Power distribution network line fault identification method and device, equipment and medium

Abstract

The present disclosure relates to the technical field of power distribution, and particularly relates to a power distribution network line fault identification method and device, equipment and medium, the method comprising: acquiring node feature data, distributed energy state feature data and connection line feature data; acquiring an adjacency matrix; generating a node feature matrix, a distributed energy state feature matrix and a connection line feature matrix corresponding to the power distribution network; acquiring a pre-trained line fault identification model; inputting the node feature matrix, the distributed energy state feature matrix and the connection line feature matrix as inputs into the line fault identification model to obtain a line fault identification result output by the line fault identification model; and determining whether a fault occurs in the corresponding connection line according to the line fault identification result. The scheme improves the accuracy and efficiency of power distribution network fault identification, enables operation and maintenance personnel to identify faults in the power distribution network in a timely and accurate manner, and helps to improve the stability and reliability of the power distribution network.

Description

Technical Field

[0001] The present disclosure relates to the field of power supply and distribution technology, and in particular to a method, device, equipment and medium for identifying line faults in a distribution network. Background Art

[0002] As a crucial hub for power supply and distribution, the operating conditions of the distribution network directly impact power quality and user experience. When a distribution network fault occurs, the system must quickly and accurately identify the fault so that power can be restored to non-faulty areas with minimal loss.

[0003] However, with the continuous improvement of smart grids and the large-scale access of distributed power sources to distribution networks, the load changes have increased and the flow direction has become more complicated. In related technologies, the impact of distributed power source access on the distribution network is often not taken into account when identifying distribution network faults, thereby reducing the accuracy and efficiency of distribution network fault identification, making it impossible for operation and maintenance personnel to identify faults in the distribution network in a timely and accurate manner, thereby increasing the difficulty of power supply restoration in the distribution network. Summary of the Invention

[0004] In order to solve the problems in the related art, the embodiments of the present disclosure provide a method, apparatus, device and medium for identifying line faults in a distribution network.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for identifying a distribution network line fault, comprising:

[0006] Obtain node characteristic data of each node in the distribution network, distributed energy state characteristic data of each node, and connection line characteristic data of the connection lines in the distribution network;

[0007] Obtaining an adjacency matrix indicating topological relationships of nodes in the distribution network;

[0008] According to the adjacency matrix, the node feature data, the distributed energy state feature data and the connection line feature data are aggregated respectively to generate the node feature matrix, the distributed energy state feature matrix and the connection line feature matrix corresponding to the distribution network;

[0009] Obtain a pre-trained line fault identification model;

[0010] The node feature matrix, the distributed energy state feature matrix, and the connection line feature matrix are input into the line fault identification model to obtain a line fault identification result output by the line fault identification model. The line fault identification result is used to indicate the probability of a fault occurring in the corresponding connection line in the distribution network.

[0011] Determine whether a fault occurs in the corresponding connection line based on the line fault identification result.

[0012] In one embodiment of the present disclosure, the node characteristic data includes at least one of voltage amplitude, voltage phase angle, active power, reactive power, node load, generated power, and node fault status.

[0013] In one embodiment of the present disclosure, the distributed energy status characteristic data includes at least one of the distributed energy node type, the distributed energy node availability status, the distributed energy node grid access status, the distributed energy node charge and discharge status, and the distributed energy node energy storage device charge and discharge status.

[0014] In one embodiment of the present disclosure, the connection line characteristic data includes at least one of line impedance, line current intensity, active power, reactive power, conduction state, line type, line capacity, line distance, and connection state.

[0015] In one embodiment of the present disclosure, the method further comprises:

[0016] Obtain the line fault type code of the corresponding connection line uploaded by the distributed device and the line fault status code of the corresponding connection line uploaded by the node fault detection device. If a ground fault occurs on the corresponding connection line, the line fault type code is 01; if a forward current short circuit fault occurs on the corresponding connection line, the line fault type code is 10 and the line fault status code is 1; if a reverse current short circuit fault occurs on the corresponding connection line, the line fault type code is 11 and the line fault status code is -1; if no fault occurs on the corresponding connection line, the line fault status code is 0;

[0017] Obtaining the next moment line fault type code of the corresponding connected line based on the line characteristic data;

[0018] Get the switch function of the corresponding connection line;

[0019] Verify the fitting function based on the next moment line fault type code, line fault type code, fault state code and switching function of the corresponding connected line;

[0020] Determine whether a fault occurs on the corresponding connection line based on the line fault identification result, including:

[0021] If the fitting function verification result meets the preset fitting function verification requirements, consistency fitting is performed based on the line fault identification result and the line fault type code;

[0022] Determine whether a fault occurs in the corresponding connection line based on the consistency fitting result and the line fault identification result.

[0023] In one embodiment of the present disclosure, obtaining a switching function corresponding to a connection line includes:

[0024] pass Obtain the switch function K of the corresponding connection line;

[0025] Among them, x ij is the line fault type code of the connection line between the i-th node and the j-th node at the next moment, C1 is the number of connection lines downstream of the corresponding connection line, C2 is the number of connection lines upstream of the corresponding connection line, M is the number of distributed energy type nodes in the distribution network, if the t-th distributed energy type node in the distribution network is connected to the grid, then If the tth distributed energy type node in the distribution network is not connected to the grid,

[0026] In one embodiment of the present disclosure, performing fitting function verification based on the next moment line fault type code, line fault type code, fault state code, and switching function of the corresponding connected line includes:

[0027] pass Calculating a first mathematical expectation value E1, where C(X) is used to indicate a set of line fault type codes of the connection line at the next moment, and F' is used to indicate a line fault state code of the corresponding connection line;

[0028] pass Calculating a second mathematical expectation value E2, where F is used to indicate a line fault type code corresponding to the connection line, and C(K) is used to indicate a set of switching functions of the connection line;

[0029] If the fitting function verification result meets the preset fitting function verification requirements, consistency fitting is performed based on the line fault identification result and the line fault type code, including:

[0030] If E1≥σ and E2≥β, consistency fitting is performed based on the line fault identification result and the line fault type code, where σ is a preset first mathematical expectation threshold and β is a preset second mathematical expectation threshold.

[0031] In one embodiment of the present disclosure, performing consistency fitting based on the line fault identification result and the line fault type code includes:

[0032] based on Calculate the risk estimate R ξ，λ ;

[0033] Among them C ξ (X l ) is the line fault type code of the lth connecting line in the distribution network at the next moment, C λ (K l ) is the switching function of the lth connecting line in the distribution network, and n is the number of connecting lines in the distribution network;

[0034] based on Calculate the fault probability threshold ξ*, where μ is the upper limit of the consistency probability obtained in advance;

[0035] Determine whether a fault occurs in the corresponding connection line based on the consistency fitting results and line fault identification results, including:

[0036] If the probability of a fault occurring in the corresponding connection line indicated by the line fault identification result is greater than or equal to the fault probability threshold ξ*, it is determined that a fault occurs in the corresponding connection line.

