Power transmission network fault positioning method and device, equipment, storage medium and chip

Abstract

The invention discloses a power transmission network fault positioning method, device and equipment, a storage medium and a chip, and belongs to the technical field of power grids. Wherein the power transmission network comprises a plurality of power transmission lines, and traveling wave measuring points are arranged at the two ends of each power transmission line; the method comprises the steps that the wide-area traveling wave topology of the power transmission network is determined, the wide-area traveling wave topology takes traveling wave measuring points as nodes and a power transmission line as edges, each traveling wave measuring point corresponds to traveling wave characteristics, and the traveling wave characteristics are obtained by performing modal decomposition on traveling wave signals collected by the traveling wave measuring points; based on wide-area traveling wave topology, fault identification is carried out on each power transmission line through a graph identification network, and a fault line is positioned; and taking the traveling wave measuring points at the two ends of the fault line as starting points, determining a plurality of distance measuring lines related to the fault line, and positioning a fault position in the plurality of distance measuring lines. According to the invention, the fault identification precision is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of power grids, and in particular relates to a method, device, equipment, storage medium and chip for locating faults in a power transmission network. Background Art

[0002] In the process of power transmission network fault diagnosis, traveling wave signals are widely used in fault detection and ranging due to their fast propagation speed and high positioning accuracy.

[0003] Traditional traveling wave fault location methods include single-ended ranging method and dual-ended ranging method. The single-ended ranging method uses the time difference between the initial traveling wave detected by a single end and the wave head of the reflected traveling wave at the fault point to calculate the fault location. However, in a complex line network, the reflected traveling wave is refracted and reflected multiple times, and the source of the wave head is difficult to accurately identify. The dual-ended ranging method determines the location of the fault point by the time difference of the initial traveling wave arrival at the measuring points at both ends of the line. However, when the distance between the measuring points is long, the ranging accuracy will decrease due to the attenuation of the line mode wave velocity, and the measurement point acquisition accuracy is required to be high. Failure to capture the wave head at any end of the measuring point will lead to positioning failure.

[0004] Therefore, how to improve the accuracy of fault location in a complex transmission network environment is an urgent problem to be solved. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the related art. To this end, the present invention proposes a transmission network fault location method, device, equipment, storage medium and chip to improve the accuracy of fault location.

[0006] In a first aspect, the present invention provides a method for locating a fault in a transmission network, wherein the transmission network comprises a plurality of transmission lines, and a traveling wave measuring point is arranged at both ends of each transmission line; the method comprises: Determine a wide-area traveling wave topology of the power transmission network, wherein the wide-area traveling wave topology has the traveling wave measuring points as nodes and the transmission lines as edges, each traveling wave measuring point corresponds to a traveling wave feature, and the traveling wave feature is obtained by performing modal decomposition on traveling wave signals collected by the traveling wave measuring points; Based on the wide-area traveling wave topology, fault identification is performed on each transmission line through a graph recognition network to locate the faulty line; Taking the traveling wave measurement points at both ends of the fault line as starting points, multiple distance measurement lines related to the fault line are determined, and the fault position is located in the multiple distance measurement lines.

[0007] In the above technical scheme, by constructing a wide-area traveling wave graph data structure, taking the traveling wave measurement points as nodes and the overhead lines as edges, the graph data structure is used to represent the topological relationship of the transmission network, providing basic data support for fault location; and taking the wide-area traveling wave topology as input, a learnable graph recognition network is proposed to mine the wide-area traveling wave characteristics and learn the nonlinear relationship between multiple measurement points and the fault line, which can make the fault line identification more accurate, especially in the power grid with multi-T connection structure, greatly improving the robustness of fault line identification; finally, multiple ranging lines are formed based on the double-end measurement points of the fault line, further narrowing the topological range of locating the fault, and adopting a multi-link ranging fusion mechanism for fault location, avoiding the error of a single ranging path, and improving the accuracy and stability of ranging.

[0008] According to an embodiment of the present invention, based on the wide area traveling wave topology, the fault identification of each transmission line is performed through a graph recognition network to locate the fault line, including: Based on the correlation relationship between each traveling wave measurement point in the wide-area traveling wave topology, adjacent measurement points of each traveling wave measurement point are determined respectively; Generate global features based on the traveling wave features of each traveling wave measuring point and its adjacent measuring points; Determine the importance of each traveling wave measuring point and its adjacent measuring points respectively, and generate a plurality of positioning features based on the importance; Fusion of the global features and the positioning features to generate target features corresponding to each transmission line; Fault identification is performed on each transmission line based on the target feature to obtain a determination result of each transmission line, and the fault line is located based on the determination result of each transmission line.

[0009] In the above embodiments, global fault propagation feature extraction is achieved by combining the transmission network topology, thereby improving the robustness of fault detection, and by highlighting key measurement points by determining the importance, the accuracy of fault identification can be improved.

[0010] In a second aspect, the present invention provides a transmission network fault location device, wherein the transmission network includes a plurality of transmission lines, and traveling wave measurement points are arranged at both ends of each transmission line; the device comprises: A topology module, used for determining a wide-area traveling wave topology of a power transmission network, wherein the wide-area traveling wave topology has the traveling wave measuring points as nodes and the transmission lines as edges, each traveling wave measuring point corresponding to a traveling wave feature, and the traveling wave feature is obtained by performing modal decomposition on traveling wave signals collected by the traveling wave measuring points; An identification module, used to identify faults of each transmission line through a graph recognition network based on the wide area traveling wave topology and locate the faulty line; The positioning module is used to determine a plurality of distance measurement lines related to the faulty line with the traveling wave measurement points at both ends of the faulty line as the starting point, and locate the fault position in the plurality of distance measurement lines.

[0011] In the above technical scheme, by constructing a wide-area traveling wave graph data structure, taking the traveling wave measurement points as nodes and the overhead lines as edges, the graph data structure is used to represent the topological relationship of the transmission network, providing basic data support for fault location; and taking the wide-area traveling wave topology as input, a learnable graph recognition network is proposed to mine the wide-area traveling wave characteristics and learn the nonlinear relationship between multiple measurement points and the fault line, which can make the fault line identification more accurate, especially in the power grid with multi-T connection structure, greatly improving the robustness of fault line identification; finally, multiple ranging lines are formed based on the double-end measurement points of the fault line, further narrowing the topological range of locating the fault, and adopting a multi-link ranging fusion mechanism for fault location, avoiding the error of a single ranging path, and improving the accuracy and stability of ranging.

