The historical electricity usage information includes historical electricity usage and historical electricity usage duration, the campus information distribution map also includes a campus building distribution map, the device key coefficients of all campus electrical devices are analyzed in combination with the historical electricity usage information and the campus line topology map, and a number of campus electrical devices are selected from all campus electrical devices as key campus electrical devices according to the device key coefficients, including the following steps: Divide the target campus into regions according to the campus building distribution map to obtain multiple campus electricity consumption areas; Combining the historical power consumption and the historical power consumption duration, dividing the regional power consumption levels for all the campus power consumption areas; Position matching is performed between the campus line distribution map and the campus building distribution map to obtain device area locations of all campus electrical devices; For any campus electrical device, an initial device critical coefficient is allocated to the campus electrical device according to the regional power consumption level corresponding to the device regional location; Calculating the node centrality of the campus electrical devices according to the device connection relationship; Correcting the initial device critical coefficient to a device critical coefficient using the node centrality; A number of campus electrical components whose component critical coefficients are greater than or equal to a preset coefficient threshold are marked as critical campus electrical components.

3. The method according to claim 1, characterized in that The method of building a line fault judgment matrix based on the campus line topology map by integrating the key terminal information and the edge terminal information, and locating the fault in the campus line topology map based on the line fault judgment matrix to obtain the first fault section of the campus line topology map includes the following steps: For any of the key feeder terminal devices, calculating the information difference between the key terminal information collected by the redundant sensor in the key feeder terminal device and the key terminal information collected by other sensors in the key feeder terminal device except the redundant sensor, to obtain a plurality of key terminal information differences; If the absolute value of any difference of the key terminal information is greater than or equal to a preset difference threshold, it is determined that abnormal terminal information exists in the key terminal information; If the absolute values ​​of all the key terminal information differences are less than the difference threshold, it is determined that there is no abnormal terminal information in the key terminal information; If there is abnormal terminal information in the key terminal information, selecting the key terminal information collected by the redundant sensor as the target terminal information; Performing data fusion on the target terminal information and the edge terminal information to obtain target feeder terminal information; Building a line fault judgment matrix in combination with the campus line topology map and all the target feeder terminal information, and locating several primary fault sections in the campus line topology map based on the line fault judgment matrix; For any of the primary fault sections, performing information verification on the target terminal information based on the primary fault section and using an information verification function; If the information verification result shows that there is no information error in the target terminal information, it is determined that the primary fault section is the first fault section of the campus line topology map; If the information verification result shows that the target terminal information has information errors, the target terminal information is updated according to all other information in the key terminal information except the target terminal information to obtain the reference terminal information; The reference terminal information and the edge terminal information are combined to perform fault location in the campus line topology map to obtain the first fault section of the campus line topology map.

4. The method according to claim 3, characterized in that The step of building a line fault judgment matrix by combining the campus line topology map and all the target feeder terminal information, and locating a number of primary fault sections in the campus line topology map based on the line fault judgment matrix comprises the following steps: Acquire electrical parameters of all campus electrical devices according to the target feeder terminal information, and analyze the power direction of all campus electrical devices in combination with the electrical parameters and the topological structure type of the campus line topology diagram; Based on the campus line topology diagram, a campus line description matrix of the campus power distribution line is constructed in combination with the line power direction and the device connection relationship; According to the electrical parameters and using a threshold method, device fault information in the target feeder terminal information is obtained, and a campus fault information matrix of the campus power distribution line is constructed by combining the target feeder terminal information and the campus line topology map; Combining the campus line description matrix and the campus fault information matrix to construct a line fault judgment matrix; According to the line fault judgment matrix and using preset fault location rules, fault location is performed in the campus line topology map to obtain several primary fault sections in the campus line topology map.