[0037] In a second aspect, an embodiment of the present disclosure provides a distribution network line fault identification device, comprising:

[0038] A distribution network data acquisition module is configured to acquire node characteristic data of each node in the distribution network, distributed energy state characteristic data of each node, and connection line characteristic data of connection lines in the distribution network;

[0039] An adjacency matrix acquisition module is configured to acquire an adjacency matrix for indicating a topological relationship of nodes in the distribution network;

[0040] a data aggregation module configured to aggregate the node feature data, the distributed energy state feature data, and the connection line feature data according to the adjacency matrix to generate a node feature matrix, a distributed energy state feature matrix, and a connection line feature matrix corresponding to the distribution network;

[0041] A model acquisition module is configured to acquire a pre-trained line fault identification model;

[0042] an identification result acquisition module configured to input the node feature matrix, the distributed energy state feature matrix, and the connection line feature matrix into a line fault identification model to obtain a line fault identification result output by the line fault identification model, wherein the line fault identification result is used to indicate the probability of a corresponding connection line in the distribution network having a fault;

[0043] The fault identification module is configured to determine whether a fault occurs in the corresponding connection line according to the line fault identification result.

[0044] In one embodiment of the present disclosure, the node characteristic data includes at least one of voltage amplitude, voltage phase angle, active power, reactive power, node load, generated power, and node fault status.

[0045] In one embodiment of the present disclosure, the distributed energy status characteristic data includes at least one of the distributed energy node type, the distributed energy node availability status, the distributed energy node grid access status, the distributed energy node charge and discharge status, and the distributed energy node energy storage device charge and discharge status.

[0046] In one embodiment of the present disclosure, the connection line characteristic data includes at least one of line impedance, line current intensity, active power, reactive power, conduction state, line type, line capacity, line distance, and connection state.

[0047] In one embodiment of the present disclosure, the apparatus further comprises:

[0048] a code acquisition module configured to acquire a line fault type code of the corresponding connection line uploaded by the distributed device and a line fault status code of the corresponding connection line uploaded by the node fault detection device, wherein if a ground fault occurs in the corresponding connection line, the line fault type code is 01; if a forward current short circuit fault occurs in the corresponding connection line, the line fault type code is 10 and the line fault status code is 1; if a reverse current short circuit fault occurs in the corresponding connection line, the line fault type code is 11 and the line fault status code is -1; if no fault occurs in the corresponding connection line, the line fault status code is 0;

[0049] A fault prediction module is configured to obtain a line fault type code of a corresponding connected line at a next moment based on the line characteristic data;

[0050] A switch function acquisition module is configured to acquire a switch function corresponding to a connection line;

[0051] A fitting function verification module is configured to verify the fitting function based on the next moment line fault type code, line fault type code, fault state code and switching function of the corresponding connected line;

[0052] The fault identification module is specifically configured as follows:

[0053] If the fitting function verification result meets the preset fitting function verification requirements, consistency fitting is performed based on the line fault identification result and the line fault type code;

[0054] Determine whether a fault occurs in the corresponding connection line based on the consistency fitting result and the line fault identification result.

[0055] In one embodiment of the present disclosure, the switch function acquisition module is specifically configured to:

[0056] pass Obtain the switch function K of the corresponding connection line;

[0057] Among them, x ijis the line fault type code of the connection line between the i-th node and the j-th node at the next moment, C1 is the number of connection lines downstream of the corresponding connection line, C2 is the number of connection lines upstream of the corresponding connection line, M is the number of distributed energy type nodes in the distribution network, if the t-th distributed energy type node in the distribution network is connected to the grid, then If the tth distributed energy type node in the distribution network is not connected to the grid,

[0058] In one embodiment of the present disclosure, the fitting function verification module is specifically configured to:

[0059] pass Calculating a first mathematical expectation value E1, where C(X) is used to indicate a set of line fault type codes of the connection line at the next moment, and F' is used to indicate a line fault state code of the corresponding connection line;

[0060] pass Calculating a second mathematical expectation value E2, where F is used to indicate a line fault type code corresponding to the connection line, and C(K) is used to indicate a set of switching functions of the connection line;

[0061] The fault identification module is specifically configured as follows:

[0062] If E1≥σ and E2≥β, consistency fitting is performed based on the line fault identification result and the line fault type code, where σ is a preset first mathematical expectation threshold and β is a preset second mathematical expectation threshold.

[0063] In one embodiment of the present disclosure, the fault identification module is specifically configured to:

[0064] based on Calculate the risk estimate R ξ，λ ;

[0065] Among them C ξ (X l ) is the line fault type code of the lth connecting line in the distribution network at the next moment, C λ (K l ) is the switching function of the lth connecting line in the distribution network, and n is the number of connecting lines in the distribution network;

[0066] based on Calculate the fault probability threshold ξ*, where μ is the upper limit of the consistency probability obtained in advance;

[0067] If the probability of a fault occurring in the corresponding connection line indicated by the line fault identification result is greater than or equal to the fault probability threshold ξ*, it is determined that a fault occurs in the corresponding connection line.

[0068] In a third aspect, an embodiment of the present disclosure provides an electronic device comprising a memory and a processor, wherein the memory is used to store one or more computer instructions, and wherein the one or more computer instructions are executed by the processor to implement a method as described in any one of the first aspects.

[0069] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the method as described in any one of the first aspects.

[0070] According to the technical solution provided by the embodiments of the present disclosure, node feature data of each node in the distribution network, distributed energy state feature data of each node, and connection line feature data of the connection lines in the distribution network are obtained; an adjacency matrix for indicating the topological relationship of the nodes in the distribution network is obtained; the node feature data, distributed energy state feature data, and connection line feature data are respectively aggregated according to the adjacency matrix to generate a node feature matrix, a distributed energy state feature matrix, and a connection line feature matrix corresponding to the distribution network; a pre-trained line fault identification model is obtained; the node feature matrix, the distributed energy state feature matrix, and the connection line feature matrix are used as input and input into the line fault identification model to obtain a line fault identification result output by the line fault identification model, the line fault identification result being used to indicate the probability of a fault occurring in the corresponding connection line in the distribution network; and whether a fault occurs in the corresponding connection line is determined according to the line fault identification result. In this scheme, not only the characteristics of each node in the distribution network and the topological relationship of the nodes in the distribution network are taken into account, but also the impact of the access of distributed energy type nodes on the fault line of the distribution network is taken into account. Therefore, when determining whether the corresponding connection line has a fault based on the obtained line fault identification result, the determination result is more accurate, which improves the accuracy and efficiency of distribution network fault identification, allowing operation and maintenance personnel to identify faults in the distribution network in a timely and accurate manner, thereby accelerating the speed of power supply recovery of the distribution network and helping to improve the stability and reliability of the distribution network.