[0012] In a third aspect, the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for locating a power transmission network fault as described in the first aspect above is implemented.

[0013] In a fourth aspect, the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for locating a fault in a power transmission network as described in the first aspect above is implemented.

[0014] In a fifth aspect, the present invention provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the power transmission network fault location method as described in the first aspect above.

[0015] In a sixth aspect, the present invention provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for locating a fault in a power transmission network as described in the first aspect above is implemented.

[0016] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which: Figure 1 is a flow chart of a method for locating a power transmission network fault provided in some embodiments of the present invention; Figure 2is a schematic structural diagram of a typical traveling wave topology provided in some embodiments of the present invention; Figure 3 is a schematic diagram of the structure of a wide-area traveling wave topology provided in some embodiments of the present invention; Figure 4 is a schematic diagram of a process of variational mode decomposition provided in some embodiments of the present invention; Figure 5 is a schematic diagram of the principle of a graph recognition network provided in some embodiments of the present invention; Figure 6 is a schematic diagram of the principle of multi-link ranging provided in some embodiments of the present invention; Figure 7 is a schematic diagram of the structure of a power transmission network fault location device provided in some embodiments of the present invention; Figure 8 It is a schematic diagram of the structure of a computer device provided in some embodiments of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0019] Unless otherwise defined, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by technicians in the technical field of the present invention; the terms used in the specification of the present invention in the application are only for the purpose of describing specific embodiments and are not intended to limit the present invention; the terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present invention or the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order or a primary and secondary relationship.

[0020] Reference to "embodiments" in the present invention means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in the present invention may be combined with other embodiments.

[0021] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", and "attached" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0022] The term "and / or" in the present invention is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects before and after are in an "or" relationship.

[0023] The term "plurality" used in the present invention refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple sheets" refers to more than two sheets (including two sheets).

[0024] In the power system, traveling wave measurement points (nodes) and overhead lines (edges) together form a natural graph data structure. When a transmission line fails, the fault traveling wave will be refracted and reflected multiple times along the overhead line, and finally reach each measurement point and be mixed and superimposed. In this process, the traveling wave waveform of each measurement point presents two characteristics: on the one hand, it is related to the topological structure of the power grid, and on the other hand, it also contains a complex nonlinear relationship with the fault point.

[0025] Especially for transmission systems with multi-T connection and ring network structure, the robustness of fault location can be effectively improved. Under complex power grid topology (such as multi-T connection structure), it is easily affected by traveling wave reflection, signal attenuation and noise interference, resulting in large positioning errors.

[0026] In view of this, an embodiment of the present invention provides a method for locating faults in a power transmission network, by establishing a wide-area traveling wave topology based on traveling wave measurement points and transmission lines, and identifying faulty lines based on the wide-area traveling wave topology, using a graph recognition network to mine the complex associations between nodes, accurately determining the faulty lines, and finally combining the adaptive weights calculated by the graph recognition network to locate faults based on multi-link ranging, thereby improving the ranging accuracy and accurately locating the faults.

[0027] The following describes in detail the power transmission network fault location method and the like provided by the embodiments of the present invention through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0028] The transmission network fault location method provided in the embodiment of the present invention can be applied to computer equipment, and can be specifically executed by hardware or software in the computer equipment. The computer equipment includes but is not limited to one or more of various desktop computers, laptops, smart phones, tablet computers, vehicle-mounted terminals, Internet of Things devices, or portable wearable devices, etc. The Internet of Things device can be one or more of smart speakers, smart TVs, smart air conditioners, or smart vehicle-mounted devices. The portable wearable device can be one or more of a smart watch, a smart bracelet, or a head-mounted device. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, and big data and artificial intelligence platforms.

[0029] The transmission network fault location method provided by the embodiment of the present invention can be executed by a computer device or a functional module or functional entity in the computer device that can implement the transmission network fault location method. The transmission network fault location method provided by the embodiment of the present invention is described below using a computer device as an example of the execution subject.

[0030] like Figure 1 As shown, the transmission network fault location method includes: steps 110 to 130.

[0031] Step 110: determine the wide-area traveling wave topology of the transmission network. The wide-area traveling wave topology uses traveling wave measurement points as nodes and transmission lines as edges. Each traveling wave measurement point corresponds to a traveling wave feature, which is obtained by performing modal decomposition on traveling wave signals collected by the traveling wave measurement points.

[0032] The computer equipment obtains the traveling wave signals collected by each traveling wave measuring point in the transmission network, and establishes a wide-area traveling wave topology with the traveling wave measuring points as nodes and the transmission lines as edges. Among them, the traveling wave measuring points (also called measuring points) are usually located at locations such as transformers and line ends, and can collect the original traveling wave signals transmitted on the transmission lines. Traveling wave signals refer to high-frequency voltage or current components that propagate at high speed along the transmission lines when a fault or other sudden event (such as lightning strikes, switch operations) occurs in the transmission line. Unlike traditional power frequency signals, traveling wave signals mainly have the characteristics of high frequency, rapid propagation, bidirectional propagation, and transients. In complex multi-T-connected transmission lines, due to the characteristics of traveling wave signals and the existence of problems such as wave velocity attenuation and signal interference, the fault location accuracy is not high.

[0033] Wide-area traveling wave topology is a traveling wave signal propagation model based on the topological structure of the transmission network diagram. In the wide-area traveling wave topology, the traveling wave measurement points are used as nodes, and the transmission lines are used as edges to represent the propagation path of the traveling wave signals, reflecting the physical connection relationship between the various traveling wave measurement points. The node of each node is the traveling wave feature of the traveling wave measurement point, which describes the traveling wave signal properties of the traveling wave measurement point.

[0034] Traveling wave characteristics refer to signal parameters obtained after processing the traveling wave signals collected by traveling wave measurement points, including but not limited to at least one of instantaneous energy, center frequency, propagation delay, wave head polarity, etc., which are used to characterize the dynamic changes of traveling wave signals. Traveling wave characteristics are usually extracted by modal decomposition or other signal processing methods as node characteristics of each node in the transmission network topology.