5. The method according to claim 3, characterized in that: The campus electrical equipment also includes a main power distribution device, a secondary power distribution device, and campus power equipment. The information verification of the target terminal information based on the primary fault section and using an information verification function includes the following steps: converting the primary fault section into a primary fault section matrix according to the line fault judgment matrix; Taking the primary fault section as the center point, the campus line topology map is divided into an upstream section and a downstream section, wherein the upstream section is connected to the main power distribution equipment, and the downstream section is connected to the campus power equipment; Taking the campus line topology as a reference, obtaining the power distribution status values ​​of all the secondary power distribution equipment according to the campus fault information matrix, wherein the status power distribution values ​​include the first power distribution status value of the upstream section and the second power distribution status value of the downstream section; Analyze the status values ​​of all line sections in the campus line topology map according to all the primary fault sections to obtain a plurality of section status values, wherein the section status values ​​include an upstream section status value and a downstream section status value; Integrate all the upstream segment status values ​​and all the downstream segment status values ​​to obtain an upstream total status value and a downstream total status value respectively; The primary fault section matrix, the power distribution status value, the upstream section status value, the downstream section status value, the upstream total status value and the downstream total status value are input into the information verification function to obtain the primary fault verification matrix. The information verification function is as follows: Where i is a matrix element in the primary fault section matrix, x represents the upstream line, y represents the downstream line, D x represents the first power distribution state value, D y represents the second power distribution state value, Indicates the upstream total status value, Represents the total downstream status value, N x and N y represents the total number of the secondary power distribution devices in the upstream line x and the downstream line y, respectively, x and M y represents the total number of all the line segments in the upstream line x and the downstream line y, respectively, Q i，x represents the upstream segment status value of all the route segments in the upstream route x, Q i，y represents the downstream segment state value of all the line segments in the downstream line y, and Π represents a logical operation or operation; If the primary fault check matrix and the primary fault section matrix are equal matrices, it is determined that there is no information error in the target terminal information; If the primary fault check matrix and the primary fault section matrix are not equal matrices, it is determined that there is an information error in the target terminal information.

6. The method according to claim 1, characterized in that The extracting of a plurality of fault topology subgraphs from the campus line topology graph according to the first fault section comprises the following steps: Marking the line nodes for faults according to the section positions of all the first fault sections in the campus line topology map to obtain a plurality of first fault line nodes; Performing node aggregation on the first fault line node to obtain a plurality of fault line node sets; A plurality of fault topology subgraphs are extracted from the campus line topology graph according to all the fault line node sets.

7. The method according to claim 6, characterized in that The method of constructing a fault section location model based on a graph neural network model, using the fault section location model to locate the fault in all the fault topology subgraphs, and obtaining a plurality of second fault sections in the campus line topology graph comprises the following steps: A fault section location model is constructed based on a graph neural network model, wherein the fault section location model includes a fault feature extraction module, a fault feature weighting module, a feature dimension transformation module and a fault classification learning module. The fault feature extraction module is constructed based on a spatiotemporal graph neural network model, the fault feature weighting module is constructed based on a graph attention network model, the feature dimension transformation module is constructed based on a one-dimensional convolutional neural network model, and the fault classification learning module is constructed based on a full convolutional neural network model. The fault section location model is trained using a pre-constructed fault location training set, and the fault topology subgraphs are sequentially input into the fault section location model for fault location, thereby obtaining a plurality of second fault sections in the campus power distribution line.

8. The method according to claim 7, characterized in that The step of sequentially inputting the fault topology subgraphs into the fault section location model to locate the fault and obtaining a plurality of second fault sections in the campus power distribution line comprises the following steps: The fault topology subgraph is sequentially input into the fault feature extraction module of the fault section location model to perform convolution operation on the fault topology subgraph in the time and space scale to obtain the fault time and space features of the fault topology subgraph; Inputting the fault spatiotemporal features into the fault feature weighting module to calculate the attention coefficient, and assigning weights to the fault spatiotemporal features according to the attention coefficient calculation result; Performing weighted fusion on the fault spatiotemporal features after weight allocation to obtain fault fusion features; The fault fusion features are input into the feature dimension transformation module for feature mapping, and the fault fusion features after feature mapping are input into the fault classification learning module for classification learning to obtain several second fault sections in the campus line topology map.

9. The method according to claim 8, characterized in that The method of using all the second fault sections to correct all the first fault sections to obtain several line fault sections of the campus power distribution line comprises the following steps: Marking the line node for fault according to the position of the second fault section in the campus line topology map to obtain a second fault line node; Analyze whether the second fault line node coincides with the first fault line node according to the campus line topology map; If the second fault line node coincides with the first fault line node, marking the second fault section corresponding to the coincident second fault line node as a topological line fault section; All the topological line fault sections are position-matched with the campus line distribution map, and several line fault sections in the campus line distribution map are located according to the position matching structure.

10. A distribution system operation and maintenance management system based on data fusion analysis technology, characterized in that: include: a memory configured to store instructions; as well as A processor is configured to call the instruction from the memory and to implement the method for distribution system operation and maintenance management based on data fusion analysis technology according to any one of claims 1 to 9 when executing the instruction.

Images