[0071] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Other features, objectives and advantages of the present disclosure will become more apparent through the following detailed description of non-limiting embodiments in conjunction with the accompanying drawings. In the accompanying drawings:

[0073] Figure 1 A flow chart of a method for identifying line faults in a power distribution network according to an embodiment of the present disclosure is shown.

[0074] Figure 2A structural block diagram of a distribution network line fault identification device according to an embodiment of the present disclosure is shown.

[0075] Figure 3 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0076] Figure 4 A schematic diagram showing the structure of a computer system suitable for implementing the method according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0077] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. In addition, for the sake of clarity, parts not related to the description of the exemplary embodiments are omitted in the accompanying drawings.

[0078] In the present disclosure, it should be understood that terms such as "include" or "have" are intended to indicate the presence of features, numbers, steps, actions, components, parts, or combinations thereof disclosed in the present specification, and are not intended to exclude the possibility that one or more other features, numbers, steps, actions, components, parts, or combinations thereof exist or are added.

[0079] It should also be noted that, in the absence of conflict, the embodiments and features of the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0080] In this disclosure, if it involves operations of obtaining user information or user data or displaying user information or user data to others, such operations are all authorized and confirmed by the user, or actively selected by the user.

[0081] In recent years, with the continuous improvement of smart grids and the large-scale access of distributed power sources to distribution networks, the load changes in distribution networks have increased and the flow direction has become more complicated. In related technologies, when identifying distribution network faults, the impact of distributed power source access on the distribution network is often not taken into account, thereby reducing the accuracy and efficiency of distribution network fault identification, making it impossible for operation and maintenance personnel to identify faults in the distribution network in a timely and accurate manner, thereby increasing the difficulty of power supply restoration in the distribution network.

[0082] In order to solve the above problems, embodiments of the present disclosure provide a method, apparatus, device and medium for identifying line faults in a distribution network.

[0083] According to the technical solution provided by the embodiments of the present disclosure, node feature data of each node in the distribution network, distributed energy state feature data of each node, and connection line feature data of the connection lines in the distribution network are obtained; an adjacency matrix for indicating the topological relationship of the nodes in the distribution network is obtained; the node feature data, distributed energy state feature data, and connection line feature data are respectively aggregated according to the adjacency matrix to generate a node feature matrix, a distributed energy state feature matrix, and a connection line feature matrix corresponding to the distribution network; a pre-trained line fault identification model is obtained; the node feature matrix, the distributed energy state feature matrix, and the connection line feature matrix are used as input and input into the line fault identification model to obtain a line fault identification result output by the line fault identification model, the line fault identification result being used to indicate the probability of a fault occurring in the corresponding connection line in the distribution network; and whether a fault occurs in the corresponding connection line is determined according to the line fault identification result. In this scheme, not only the characteristics of each node in the distribution network and the topological relationship of the nodes in the distribution network are taken into account, but also the impact of the access of distributed energy type nodes on the fault line of the distribution network is taken into account. Therefore, when determining whether the corresponding connection line has a fault based on the obtained line fault identification result, the determination result is more accurate, which improves the accuracy and efficiency of distribution network fault identification, allowing operation and maintenance personnel to identify faults in the distribution network in a timely and accurate manner, thereby accelerating the speed of power supply recovery of the distribution network and helping to improve the stability and reliability of the distribution network.

[0084] Figure 1 FIG. 1 is a flow chart showing a method for identifying a distribution network line fault according to an embodiment of the present disclosure. Figure 1 As shown, the distribution network line fault identification method includes the following steps S101-S106:

[0085] In step S101, node characteristic data of each node in the distribution network, distributed energy state characteristic data of each node, and connection line characteristic data of connection lines in the distribution network are obtained;

[0086] In step S102, an adjacency matrix indicating the topological relationship of nodes in the power distribution network is obtained;

[0087] In step S103, the node feature data, the distributed energy state feature data, and the connection line feature data are aggregated according to the adjacency matrix to generate a node feature matrix, a distributed energy state feature matrix, and a connection line feature matrix corresponding to the distribution network;

[0088] In step S104, a pre-trained line fault identification model is obtained;

[0089] In step S105, the node feature matrix, the distributed energy state feature matrix, and the connection line feature matrix are input into a line fault identification model to obtain a line fault identification result output by the line fault identification model;

[0090] The line fault identification result is used to indicate the probability of a fault occurring in the corresponding connected line in the distribution network;

[0091] In step S106, it is determined whether a fault occurs in the corresponding connection line according to the line fault identification result.

[0092] In one implementation of the present disclosure, the line fault identification model can be trained in the following manner:

[0093] Step 1: Obtain historical node feature data of each node in the distribution network, historical distributed energy state feature data of each node, and historical connection line feature data of the connection line, and aggregate the historical node feature data, historical distributed energy state feature data, and historical connection line feature data according to the adjacency matrix to generate the historical node feature matrix, historical distributed energy state feature matrix, and historical connection line feature matrix corresponding to the distribution network;

[0094] Each vector in the historical node feature matrix includes data of multiple dimensions. For example, each vector in the historical node feature matrix may include data of multiple dimensions such as voltage amplitude, voltage phase angle, active power, reactive power, node load, generated power, and node fault status.

[0095] Each vector in the historical distributed energy state feature matrix includes data of multiple dimensions. For example, each vector in the historical distributed energy state feature matrix includes data of multiple dimensions such as distributed energy node type, distributed energy node availability status, distributed energy node grid access status, distributed energy node charge and discharge status, distributed energy node energy storage device charge and discharge status, etc.;

[0096] Each vector in the historical connection line feature matrix includes data of multiple dimensions. For example, each vector in the historical connection line feature matrix includes data of multiple dimensions such as line impedance, line current intensity, active power, reactive power, conduction state, line type, line capacity, line distance, and connection state.

[0097] Step 2: Perform average pooling (Avgpool) operations on the data of each dimension in the historical node feature matrix, the historical distributed energy state feature matrix, and the historical connection line feature matrix;

[0098] Step 3: Perform a MAXpooling operation on the data of each dimension in the historical node feature matrix, the historical distributed energy state feature matrix, and the historical connection line feature matrix;

[0099] Step 4: Concatenate and perform two-dimensional convolution on the matrices obtained in steps 2 and 3 respectively;

[0100] Step 5: Use the Sigmoid activation function to process the feature matrix generated in step 4. Specifically, any real value in the matrix is ​​mapped to a value between 0 and 1, and the weight values ​​of different feature matrices for different nodes are output.