[0035] Traditional topology diagrams usually only show the connection relationship between devices in the transmission network, such as Figure 2 As shown in the figure, the topology diagram shows the connection relationship between solar panels, wind power generators and power supplies. Different from the traditional topology diagram, the present invention combines the traveling wave characteristics of each traveling wave measurement point on this basis and refines it into a more representative wide-area traveling wave topology, such as Figure 3 As shown, it can not only clearly represent the transmission path formed by each transmission line in the transmission network, but also accurately reflect the transmission characteristics of the traveling wave signal in the transmission network, which can make the positioning of the fault position more accurate.

[0036] Step 120: Based on the wide area traveling wave topology, faults of each transmission line are identified through a graph recognition network to locate the faulty line.

[0037] Among them, the traveling wave characteristics of each traveling wave measurement point constitute an initial traveling wave characteristic matrix corresponding to the wide-area traveling wave topology.

[0038] The computer equipment uses the wide-area traveling wave topology and the traveling wave feature matrix composed of each traveling wave feature, combined with deep learning technology and graph structure technology, to identify the probability of failure of each transmission line, and judge the transmission line through the probability threshold, thereby judging whether each transmission line is a faulty line. There can be one or more faulty lines.

[0039] Therefore, the fault location problem of complex multi-T-connected transmission lines can be converted into a classification problem, that is, each transmission line is classified into a faulty line and a normal line, thereby achieving efficient fault location.

[0040] In some embodiments, the computer device uses the topological structure of the wide-area traveling wave topology and the traveling wave feature matrix composed of the traveling wave features of each topological node (i.e., the traveling wave measurement point) as input, and learns through the graph recognition network, thereby outputting the fault probability of each transmission line, and then identifying the fault line. Exemplarily, the graph recognition network includes a graph convolutional neural network (GCN) and a graph attention network (GAT). In other words, the graph recognition network can be a fusion of a graph convolutional network and a graph attention network, which can be called a graph convolutional attention network. It can not only learn the traveling wave features of each traveling wave node in the graph topology, but also adaptively mine the correlation between the traveling wave measurement points from the topological structure with the help of the attention mechanism. It is suitable for learning the nonlinear correlation between the wide-area multi-source traveling wave signal and the fault location in a complex power grid environment, and building a more robust and robust transmission network fault line determination model. The correlation output by the model can be used to fuse the multi-source measurement points to achieve accurate fault location after subsequent processing.

[0041] Step 130: Taking the traveling wave measurement points at both ends of the faulty line as starting points, multiple distance measurement lines related to the faulty line are determined, and the fault position is located in the multiple distance measurement lines.

[0042] After obtaining one or more faulty lines, the computer device performs a specific analysis on each faulty line.

[0043] Specifically, for any fault line, the computer device takes the traveling wave measurement point at both ends of the fault line as the starting point, selects the adjacent measurement points of the traveling wave measurement point at both ends, further narrows the scope in the entire wide-area traveling wave topology, and forms multiple ranging lines related to the fault line to locate the fault position from these ranging lines. Among them, the ranging line refers to the ranging path used to calculate the fault position. The adjacent measurement points of the traveling wave measurement points at both ends of the fault line can be the first-order adjacent measurement points, second-order adjacent measurement points, etc. of the traveling wave measurement points at both ends.

[0044] The computer device locates the fault position in multiple distance measurement lines, including: using a single-end method, a double-end method, etc. to measure the distance between the fault position and a reference measurement point, thereby locating the fault position. The reference measurement point can be a traveling wave measurement point at both ends of the fault line, or a preset traveling wave measurement point. Since there may be multiple distance measurement lines, the computer device will obtain multiple distance results, and the computer device can fuse the multiple distance results to obtain the final distance result. The fusion processing includes but is not limited to at least one of averaging, median, weighted summation, etc.

[0045] The transmission network fault location method provided by the embodiment of the present invention constructs a wide-area traveling wave graph data structure, takes traveling wave measurement points as nodes and overhead lines as edges, and uses the graph data structure to represent the topological relationship of the transmission network, thereby providing basic data support for fault location; and takes the wide-area traveling wave topology as input, adopts a proposed learnable graph recognition network, mines wide-area traveling wave features and learns the nonlinear relationship between multiple measurement points and the fault line, thereby making the fault line identification more accurate, especially in a power grid with a multi-T connection structure, greatly improving the robustness of the fault line identification; finally, multiple ranging lines are formed based on the double-end measurement points of the fault line, further narrowing the topological range of the fault location, adopting a multi-link ranging fusion mechanism for fault location, avoiding the error of a single ranging path, and improving the accuracy and stability of ranging.

[0046] In the fault diagnosis of power transmission networks, traveling wave signals are widely used due to their fast propagation speed and sensitive fault response. However, the original traveling wave signal usually contains noise and multi-frequency aliasing components, and the traveling wave signal at a single moment is difficult to fully reflect the fault characteristics, resulting in low accuracy of fault identification directly using the original traveling wave signal. Therefore, it is necessary to use signal processing methods to extract features from traveling wave signals in order to enhance the robustness and stability of fault diagnosis.

[0047] Among them, modal decomposition is a signal processing method used to decompose a complex signal into multiple independent modal components in order to analyze the signal characteristics in different frequency ranges. Based on this, in some embodiments, the above method also includes: respectively obtaining the original traveling wave signals collected by each traveling wave measurement point; for any traveling wave measurement point, performing modal decomposition on the original traveling wave signal collected by the targeted traveling wave measurement point to obtain the multi-dimensional modal components corresponding to the targeted traveling wave measurement point; by setting window parameters, respectively determining the energy values ​​of the multi-dimensional modal components in multiple windows; based on the energy values ​​of the multi-dimensional modal components in each window, performing dimensionality reduction processing on the modal components to obtain the traveling wave characteristics of the preset dimension.

[0048] The computer equipment obtains the traveling wave signals collected by multiple traveling wave measurement points in the transmission network. U ( t )express, t ∈[0, T ].in, T The sampling time is usually a few milliseconds to tens of milliseconds, and the sampling rate is usually between 1 and 10 MHz. Therefore, through high-frequency sampling of the traveling wave measurement point, the transient information of the traveling wave signal can be fully obtained, thereby improving the sensitivity of fault detection.

[0049] For any traveling wave measurement point, the computer equipment decomposes the original traveling wave signal collected by it into k modal components, the k The modal components constitute the traveling wave measurement pointk dimensional modal components. k The number can be a preset value or can be selected using a data-driven adaptive mode selection algorithm (such as deep learning prediction k value, optimize the modal decomposition effect. The original traveling wave signal is decomposed into k The modal components can be expressed as: U ( t )→{ u 1( t ), u 2( t ),…, u k ( t )}.

[0050] For any original traveling wave signal, the computer device obtains preset window parameters, including the time window size and the number of windows, and divides the traveling wave signal into multiple windows, that is, forming multiple energy blocks, and respectively calculates the energy value of the multidimensional modal component in each window. Exemplarily, the energy value of the multidimensional modal component in each window calculated by the computer device can be expressed as: (1) in, Indicates i The signal value of the sampling point, M is the number of sampling points in each window.

[0051] For example, assuming that 50 windows are set and the total number of sampling points is 500 to 1000, each window contains approximately 10 to 20 sampling points.

[0052] Furthermore, the computer device performs dimensionality reduction processing on the modal components based on the energy values ​​of the multidimensional modal components in each window through normalization processing to obtain the traveling wave characteristics of a preset dimension. The preset dimension is related to the number of windows, and the preset dimension is usually equal to the number of windows.

[0053] Exemplarily, the traveling wave feature of a preset dimension obtained by the computer device through normalization processing can be expressed as: (2) Among them, max E is the maximum energy value of all modal components of the original traveling wave signal, min E is the minimum energy value of all modal components of the original traveling wave signal.

[0054] In the above embodiment, by dividing the windows and calculating the modal energy of each window, the characteristics when the fault occurs are made more prominent, the robustness is improved and it helps to improve the accuracy of subsequent fault identification; by dimensionality reduction processing, the computational complexity is reduced and the model calculation efficiency is improved.

[0055] Variational Mode Decomposition (VMD) is an adaptive signal decomposition method that can decompose complex signals into several intrinsic mode functions (IMFs) with limited bandwidth, and can adaptively adjust the center frequency of each mode to retain key features to the greatest extent. In some embodiments, the computer device can perform variational mode decomposition on the traveling wave signal collected by the traveling wave measurement point, and decompose the traveling wave signal into k The eigenmode components are divided into three parts, each of which has a limited bandwidth, thereby removing noise and highlighting key frequency components. The final frequency distribution of the traveling wave characteristics is clearer, which can improve the stability of the traveling wave signal and help improve the accuracy of fault line identification.

[0056] To this end, for any traveling wave measuring point, the original traveling wave signal collected at the traveling wave measuring point is subjected to modal decomposition to obtain a multi-dimensional modal component corresponding to the traveling wave measuring point, including: for any traveling wave measuring point, the original traveling wave signal collected at the traveling wave measuring point is subjected to multi-layer decomposition to obtain a plurality of initial modal components; an initial center frequency of each initial modal component is determined; and with the sum of the plurality of initial modal components being equal to the original traveling wave signal as a constraint condition, each initial modal component and the corresponding initial center frequency are iteratively updated for multiple times until an iteration stop condition is satisfied to obtain a multi-dimensional modal component corresponding to the traveling wave measuring point.

[0057] For any traveling wave measurement point, the computer equipment collects its original traveling wave signal and sets the number of decomposition layers. k , and the variational mode decomposition method is used k Layer decomposition, we get k Initial modal components. The initial modal components provide the basic spectrum information of the traveling wave signal and provide input for subsequent optimization. In addition, the fault traveling wave is effectively characterized based on the decomposed intrinsic modal components, and the complex signal is decomposed into simple parts, each containing specific frequency information, which greatly reduces the complexity of the original signal. Compared with the original waveform, the local mutation is more clearly identifiable and the location information is clearer.

[0058] The computer device calculates the center frequency of each initial modal component to represent the spectral characteristics of the signal. Then, under the constraint that the sum of multiple initial modal components is equal to the original traveling wave signal, the computer device continuously optimizes the modal components and the center frequency through multiple iterations until convergence, that is, the iteration stop condition is met. The iteration stop condition includes but is not limited to the alignment of each initial modal component around its own center frequency and the minimization of the sum of the bandwidths of each initial modal component.

[0059] Since the frequency components of the signal are not fixed, if the center frequency is inaccurate, the decomposed modal components may be aliased or have frequency drift. By recalculating each iteration, each modal component can be gathered around its correct center frequency.

[0060] For example, assuming a complex signal U ( t ) is decomposed into k components, the optimization goal is to decompose the sequence into modal components with limited bandwidth and center frequency, and at the same time, the sum of the estimated bandwidths of each mode is minimized, and the constraint condition is that the sum of all modes is equal to the original complex signal. Then the constrained variational model can be expressed as: (3) Among them, ω k yes k dimensional eigenmode component u k The center frequency of (t), u k After decomposition, k eigenmode components, k is the number of decomposition levels, that is, the number of eigenmodes. is the Dirac function, * is the convolution operator, U It is the line mode or zero mode component of the fault voltage traveling wave.

[0061] like Figure 4 As shown, the computer device initializes the modal component u k , center frequency ω k and Lagrange multipliers λ , from the number of iterations n = 0, and for each modal component u k and center frequency ω k Update and update the Lagrange multiplier at the same time λ Through repeated iterations n When the iteration stop condition is met, we get k modal components, that is, the multi-dimensional modal components of the traveling wave measuring point.

[0062] Furthermore, by taking advantage of the quadratic multiplication and the Lagrange multiplier method, the augmented Lagrange function is introduced to convert the above equality constraint optimization problem into an unconstrained optimization problem. Afterwards, the computer device updates each modal component and the center frequency of each modal component , is solved by the alternating direction multiplier method, that is, the other two variables are fixed and one of the variables is updated, thereby achieving iterative update. Alternating optimization ensures that the decomposition of each mode has good bandwidth convergence and can adaptively adjust the frequency, with strong robustness. When the iterative stop condition is met, the iterative update is stopped and the final k dimensional eigenmode components.

[0063] In the above embodiment, the traveling wave signal is decomposed into multiple band-limited signals through multi-layer decomposition to avoid high-frequency noise interference and improve the separability of the traveling wave characteristics. By iteratively optimizing the modal components and the center frequency and taking the sum of all modal components equal to the original signal as a constraint, not only the accuracy of signal decomposition is improved, but also the modal center frequency can be made more stable, which is helpful for subsequent feature extraction and fault diagnosis.