[0101] Step 6: Weight the historical node feature matrix, the historical distributed energy state feature matrix, and the historical connection line feature matrix using the weight values ​​output in step 5;

[0102] Step 7: Perform horizontal average pooling on the weighted matrix obtained in step 6, that is, perform average pooling on each dimension in the width direction, retaining the average features of all horizontal directions of each dimension;

[0103] Step 8: Perform vertical average pooling on the matrix generated in step 6, that is, perform average pooling on each dimension in the height direction, retaining the average features of all vertical directions of each dimension;

[0104] Step 9: Perform depth average pooling on the matrices generated in steps 7 and 8, that is, perform average pooling on each dimension in the depth direction, retain the average features of all depth directions of each dimension, and output a one-dimensional matrix;

[0105] Step 10: Concatenate and perform two-dimensional convolution on the matrices generated in steps 7, 8, and 9;

[0106] Step 11: Batch normalize the data generated in step 10, that is, standardize and reparameterize the data. Standardization can be understood as first calculating the mean and variance of the input data of each training batch, and then performing a standardized transformation on the data to make it have zero mean and unit variance; reparameterization can be understood as scaling and translating the standardized data through two learnable parameters (scaling parameter and translation parameter) to restore the expressive power of the model.

[0107] Step 12: Obtain a pre-set threshold, discard the features whose weight values ​​generated in step 11 are less than the threshold, and retain and weight the features whose weight values ​​are higher than the threshold;

[0108] Step 13: Splice the features generated in step 12;

[0109] Step 14: Perform two-dimensional convolution on the features generated in step 13;

[0110] Step 15: Perform batch normalization on the features generated in step 14, that is, standardize and reparameterize the features:

[0111] Step 16: retain the values ​​greater than 0 in the data normalized in step 15 and output the size of the value;

[0112] Step 17: Enter the expansion layer processing, use the convolution block to perform three-dimensional convolution on the data output in step 16, and expand the feature matrix from one dimension to three dimensions;

[0113] Step 18: Multiply the elements in each dimension generated in Steps 16 and 17 one by one to generate a feature matrix. At this point, the spatial expansion of the feature matrix is ​​completed.

[0114] In step 19, the feature matrix outputted in step 18 is subjected to two sets of consecutive two-dimensional convolution, batch normalization, and linear rectification operations, and finally outputted through the sigmoid function to obtain the probability of failure of the corresponding connection line in the distribution network in history.

[0115] In this training scheme, fault line features in the distribution network are extracted. Spatial coordinated attention is used to accurately locate and retain key features. Amplified search and core feature identification are performed on retained features to enrich the perceptual field of view. Residual connections are used to enhance information transfer while preventing gradient vanishing. This improves the accuracy of key information extraction and fault location.

[0116] In one embodiment of the present disclosure, the node characteristic data includes at least one of voltage amplitude, voltage phase angle, active power, reactive power, node load, generated power, and node fault status.

[0117] Among them, the voltage amplitude is the voltage range value of the node; the voltage phase angle is the voltage phase angle of the node; the active power is the AC power actually generated or consumed by the node per unit time; the reactive power is the electric power required by the electrical equipment in the node to establish an alternating magnetic field and induced magnetic flux; the node load is the load situation of the node, including the number and type of power consumption or power generation equipment connected to the distribution network through the node; the generated power is the power of the node uploading electricity to the distribution network, and the generated power is less than the active power; the node fault status is whether the node has a fault and the specific fault type (such as fault voltage, current, etc.).

[0118] In one embodiment of the present disclosure, the distributed energy status characteristic data includes at least one of the distributed energy node type, the distributed energy node availability status, the distributed energy node grid access status, the distributed energy node charge and discharge status, and the distributed energy node energy storage device charge and discharge status.

[0119] Among them, the distributed energy node type is used to indicate whether the node is a distributed energy type node (that is, a node with the function of uploading electricity to the distribution network); the distributed energy node availability status is used to indicate whether the distributed energy type node is available; the distributed energy node grid access status is used to indicate whether the distributed energy type node is involved in the distribution network; the distributed energy node charge and discharge status is used to indicate whether the distributed energy type node is in a charging state, a discharging state or an idle state; the distributed energy node energy storage device charge and discharge status is used to indicate that the energy storage device in the distributed energy type node is in a charging state, a discharging state or an idle state.

[0120] In one embodiment of the present disclosure, the connection line characteristic data includes at least one of line impedance, line current intensity, active power, reactive power, conduction state, line type, line capacity, line distance, and connection state.

[0121] Among them, Line Impedance is the line impedance of the connecting line, including resistance and reactance; Line Current is the current value passing through the connecting line; Active Power is the active power passing through the connecting line, and Reactive Power is the reactive power passing through the connecting line; Conductivity is whether the connecting line is conductive; Line Type is whether the connecting line is connected to a main line or a branch line; Line Capacity is the maximum tolerable power or current of the connecting line; Line Distance is the physical distance or topological distance of the line distance; Connection Status is whether the line distance is set to conductive or disconnected.

[0122] According to the technical solution provided by the embodiments of the present disclosure, node feature data of each node in the distribution network, distributed energy state feature data of each node, and connection line feature data of the connection lines in the distribution network are obtained; an adjacency matrix for indicating the topological relationship of the nodes in the distribution network is obtained; the node feature data, distributed energy state feature data, and connection line feature data are respectively aggregated according to the adjacency matrix to generate a node feature matrix, a distributed energy state feature matrix, and a connection line feature matrix corresponding to the distribution network; a pre-trained line fault identification model is obtained; the node feature matrix, the distributed energy state feature matrix, and the connection line feature matrix are used as input and input into the line fault identification model to obtain a line fault identification result output by the line fault identification model, the line fault identification result being used to indicate the probability of a fault occurring in the corresponding connection line in the distribution network; and whether a fault occurs in the corresponding connection line is determined according to the line fault identification result. In this scheme, not only the characteristics of each node in the distribution network and the topological relationship of the nodes in the distribution network are taken into account, but also the impact of the access of distributed energy type nodes on the fault line of the distribution network is taken into account. Therefore, when determining whether the corresponding connection line has a fault based on the obtained line fault identification result, the determination result is more accurate, which improves the accuracy and efficiency of distribution network fault identification, allowing operation and maintenance personnel to identify faults in the distribution network in a timely and accurate manner, thereby accelerating the speed of power supply recovery of the distribution network and helping to improve the stability and reliability of the distribution network.

[0123] In one embodiment of the present disclosure, the method further comprises:

[0124] Obtain the line fault type code of the corresponding connection line uploaded by the distributed device and the line fault status code of the corresponding connection line uploaded by the node fault detection device. If a ground fault occurs on the corresponding connection line, the line fault type code is 01; if a forward current short circuit fault occurs on the corresponding connection line, the line fault type code is 10 and the line fault status code is 1; if a reverse current short circuit fault occurs on the corresponding connection line, the line fault type code is 11 and the line fault status code is -1; if no fault occurs on the corresponding connection line, the line fault status code is 0;

[0125] Obtaining the next moment line fault type code of the corresponding connected line based on the line characteristic data;

[0126] Get the switch function of the corresponding connection line;

[0127] Verify the fitting function based on the next moment line fault type code, line fault type code, fault state code and switching function of the corresponding connected line;

[0128] Determine whether a fault occurs on the corresponding connection line based on the line fault identification result, including:

[0129] If the fitting function verification result meets the preset fitting function verification requirements, consistency fitting is performed based on the line fault identification result and the line fault type code;

[0130] Determine whether a fault occurs in the corresponding connection line based on the consistency fitting result and the line fault identification result.