[0064] In the transmission network, accurate fault identification is crucial for the safe operation of the power grid. Due to the complex topological structure of the transmission line, the propagation of the traveling wave signal on the line is affected by factors such as the power grid topology, branch nodes, and impedance characteristics, resulting in complex temporal and spatial relationships between the characteristics of the traveling wave signal at different measuring points. Therefore, how to effectively utilize wide-area traveling wave data and combine topological information to accurately identify faulty lines has become an urgent problem to be solved. Traditional methods often analyze the traveling wave signals of each measuring point separately, ignoring the dynamic correlation between different measuring points, resulting in a decrease in fault identification accuracy under multi-T connections and ring network structures.

[0065] Based on this, in some embodiments, based on the wide-area traveling wave topology, fault identification is performed on each transmission line respectively through a graph recognition network to locate the faulty line, including: based on the correlation between each traveling wave measurement point in the wide-area traveling wave topology, the adjacent measurement points of each traveling wave measurement point are determined respectively; based on the traveling wave characteristics of each traveling wave measurement point and its adjacent measurement points, a global feature is generated; the importance of each traveling wave measurement point and its adjacent measurement points is determined respectively, and a plurality of positioning features are generated based on the importance; the global feature and the positioning feature are integrated to generate a target feature corresponding to each transmission line; based on the target feature, fault identification is performed on each transmission line to obtain a determination result of each transmission line, and the faulty line is located based on the determination result of each transmission line.

[0066] Specifically, the computer device builds the adjacency relationship between the measurement points based on the connection relationship of the transmission line according to the wide area traveling wave topology. In some embodiments, the computer device can determine the directly adjacent measurement points of each traveling wave measurement point by defining an adjacency matrix.

[0067] (4) Based on the correlation between each traveling wave measurement point, the computer equipment can use the graph convolutional neural network to extract the global features of the wide-area traveling wave topology based on the traveling wave characteristics of each traveling wave measurement point and its adjacent measurement points to generate global features.

[0068] Exemplarily, the computer device generates global features through the graph convolutional neural network, which can be expressed as: (5) (6) in, A is the adjacency matrix, It is l The node feature matrix of the layer, It is l The learnable weight matrix of the layer, is the activation function.

[0069] Moreover, based on the correlation between each traveling wave measurement point, the computer device can combine the attention mechanism to measure the importance of each traveling wave measurement point to its adjacent measurement points, and generate multiple positioning features based on the importance.

[0070] Thus, the computer equipment fuses the global features and the positioning features, combines the global information with the local fault propagation characteristics, and generates the target features corresponding to each transmission line.

[0071] Finally, the computer device identifies the fault of each transmission line based on the target feature, obtains the determination result of each transmission line, and locates the faulty line based on the determination result of each transmission line. In some embodiments, the computer device can identify the fault of the target feature by binary classification and output the fault probability of each transmission line. For any transmission line, if its fault probability exceeds the preset threshold, it is determined to be a faulty line; conversely, if its fault probability does not exceed the preset threshold, it is determined to be a normal line, thereby improving the degree of automation of fault identification and achieving accurate fault location.

[0072] In the above embodiments, global fault propagation feature extraction is achieved by combining the transmission network topology, thereby improving the robustness of fault detection, and by highlighting key measurement points by determining the importance, the accuracy of fault identification can be improved.

[0073] In the fault detection of power transmission network, the propagation of traveling wave signals is affected by factors such as the topological structure, impedance characteristics, and branch connection relationship of the transmission line. It is difficult to fully reflect the global characteristics of fault propagation by analyzing the traveling wave characteristics of a certain measuring point alone. Especially in the transmission network with multi-T connection and ring network structure, the traveling wave signal will be reflected and attenuated multiple times, making it difficult for the information of a single measuring point to accurately characterize the fault characteristics. If only the traveling wave data of a certain measuring point is used for fault diagnosis, it may lead to misjudgment or missed judgment.

[0074] Therefore, in some embodiments, based on the traveling wave characteristics of each traveling wave measuring point and each of its adjacent measuring points, a global feature is generated, including: for any traveling wave measuring point, the traveling wave characteristics of the traveling wave measuring point targeted are aggregated multiple times with the traveling wave characteristics of all adjacent measuring points targeted to the traveling wave measuring point to obtain multiple aggregated characteristics; wherein the traveling wave characteristics of the traveling wave measuring point in each aggregation process are obtained based on the aggregated characteristics obtained in the last aggregation process; and the aggregated characteristics obtained in the last aggregation are used as global characteristics. Through multiple feature aggregations, the traveling wave information is diffused and integrated in the entire power grid topology structure, and finally a global feature vector capable of characterizing the global traveling wave characteristics is obtained.

[0075] Specifically, in each feature aggregation, the computer device aggregates the initial traveling wave features of each traveling wave measurement point with the initial traveling wave features of its adjacent measurement points to obtain the traveling wave features output at that time. For example, assuming that the initial traveling wave feature of traveling wave measurement point A is H (0) , the adjacent measuring points of traveling wave measuring point A include traveling wave measuring point B and traveling wave measuring point D, a total of l After the first feature aggregation, H (1) , and based on H (1) Perform the second feature aggregation to obtain H (2) ...until the l The feature aggregation is H (l) . The feature aggregation method includes but is not limited to weighted summation. Exemplarily, each feature aggregation can be expressed as the above formula (5).

[0076] Finally, after l After the sub-features are aggregated, the computer equipment can obtain the global features of each traveling wave measuring point, which not only contains the information of the measuring point itself, but also integrates the global information in the topological structure.

[0077] In the above embodiment, by performing feature aggregation on the traveling wave features of the traveling wave measuring point and its adjacent measuring points, the final features of the measuring point can fully express the global topology information, thereby improving the accuracy and robustness of fault location.

[0078] In the fault detection of power transmission network, the traveling wave signal will propagate between multiple measuring points, and the traveling wave signals received at different measuring points may differ in amplitude, phase, arrival time, etc. These differences are affected by factors such as the topology of the power transmission network, line impedance, traveling wave attenuation, and distance between measuring points, resulting in different importance of each measuring point for fault identification. In fault identification, if the same weight is used for measuring points with large contributions to fault identification and measuring points with small contributions, the fault characteristics may be diluted. Especially in complex topologies (such as multi-T connection structures), the characteristics of a single measuring point are difficult to accurately describe the entire fault mode and are prone to misjudgment.

[0079] To this end, in some embodiments, the importance of each traveling wave measurement point and its adjacent measurement points is determined respectively, and multiple positioning features are generated based on the importance, including: for any traveling wave measurement point, determining the correlation between the targeted traveling wave measurement point and any adjacent measurement point of the targeted traveling wave measurement point; based on the correlation between the targeted traveling wave measurement point and any adjacent measurement point of the targeted traveling wave measurement point, determining the attention weight between the targeted traveling wave measurement point and any adjacent measurement point of the targeted traveling wave measurement point; based on the attention weight between the targeted traveling wave measurement point and any adjacent measurement point of the targeted traveling wave measurement point, aggregating the traveling wave features of all adjacent measurement points to obtain the positioning feature corresponding to the targeted traveling wave measurement point.

[0080] Specifically, for each traveling wave measuring point, the computer device calculates the correlation between the traveling wave measuring point and each adjacent measuring point based on one or more adjacent measuring points of the traveling wave measuring point. The correlation reflects the degree of association between the traveling wave measuring point and its adjacent measuring points.

[0081] The calculation method of the correlation can be based on feature similarity, signal propagation characteristics, or the learning weights of the deep learning model to ensure that the correlation can effectively reflect the fault correlation between the measuring points. For example, the computer device can calculate the cosine similarity as the correlation to measure the directional similarity of the traveling wave feature vectors of the two measuring points. For another example, the computer device can calculate the Pearson correlation coefficient as the correlation to measure the linear correlation between the traveling wave signals of the two measuring points. For another example, the computer device can also calculate the Euclidean distance between the traveling wave feature vectors of the two measuring points as the correlation to measure the difference between the measuring point signals.

[0082] In some embodiments, for any traveling wave measurement point, the computer device automatically learns the correlation between the traveling wave measurement point and any of its adjacent measurement points through a graph convolutional network to obtain the correlation between the two. Exemplarily, the computer device outputs the traveling wave measurement point through the graph convolutional network. i Adjacent measuring points j The correlation between them can be expressed as: (7) in, Indicates the traveling wave measurement point i With traveling wave measuring point j The correlation between is the attention parameter of the neural network, W is the learnable parameter matrix, Represents the concatenation operation of the vector, LeakyReLU is the rectified linear unit, and Traveling wave measuring points i With traveling wave measuring point j Their respective traveling wave characteristics.

[0083] Therefore, for any traveling wave measurement point, the computer device can calculate the correlation between it and all adjacent measurement points. By calculating the correlation, the adjacent measurement points that have a greater impact on the current traveling wave measurement point can be identified, providing a basis for subsequent attention weight calculation.

[0084] After calculating the correlation, it is necessary to convert these correlations into weight coefficients for subsequent feature aggregation. In some embodiments, for any traveling wave measurement point, the computer device can convert the correlation between the traveling wave measurement point and any adjacent measurement point into an attention weight between the traveling wave measurement point and the adjacent measurement point by means of softmax normalization, normalized weighting or direct weighting.

[0085] After obtaining the attention weight of each adjacent measuring point, the computer device aggregates its traveling wave features with the traveling wave features of all its adjacent measuring points to obtain the final positioning features. The aggregation processing methods include but are not limited to weighted summation, weighted average, linear transformation, or recursive update through a multi-layer attention mechanism. Since the attention weights of different measuring points are different, the final positioning features can more accurately reflect the fault correlation between the measuring points.

[0086] In some embodiments, the computer device uses the attention weight of each adjacent measurement point as a weighting coefficient to aggregate the traveling wave features of all adjacent measurement points, thereby reflecting the propagation of multi-source traveling wave positioning information in the local area to the central node to obtain the positioning feature. For example, the computer device can calculate the positioning feature by the following formula: (8) in, The traveling wave characteristics i Corresponding positioning features.

[0087] In the above embodiment, by calculating the correlation, the adjacent measuring points that have a greater impact on the current measuring point can be identified, providing a basis for the subsequent attention weight calculation; the attention weight is then calculated so that in the fault identification process, the measuring points that contribute more can play a more important role, and the final positioning features more accurately characterize the fault impact range and reduce the interference of irrelevant measuring points.

[0088] To this end, in some embodiments, based on the correlation between the targeted traveling wave measurement point and any adjacent measurement point of the targeted traveling wave measurement point, the attention weight between the targeted traveling wave measurement point and any adjacent measurement point of the targeted traveling wave measurement point is determined, including: obtaining the total correlation based on the sum of the correlations between the targeted traveling wave measurement point and all the adjacent measurement points of the targeted traveling wave measurement point; for any adjacent measurement point of the targeted traveling wave measurement point, determining the proportion of the correlation between the targeted traveling wave measurement point and the targeted adjacent measurement point to the total correlation; based on the proportion, obtaining the attention weight between the targeted traveling wave measurement point and the targeted adjacent measurement point.

[0089] Specifically, for any traveling wave measuring point, the computer device calculates the correlation between it and each adjacent measuring point, and obtains the total correlation corresponding to the traveling wave measuring point based on the sum of the correlations of all adjacent measuring points. The total correlation can reflect the fault propagation influence range of the traveling wave measuring point in the entire set of adjacent measuring points.

[0090] Afterwards, the computer device calculates the correlation ratio between the traveling wave measurement point and any adjacent measurement point, that is, the ratio of the correlation in the total correlation. The ratio indicates the contribution of the adjacent measurement point in the final feature calculation of the traveling wave measurement point. Therefore, the correlation ratio is used as the final attention weight to weight the traveling wave features of the adjacent measurement point. The traveling wave features of the traveling wave measurement point will be calculated by weighting the traveling wave features of the adjacent measurement points.

[0091] Exemplarily, the computer device can calculate the traveling wave measurement point by the following formula: i Adjacent measuring points j The attention weights between: (9) in, Indicates the traveling wave measurement point Adjacent points k , Indicates the traveling wave measurement point The number of adjacent measurement points, Adjacent measuring points k The traveling wave characteristics.

[0092] In the above embodiment, by calculating the attention weight, in the fault identification process, the measurement points with greater contributions can play a more important role, highlighting the features of the measurement points with higher contributions to the fault, making the final features more consistent with the fault propagation law and improving the fault identification accuracy.