[0131] In one embodiment of the present disclosure, obtaining a switching function corresponding to a connection line includes:

[0132] pass Obtain the switch function K of the corresponding connection line;

[0133] Among them, x ij is the line fault type code of the connection line between the i-th node and the j-th node at the next moment, C1 is the number of connection lines downstream of the corresponding connection line, C2 is the number of connection lines upstream of the corresponding connection line, M is the number of distributed energy type nodes in the distribution network, if the t-th distributed energy type node in the distribution network is connected to the grid, then If the tth distributed energy type node in the distribution network is not connected to the grid, then

[0134] In one embodiment of the present disclosure, performing fitting function verification based on the next moment line fault type code, line fault type code, fault state code, and switching function of the corresponding connected line includes:

[0135] pass Calculating a first mathematical expectation value E1, where C(X) is used to indicate a set of line fault type codes of the connection line at the next moment, and F' is used to indicate a line fault state code of the corresponding connection line;

[0136] pass Calculating a second mathematical expectation value E2, where F is used to indicate a line fault type code corresponding to the connection line, and C(K) is used to indicate a set of switching functions of the connection line;

[0137] If the fitting function verification result meets the preset fitting function verification requirements, consistency fitting is performed based on the line fault identification result and the line fault type code, including:

[0138] If E1≥σ and E2≥β, consistency fitting is performed based on the line fault identification result and the line fault type code, where σ is a preset first mathematical expectation threshold and β is a preset second mathematical expectation threshold.

[0139] In one embodiment of the present disclosure, performing consistency fitting based on the line fault identification result and the line fault type code includes:

[0140] based on Calculate the risk estimate R ξ，λ ;

[0141] Among them C ξ (X l ) is the line fault type code of the lth connecting line in the distribution network at the next moment, C λ (K l ) is the switching function of the lth connecting line in the distribution network, and n is the number of connecting lines in the distribution network;

[0142] based on Calculate the fault probability threshold ξ*, where μ is the upper limit of the consistency probability obtained in advance;

[0143] Determine whether a fault occurs in the corresponding connection line based on the consistency fitting results and line fault identification results, including:

[0144] If the probability of a fault occurring in the corresponding connection line indicated by the line fault identification result is greater than or equal to the fault probability threshold ξ*, it is determined that a fault occurs in the corresponding connection line.

[0145] According to the technical solution provided by the embodiments of the present disclosure, data fitting is performed on the fault information collected during the actual detection process, the line fault status information extracted from line features, and the positioning results generated by deep learning. While considering multiple factors, the accuracy of fault positioning is improved.

[0146] Figure 2 The following is a block diagram of a device for identifying a fault in a power distribution network according to an embodiment of the present disclosure, wherein the device can be implemented as part or all of an electronic device through software, hardware, or a combination of both.

[0147] like Figure 2 As shown, the distribution network line fault identification device 200 includes:

[0148] The distribution network data acquisition module 201 is configured to acquire node characteristic data of each node in the distribution network, distributed energy state characteristic data of each node, and connection line characteristic data of connection lines in the distribution network;

[0149] The adjacency matrix acquisition module 202 is configured to acquire an adjacency matrix indicating a topological relationship between nodes in the power distribution network;

[0150] The data aggregation module 203 is configured to aggregate the node feature data, the distributed energy state feature data, and the connection line feature data according to the adjacency matrix to generate a node feature matrix, a distributed energy state feature matrix, and a connection line feature matrix corresponding to the distribution network;

[0151] The model acquisition module 204 is configured to acquire a pre-trained line fault identification model;

[0152] The identification result acquisition module 205 is configured to input the node feature matrix, the distributed energy state feature matrix, and the connection line feature matrix into the line fault identification model to obtain a line fault identification result output by the line fault identification model, wherein the line fault identification result is used to indicate the probability of a corresponding connection line in the distribution network having a fault;

[0153] The fault identification module 206 is configured to determine whether a fault occurs in the corresponding connection line according to the line fault identification result.

[0154] In one embodiment of the present disclosure, the node characteristic data includes at least one of voltage amplitude, voltage phase angle, active power, reactive power, node load, generated power, and node fault status.

[0155] Among them, the voltage amplitude is the voltage range value of the node; the voltage phase angle is the voltage phase angle of the node; the active power is the AC power actually generated or consumed by the node per unit time; the reactive power is the electric power required by the electrical equipment in the node to establish an alternating magnetic field and induced magnetic flux; the node load is the load situation of the node, including the number and type of power consumption or power generation equipment connected to the distribution network through the node; the generated power is the power of the node uploading electricity to the distribution network, and the generated power is less than the active power; the node fault status is whether the node has a fault and the specific fault type (such as fault voltage, current, etc.).

[0156] In one embodiment of the present disclosure, the distributed energy status characteristic data includes at least one of the distributed energy node type, the distributed energy node availability status, the distributed energy node grid access status, the distributed energy node charge and discharge status, and the distributed energy node energy storage device charge and discharge status.

[0157] Among them, the distributed energy node type is used to indicate whether the node is a distributed energy type node (that is, a node with the function of uploading electricity to the distribution network); the distributed energy node availability status is used to indicate whether the distributed energy type node is available; the distributed energy node grid access status is used to indicate whether the distributed energy type node is involved in the distribution network; the distributed energy node charge and discharge status is used to indicate whether the distributed energy type node is in a charging state, a discharging state or an idle state; the distributed energy node energy storage device charge and discharge status is used to indicate that the energy storage device in the distributed energy type node is in a charging state, a discharging state or an idle state.

[0158] In one embodiment of the present disclosure, the connection line characteristic data includes at least one of line impedance, line current intensity, active power, reactive power, conduction state, line type, line capacity, line distance, and connection state.

[0159] Among them, Line Impedance is the line impedance of the connecting line, including resistance and reactance; Line Current is the current value passing through the connecting line; Active Power is the active power passing through the connecting line, and Reactive Power is the reactive power passing through the connecting line; Conductivity is whether the connecting line is conductive; Line Type is whether the connecting line is connected to a main line or a branch line; Line Capacity is the maximum tolerable power or current of the connecting line; Line Distance is the physical distance or topological distance of the line distance; Connection Status is whether the line distance is set to conductive or disconnected.