[0093] In the present invention, global features can be extracted, for example, through graph convolutional neural networks, which can reflect the fault propagation mode of the entire power grid, but may lack accurate descriptions of local key measurement points. Positioning features can be calculated, for example, through graph attention networks, emphasizing the strength of association between measurement points, and can accurately locate the scope of fault impact, but may ignore global background information. Using global features alone may result in the loss of local details, resulting in large ranging errors.

[0094] To this end, in some embodiments, global features and positioning features are fused to generate target features corresponding to each transmission line, including: determining a first fusion coefficient and a second fusion coefficient; based on the first fusion coefficient, feature fusing the global features and positioning features corresponding to each traveling wave measurement point to obtain initial target features corresponding to each traveling wave measurement point; based on the second fusion coefficient, adjusting the initial target features corresponding to each traveling wave measurement point to obtain target features between each traveling wave measurement point and its adjacent measurement points; wherein any traveling wave measurement point and any adjacent measurement point of any traveling wave measurement point correspond to a transmission line.

[0095] Specifically, the computer device obtains a first fusion coefficient and a second fusion coefficient. The fusion coefficient is used to balance the contribution of global features and positioning features to fault line identification. The fusion coefficient can be a preset value or an adaptive learning parameter obtained through training optimization. Among them, the first fusion coefficient is used to control the weight of global features and positioning features in the initial fusion. The second fusion coefficient is used to further optimize the target features at the transmission line level to make it more consistent with the fault propagation law.

[0096] The computer device first fuses the global features and the positioning features by weighted summation to generate the initial target features. Through the initial fusion, the organic combination of global information and local information is ensured, and the fault identification capability at the measurement point level is improved. For example, based on the first fusion coefficient , the computer device fuses the global features and positioning features to generate the initial target features, which can be expressed as follows: (10) in, For positioning features, is a global feature, is the initial target feature, Indicates i Traveling wave measurement points.

[0097] The initial target feature is applicable to a single measuring point and needs to be further extended to the transmission line level. Therefore, the computer device uses the second fusion coefficient to adjust the initial target feature so that the target feature not only contains the information of a single measuring point, but also can fuse the information of adjacent measuring points to better conform to the fault propagation mode on the transmission line. For example, based on the second fusion coefficient , the computer device can calculate the target features through the following formula: (11) Among them, the target feature is the traveling wave measurement point i and traveling wave measurement points j The fault feature representation of the connected transmission lines. When the first fusion coefficient is 0 and the second fusion coefficient is 1, the model reflects the attention based on the original features. When the second fusion coefficient is 0, it reflects the characteristic of the model to uniformly aggregate the neighbor node information.

[0098] For example, Figure 5 As shown, the graph recognition network in the embodiment of the present invention includes a graph convolutional network and a graph attention network. The graph convolutional network is used to output global features, while the graph attention network is used to output positioning features. The two are finally combined, and the global features and positioning features are jointly optimized by feature fusion to obtain more accurate and stable target features at the transmission line level.

[0099] After completing the fusion of global features and positioning features, the computer device obtains the target features of each measuring point. In order to determine which transmission line has a fault, it is necessary to analyze and classify based on the target features, and finally output the identification result of the faulty line. In some embodiments, the computer device can classify by machine learning or deep learning methods, such as threshold methods, traditional machine learning methods (such as support vector machines, random forests, XGBoost, etc.), deep learning methods (such as graph neural networks, etc.) or Bayesian reasoning, etc., based on target features for analysis and classification, and finally output the identification result of the faulty line. For example, the computer device can linearly transform the target features through a graph neural network to output the probability that the corresponding transmission line is a faulty line, and then determine whether the transmission line is a faulty line. As a result, power grids of different complexities can automatically identify faulty lines, reduce manual misjudgments, and improve system efficiency.

[0100] In the above embodiment, the proportion of global features and positioning features is adjusted by the fusion coefficient to ensure adaptability in different scenarios, improve the flexibility of fault identification, and improve the fault identification capability at the single measuring point level; by adjusting the features at the transmission line level, it is ensured that the information of the fault propagation path is fully modeled, so that the target features are more in line with the actual fault propagation mode.

[0101] In some embodiments, taking the traveling wave measurement points at both ends of the fault line as the starting point, multiple ranging lines associated with the fault line are determined, including: taking the traveling wave measurement points at both ends of the fault line as candidate traveling wave measurement points, and determining the adjacent measurement points of the candidate traveling wave measurement points; based on the candidate traveling wave measurement points and their adjacent measurement points, multiple ranging lines associated with the fault line are formed.

[0102] After determining one or more faulty lines, for each faulty line, the computer equipment finds the traveling wave measurement points at both ends of the line. The traveling wave measurement points at both ends of the faulty line are key nodes for the propagation of traveling wave signals, which can be used to measure the arrival time of the traveling wave and locate the fault. Since traveling wave signals propagate along multiple paths in the transmission line, there may be errors in ranging using only the traveling wave measurement points at both ends, so it is necessary to expand to more measurement points. To this end, the computer equipment searches for adjacent traveling wave measurement points based on the traveling wave measurement points at both ends of the faulty line to form a wider ranging path, thereby expanding the range of the ranging path by increasing the adjacent measurement points and improving the reliability of the ranging data.

[0103] Furthermore, the computer equipment takes the traveling wave measurement points at both ends of the fault line and the adjacent measurement points of each traveling wave measurement point as the core, traverses all feasible traveling wave transmission routes, forms multiple ranging paths, so as to calculate the fault distance on multiple paths and perform fusion optimization.

[0104] For example, Figure 6 As shown, the computer equipment determines multiple distance measurement lines based on the traveling wave measurement points b and c at both ends of the fault line: W ab , W bc , W cd , W cf and W eb , where traveling wave measurement point a and traveling wave measurement point e are the first-order adjacent measurement points of traveling wave measurement point b, and traveling wave measurement point d and traveling wave measurement point f are the first-order adjacent measurement points of traveling wave measurement point c.

[0105] In the above embodiments, the ranging path range is expanded to enhance the redundancy of the system and improve the ranging stability; the use of multi-link fusion ranging can reduce the ranging error and improve the final ranging accuracy.