[0160] According to the technical solution provided by the embodiments of the present disclosure, node feature data of each node in the distribution network, distributed energy state feature data of each node, and connection line feature data of the connection lines in the distribution network are obtained; an adjacency matrix for indicating the topological relationship of the nodes in the distribution network is obtained; the node feature data, distributed energy state feature data, and connection line feature data are respectively aggregated according to the adjacency matrix to generate a node feature matrix, a distributed energy state feature matrix, and a connection line feature matrix corresponding to the distribution network; a pre-trained line fault identification model is obtained; the node feature matrix, the distributed energy state feature matrix, and the connection line feature matrix are used as input and input into the line fault identification model to obtain a line fault identification result output by the line fault identification model, the line fault identification result being used to indicate the probability of a fault occurring in the corresponding connection line in the distribution network; and whether a fault occurs in the corresponding connection line is determined according to the line fault identification result. In this scheme, not only the characteristics of each node in the distribution network and the topological relationship of the nodes in the distribution network are taken into account, but also the impact of the access of distributed energy type nodes on the fault line of the distribution network is taken into account. Therefore, when determining whether the corresponding connection line has a fault based on the obtained line fault identification result, the determination result is more accurate, which improves the accuracy and efficiency of distribution network fault identification, allowing operation and maintenance personnel to identify faults in the distribution network in a timely and accurate manner, thereby accelerating the speed of power supply recovery of the distribution network and helping to improve the stability and reliability of the distribution network.

[0161] In one embodiment of the present disclosure, the apparatus further comprises:

[0162] a code acquisition module configured to acquire a line fault type code of the corresponding connection line uploaded by the distributed device and a line fault status code of the corresponding connection line uploaded by the node fault detection device, wherein if a ground fault occurs in the corresponding connection line, the line fault type code is 01; if a forward current short circuit fault occurs in the corresponding connection line, the line fault type code is 10 and the line fault status code is 1; if a reverse current short circuit fault occurs in the corresponding connection line, the line fault type code is 11 and the line fault status code is -1; if no fault occurs in the corresponding connection line, the line fault status code is 0;

[0163] A fault prediction module is configured to obtain a line fault type code of a corresponding connected line at a next moment based on the line characteristic data;

[0164] A switch function acquisition module is configured to acquire a switch function corresponding to a connection line;

[0165] A fitting function verification module is configured to verify the fitting function based on the next moment line fault type code, line fault type code, fault state code and switching function of the corresponding connected line;

[0166] The fault identification module is specifically configured as follows:

[0167] If the fitting function verification result meets the preset fitting function verification requirements, consistency fitting is performed based on the line fault identification result and the line fault type code;

[0168] Determine whether a fault occurs in the corresponding connection line based on the consistency fitting result and the line fault identification result.

[0169] In one embodiment of the present disclosure, the switch function acquisition module is specifically configured to:

[0170] pass Obtain the switch function K of the corresponding connection line;

[0171] Among them, x ij is the line fault type code of the connection line between the i-th node and the j-th node at the next moment, C1 is the number of connection lines downstream of the corresponding connection line, C2 is the number of connection lines upstream of the corresponding connection line, M is the number of distributed energy type nodes in the distribution network, if the t-th distributed energy type node in the distribution network is connected to the grid, then If the tth distributed energy type node in the distribution network is not connected to the grid,

[0172] In one embodiment of the present disclosure, the fitting function verification module is specifically configured to:

[0173] pass Calculating a first mathematical expectation value E1, where C(X) is used to indicate a set of line fault type codes of the connection line at the next moment, and F' is used to indicate a line fault state code of the corresponding connection line;

[0174] pass Calculating a second mathematical expectation value E2, where F is used to indicate a line fault type code corresponding to the connection line, and C(K) is used to indicate a set of switching functions of the connection line;

[0175] The fault identification module is specifically configured as follows:

[0176] If E1≥σ and E2≥β, consistency fitting is performed based on the line fault identification result and the line fault type code, where σ is a preset first mathematical expectation threshold and β is a preset second mathematical expectation threshold.

[0177] In one embodiment of the present disclosure, the fault identification module is specifically configured to:

[0178] based on Calculate the risk estimate R ξ，λ ;

[0179] Among them C ξ (X l ) is the line fault type code of the lth connecting line in the distribution network at the next moment, C λ (K l ) is the switching function of the lth connecting line in the distribution network, and n is the number of connecting lines in the distribution network;

[0180] based on Calculate the fault probability threshold ξ*, where μ is the upper limit of the consistency probability obtained in advance;

[0181] If the probability of a fault occurring in the corresponding connection line indicated by the line fault identification result is greater than or equal to the fault probability threshold ξ*, it is determined that a fault occurs in the corresponding connection line.

[0182] According to the technical solution provided by the embodiments of the present disclosure, data fitting is performed on the fault information collected during the actual detection process, the line fault status information extracted from line features, and the positioning results generated by deep learning. While considering multiple factors, the accuracy of fault positioning is improved.

[0183] The present disclosure also discloses an electronic device, Figure 3 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0184] like Figure 3As shown, the electronic device includes a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method according to an embodiment of the present disclosure.

[0185] In a first aspect, an embodiment of the present disclosure provides a method for identifying a distribution network line fault, comprising:

[0186] Obtain node characteristic data of each node in the distribution network, distributed energy state characteristic data of each node, and connection line characteristic data of the connection lines in the distribution network;

[0187] Obtaining an adjacency matrix indicating topological relationships of nodes in the distribution network;

[0188] According to the adjacency matrix, the node feature data, the distributed energy state feature data and the connection line feature data are aggregated respectively to generate the node feature matrix, the distributed energy state feature matrix and the connection line feature matrix corresponding to the distribution network;

[0189] Obtain a pre-trained line fault identification model;

[0190] The node feature matrix, the distributed energy state feature matrix, and the connection line feature matrix are input into the line fault identification model to obtain a line fault identification result output by the line fault identification model. The line fault identification result is used to indicate the probability of a fault occurring in the corresponding connection line in the distribution network.

[0191] Determine whether a fault occurs in the corresponding connection line based on the line fault identification result.

[0192] In one embodiment of the present disclosure, the node characteristic data includes at least one of voltage amplitude, voltage phase angle, active power, reactive power, node load, generated power, and node fault status.

[0193] In one embodiment of the present disclosure, the distributed energy status characteristic data includes at least one of the distributed energy node type, the distributed energy node availability status, the distributed energy node grid access status, the distributed energy node charge and discharge status, and the distributed energy node energy storage device charge and discharge status.

[0194] In one embodiment of the present disclosure, the connection line characteristic data includes at least one of line impedance, line current intensity, active power, reactive power, conduction state, line type, line capacity, line distance, and connection state.

[0195] In one embodiment of the present disclosure, the method further comprises:

[0196] Obtain the line fault type code of the corresponding connection line uploaded by the distributed device and the line fault status code of the corresponding connection line uploaded by the node fault detection device. If a ground fault occurs on the corresponding connection line, the line fault type code is 01; if a forward current short circuit fault occurs on the corresponding connection line, the line fault type code is 10 and the line fault status code is 1; if a reverse current short circuit fault occurs on the corresponding connection line, the line fault type code is 11 and the line fault status code is -1; if no fault occurs on the corresponding connection line, the line fault status code is 0;

[0197] Obtaining the next moment line fault type code of the corresponding connected line based on the line characteristic data;

[0198] Get the switch function of the corresponding connection line;

[0199] Verify the fitting function based on the next moment line fault type code, line fault type code, fault state code and switching function of the corresponding connected line;

[0200] Determine whether a fault occurs on the corresponding connection line based on the line fault identification result, including:

[0201] If the fitting function verification result meets the preset fitting function verification requirements, consistency fitting is performed based on the line fault identification result and the line fault type code;

[0202] Determine whether a fault occurs in the corresponding connection line based on the consistency fitting result and the line fault identification result.

[0203] In one embodiment of the present disclosure, obtaining a switching function corresponding to a connection line includes:

[0204] pass Obtain the switch function K of the corresponding connection line;

[0205] Among them, x ij is the line fault type code of the connection line between the i-th node and the j-th node at the next moment, C1 is the number of connection lines downstream of the corresponding connection line, C2 is the number of connection lines upstream of the corresponding connection line, M is the number of distributed energy type nodes in the distribution network, if the t-th distributed energy type node in the distribution network is connected to the grid, then If the tth distributed energy type node in the distribution network is not connected to the grid, then

[0206] In one embodiment of the present disclosure, performing fitting function verification based on the next moment line fault type code, line fault type code, fault state code, and switching function of the corresponding connected line includes:

[0207] pass Calculating a first mathematical expectation value E1, where C(X) is used to indicate a set of line fault type codes of the connection line at the next moment, and F' is used to indicate a line fault state code of the corresponding connection line;

[0208] pass Calculating a second mathematical expectation value E2, where F is used to indicate a line fault type code corresponding to the connection line, and C(K) is used to indicate a set of switching functions of the connection line;

[0209] If the fitting function verification result meets the preset fitting function verification requirements, consistency fitting is performed based on the line fault identification result and the line fault type code, including:

[0210] If E1≥σ and E2≥β, consistency fitting is performed based on the line fault identification result and the line fault type code, where σ is a preset first mathematical expectation threshold and β is a preset second mathematical expectation threshold.

[0211] In one embodiment of the present disclosure, performing consistency fitting based on the line fault identification result and the line fault type code includes:

[0212] based on Calculate the risk estimate R ξ，λ ;

[0213] Among them C ξ (X l ) is the line fault type code of the lth connecting line in the distribution network at the next moment, C λ (K l ) is the switching function of the lth connecting line in the distribution network, and n is the number of connecting lines in the distribution network;

[0214] based on Calculate the fault probability threshold ξ*, where μ is the upper limit of the consistency probability obtained in advance;

[0215] Determine whether a fault occurs in the corresponding connection line based on the consistency fitting results and line fault identification results, including:

[0216] If the probability of a fault occurring in the corresponding connection line indicated by the line fault identification result is greater than or equal to the fault probability threshold ξ*, it is determined that a fault occurs in the corresponding connection line.

[0217] Figure 4 A schematic diagram showing the structure of a computer system suitable for implementing the method according to an embodiment of the present disclosure is shown.

[0218] like Figure 4As shown, the computer system includes a processing unit, which can execute the various methods in the above-mentioned embodiments according to a program stored in a read-only memory (ROM) or a program loaded from a storage portion into a random access memory (RAM). In the RAM, various programs and data required for the operation of the computer system are also stored. The processing unit, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0219] The following components are connected to the I / O interface: an input part including a keyboard, a mouse, etc.; an output part including a cathode ray tube (CRT), a liquid crystal display (LCD), a speaker, etc.; a storage part including a hard disk, etc.; and a communication part including a network interface card such as a LAN card, a modem, etc. The communication part performs a communication process via a network such as the Internet. The drive is also connected to the I / O interface as needed. Removable media, such as magnetic disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on the drive as needed so that the computer program read therefrom is installed into the storage part as needed. Among them, the processing unit can be implemented as a processing unit such as a CPU, a GPU, a TPU, an FPGA, an NPU, etc.

[0220] In particular, according to embodiments of the present disclosure, the methods described above can be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for executing the methods described above. In such embodiments, the computer program can be downloaded and installed from a network via a communication component and / or installed from a removable medium.

[0221] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of code, and the module, program segment or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0222] The units or modules involved in the embodiments described in this disclosure may be implemented by software or programmable hardware. The units or modules described may also be provided in a processor, and the names of these units or modules do not, in certain circumstances, constitute limitations on the units or modules themselves.

[0223] As another aspect, the present disclosure further provides a computer-readable storage medium. This computer-readable storage medium may be included in the electronic device or computer system described in the above embodiments, or may be a standalone computer-readable storage medium not incorporated into the device. The computer-readable storage medium stores one or more programs, which are used by one or more processors to execute the methods described in the present disclosure.

[0224] The above description is merely a preferred embodiment of the present disclosure and an illustration of the underlying technical principles. Those skilled in the art should understand that the scope of the invention herein is not limited to technical solutions formed by specific combinations of the aforementioned technical features. It also encompasses other technical solutions formed by any combination of the aforementioned technical features or their equivalents, without departing from the inventive concept. For example, a technical solution formed by replacing the aforementioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

Claims

1. A method for identifying a distribution network line fault, characterized in that: include: Acquire node characteristic data of each node in the distribution network, distributed energy state characteristic data of each node, and connection line characteristic data of the connection lines in the distribution network; Obtaining an adjacency matrix for indicating topological relationships of nodes in the power distribution network; Aggregating the node feature data, the distributed energy state feature data, and the connection line feature data according to the adjacency matrix to generate a node feature matrix, a distributed energy state feature matrix, and a connection line feature matrix corresponding to the distribution network; Obtain a pre-trained line fault identification model; The node characteristic matrix, the distributed energy state characteristic matrix, and the connection line characteristic matrix are input into the line fault identification model to obtain a line fault identification result output by the line fault identification model, wherein the line fault identification result is used to indicate the probability of a fault occurring in a corresponding connection line in the distribution network; determining whether a fault occurs in the corresponding connection line according to the line fault identification result; The method further comprises: Obtaining the line fault type code of the corresponding connection line uploaded by the distributed device and the line fault status code of the corresponding connection line uploaded by the node fault detection device; Obtaining a line fault type code of the corresponding connected line at a next moment based on the line characteristic data; Get the switch function of the corresponding connection line; Verify the fitting function based on the next moment line fault type code, line fault type code, fault state code and switching function of the corresponding connected line; The determining whether a fault occurs in the corresponding connection line according to the line fault identification result includes: If the fitting function verification result meets the preset fitting function verification requirement, performing consistency fitting based on the line fault identification result and the line fault type code; Determining whether a fault occurs in the corresponding connection line according to the consistency fitting result and the line fault identification result; The obtaining of the switch function of the corresponding connection line includes: pass Get the switch function of the corresponding connection line ; in, For the Node and The next moment line fault type code of the line connecting the nodes, is the number of connection lines downstream of the corresponding connection line, is the number of connection lines upstream of the corresponding connection line, is the number of nodes of distributed energy type in the distribution network. The nodes of distributed energy types are connected to the grid , if the first If the nodes of distributed energy type are not connected to the grid ; The performing of fitting function verification based on the next moment line fault type code, line fault type code, fault state code and switching function of the corresponding connection line includes: pass Calculate the first mathematical expectation ,in A set of line fault type codes used to indicate the next moment of the connection line. A line fault type code for indicating the corresponding connection line; pass Calculate the second mathematical expectation ,in A line fault status code for indicating the corresponding connection line, A set of switch functions used to indicate connection lines; If the fitting function verification result meets the preset fitting function verification requirement, performing consistency fitting based on the line fault identification result and the line fault type code, including: like and , then consistency fitting is performed based on the line fault identification result and the line fault type code, where is the preset first mathematical expectation threshold, is a preset second mathematical expectation threshold; The performing consistency fitting based on the line fault identification result and the line fault type code includes: based on Calculating risk estimates ; in is the first The next moment line fault type code of the connected line, is the first The switching function of the connection line, is the number of connecting lines in the distribution network; based on Calculating the failure probability threshold ,in is the upper limit of the consistency probability obtained in advance; The determining whether a fault occurs in the corresponding connection line according to the consistency fitting result and the line fault identification result includes: If the probability of the corresponding connection line failing as indicated by the line fault identification result is greater than or equal to the fault probability threshold , it is determined that the corresponding connection line has a fault.

2. The method for identifying a distribution network line fault according to claim 1, wherein: The node characteristic data includes at least one of voltage amplitude, voltage phase angle, active power, reactive power, node load, generated power, and node fault status.

3. The method for identifying a distribution network line fault according to claim 1, wherein: The distributed energy state characteristic data includes at least one of the distributed energy node type, the distributed energy node availability status, the distributed energy node grid access status, the distributed energy node charge and discharge status, and the distributed energy node energy storage device charge and discharge status.

4. The method for identifying a distribution network line fault according to claim 1, wherein: The connection line characteristic data includes at least one of line impedance, line current intensity, active power, reactive power, conduction state, line type, line capacity, line distance, and connection state.

5. The method for identifying a distribution network line fault according to claim 1, wherein: If a ground fault occurs in the corresponding connection line, the line fault type code is 01; if a forward current short circuit fault occurs in the corresponding connection line, the line fault type code is 10 and the line fault status code is 1; if a reverse current short circuit fault occurs in the corresponding connection line, the line fault type code is 11 and the line fault status code is -1; if no fault occurs in the corresponding connection line, the line fault status code is 0.

6. A distribution network line fault identification device, characterized in that: include: A distribution network data acquisition module is configured to acquire node characteristic data of each node in the distribution network, distributed energy state characteristic data of each node, and connection line characteristic data of connection lines in the distribution network; an adjacency matrix acquisition module, configured to acquire an adjacency matrix indicating a topological relationship between nodes in the power distribution network; a data aggregation module configured to aggregate the node feature data, the distributed energy state feature data, and the connection line feature data according to an adjacency matrix to generate a node feature matrix, a distributed energy state feature matrix, and a connection line feature matrix corresponding to the distribution network; A model acquisition module is configured to acquire a pre-trained line fault identification model; an identification result acquisition module, configured to input the node feature matrix, the distributed energy state feature matrix, and the connection line feature matrix into the line fault identification model to obtain a line fault identification result output by the line fault identification model, wherein the line fault identification result is used to indicate a probability of a fault occurring in a corresponding connection line in the distribution network; a fault identification module configured to determine whether a fault occurs in the corresponding connection line according to the line fault identification result; The device further comprises: A code acquisition module is configured to acquire a line fault type code of a corresponding connection line uploaded by a distributed device and a line fault status code of a corresponding connection line uploaded by a node fault detection device; a fault prediction module configured to obtain a next-moment line fault type code of the corresponding connected line based on the line characteristic data; A switch function acquisition module is configured to acquire a switch function corresponding to a connection line; A fitting function verification module is configured to verify the fitting function based on the next moment line fault type code, line fault type code, fault state code and switching function of the corresponding connected line; The fault identification module is specifically configured to: If the fitting function verification result meets the preset fitting function verification requirement, performing consistency fitting based on the line fault identification result and the line fault type code; Determining whether a fault occurs in the corresponding connection line according to the consistency fitting result and the line fault identification result; The switch function acquisition module is specifically configured as follows: pass Get the switch function of the corresponding connection line ; in, For the Node and The next moment line fault type code of the line connecting the nodes, is the number of connection lines downstream of the corresponding connection line, is the number of connection lines upstream of the corresponding connection line, is the number of nodes of distributed energy type in the distribution network. The nodes of distributed energy types are connected to the grid , if the first If the nodes of distributed energy type are not connected to the grid ; The fitting function verification module is specifically configured as follows: pass Calculate the first mathematical expectation ,in A set of line fault type codes used to indicate the next moment of the connection line. A line fault type code for indicating the corresponding connection line; pass Calculate the second mathematical expectation ,in A line fault status code for indicating the corresponding connection line, A set of switch functions used to indicate connection lines; The fault identification module is specifically configured to: like and , then consistency fitting is performed based on the line fault identification result and the line fault type code, where is the preset first mathematical expectation threshold, is a preset second mathematical expectation threshold; The fault identification module is specifically configured to: based on Calculating risk estimates ; in is the first The next moment line fault type code of the connected line, is the first The switching function of the connection line, is the number of connecting lines in the distribution network; based on Calculating the failure probability threshold ,in is the upper limit of the consistency probability obtained in advance; If the probability of the corresponding connection line failing as indicated by the line fault identification result is greater than or equal to the fault probability threshold , it is determined that the corresponding connection line has a fault.

7. The distribution network line fault identification device according to claim 6, characterized in that: The node characteristic data includes at least one of voltage amplitude, voltage phase angle, active power, reactive power, node load, generated power, and node fault status.

8. The distribution network line fault identification device according to claim 6, characterized in that: The distributed energy state characteristic data includes at least one of the distributed energy node type, the distributed energy node availability status, the distributed energy node grid access status, the distributed energy node charge and discharge status, and the distributed energy node energy storage device charge and discharge status.

9. The distribution network line fault identification device according to claim 6, characterized in that: The connection line characteristic data includes at least one of line impedance, line current intensity, active power, reactive power, conduction state, line type, line capacity, line distance, and connection state.

10. The distribution network line fault identification device according to claim 6, characterized in that: If a ground fault occurs in the corresponding connection line, the line fault type code is 01; if a forward current short circuit fault occurs in the corresponding connection line, the line fault type code is 10 and the line fault status code is 1; if a reverse current short circuit fault occurs in the corresponding connection line, the line fault type code is 11 and the line fault status code is -1; if no fault occurs in the corresponding connection line, the line fault status code is 0.

11. An electronic device, characterized in that: The method comprises a memory and a processor; wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method according to any one of claims 1 to 5.

12. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the computer instructions are executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images