[0106] If the signal of a certain ranging line is affected by interference or noise, it may cause deviation in the ranging result. The fault location may be located at the intersection of multiple ranging paths, and how to integrate multiple ranging results is a key issue. To this end, in some embodiments, the fault location is located in multiple ranging lines, including: determining the initial distance between the fault location and the traveling wave measurement points at both ends of each ranging line respectively; determining the path weight between the traveling wave measurement points at both ends of the fault line; based on the path weight, weighted fusion is performed on the distance between the fault location and the traveling wave measurement points at both ends of all ranging lines to obtain the target distance between the fault location and the reference measurement point; the reference measurement point includes the traveling wave measurement points at both ends of the fault line.

[0107] Specifically, on each ranging line, the computer equipment uses the traveling wave time difference ranging method to calculate the initial distance from the fault point to the measuring points at both ends of the line. For example, the computer equipment can calculate the initial distance on the ranging line of the traveling wave measuring point a and the traveling wave measuring point d by the following formula: (12) Where c is the speed of the traveling wave mode, is the electrical distance between point a and point d.

[0108] This calculation can be done for each distance measurement line. For example, for multiple distance measurement lines: W ab , W bc , W cd , W cf and W eb , the initial distances are: D ab , D bc , D cd , D cf and D eb Therefore, the initial distances from the fault point to different measuring points are calculated through multiple ranging lines, and multiple independent ranging results are obtained to improve the ranging robustness.

[0109] However, the ranging results of different ranging paths may have errors, so it is necessary to calculate path weights to measure the importance of different paths. The path weights can be calculated based on factors such as ranging signal quality, ranging path length, and historical data credibility (for example, if a path has a smaller error in historical ranging, it is given a higher weight).

[0110] In some embodiments, the path weight between the traveling wave measurement points is the attention weight between the traveling wave measurement points. In this way, the path weight has the ability to be adaptively adjusted, which can significantly improve the ranging accuracy and reliability. Especially in multi-T network and ring network structure, the traveling wave signal may propagate along multiple paths, resulting in non-unique ranging results. The attention weight calculated in the above steps can automatically select the optimal path and reduce the ranging error.

[0111] Exemplarily, the computer device performs weighted fusion of each initial distance based on the attention weight to obtain the target distance, which can be expressed as: (13) Finally, the computer equipment can fuse all the distance measurement results through the weighted average method to calculate the target distance from the final fault point to a reference measurement point. The reference measurement point can be the traveling wave measurement points at both ends of the fault line, or other traveling wave measurement points. Therefore, it is usually necessary to combine the physical parameters and geographic information of the power grid to convert the target distance into a physical distance, so as to locate the fault location in the actual transmission network and perform subsequent operations such as maintenance.

[0112] In the above embodiment, the use of path weights can improve the contribution of high-quality ranging paths, reduce the impact of low-quality ranging paths on the final result, and reduce single path errors by weighted fusion of results of different ranging lines, thereby improving the stability and accuracy of the final ranging.

[0113] In order to more accurately model the traveling wave propagation law, based on any of the above embodiments or a combination thereof, the wide-area traveling wave topology of the transmission network is determined, including: based on the structural information in the transmission network, constructing a graph data model with traveling wave measurement points as nodes and transmission lines as edges; based on at least one of the electrical distance, impedance characteristics or historical traveling wave propagation data of the transmission line, weighted processing is performed on the topological connection relationship in the graph data model to obtain the wide-area traveling wave topology of the transmission network.

[0114] Specifically, the computer equipment constructs a graph data model of the transmission network with traveling wave measurement points as nodes and transmission lines as edges. Each traveling wave measurement point collects traveling wave signals and builds adjacency relationships based on the connection relationships of the transmission lines. The formed graph structure represents the topology of the transmission network and can be used for fault propagation analysis.

[0115] In addition, the propagation characteristics of the traveling wave signal of the transmission line are not only determined by the physical connection relationship, but also affected by the electrical characteristics and historical traveling wave propagation data. The electrical characteristics include but are not limited to at least one of electrical distance and impedance characteristics.

[0116] The electrical distance refers to the equivalent physical length corresponding to the propagation of the traveling wave signal in the transmission line, which is related to the length, material, structure and electromagnetic characteristics of the transmission line. The shorter the electrical distance, the faster the traveling wave signal propagates, the smaller the attenuation, and the higher the signal correlation between the measuring points. The longer the electrical distance, the longer the signal propagation time, which may cause multiple reflections and attenuation, and reduce the ranging accuracy.

[0117] Impedance characteristics refer to the degree of obstruction of the transmission line to the propagation of traveling wave signals. The greater the impedance, the greater the traveling wave propagation loss, the more obvious the signal attenuation, and the higher the difficulty of fault location. The smaller the impedance, the more stable the traveling wave signal propagation, and the higher the signal correlation between the measurement points.

[0118] Historical traveling wave propagation data refers to the record of the propagation characteristics of traveling wave signals between different measuring points during the long-term operation of the transmission network. For example, computer equipment can calculate the correlation between measuring points by counting the arrival time, amplitude, frequency, attenuation, etc. of the past traveling wave signals. If the traveling wave propagation patterns of two measuring points remain consistent for a long time, it means that they are closely connected in the traveling wave propagation path, and they can be given a higher weight in the weighted topology. If the historical traveling wave propagation data of two measuring points have low similarity, it means that their traveling wave correlation is low and the weight should be reduced.

[0119] Therefore, the computer device can determine the weight coefficients corresponding to the electrical distance, impedance characteristics or historical traveling wave propagation data, etc., respectively, and perform weighted processing on the topological connection relationship in the graph data model to obtain the wide-area traveling wave topology of the transmission network. The weight coefficient can be, for example, a preset value.

[0120] In the above embodiment, the connection relationship between transmission lines is clarified through the graph data model, providing a data basis for the analysis of the traveling wave propagation path, which is particularly suitable for complex power grid topologies such as multi-T connections, and can improve the adaptability of fault detection. In addition, by weighting the topological connection relationship, the graph data model can more accurately reflect the characteristics of traveling wave propagation, enhance the physical authenticity of the topological model, and thus improve the accuracy of fault detection.

[0121] The present invention proposes a transmission network fault location method based on a graph recognition network (i.e., graph convolutional attention network, L-CAT), which uses wide-area traveling wave information and graph neural network technology to improve the accuracy and robustness of fault detection. The method includes core links such as traveling wave signal preprocessing, wide-area traveling wave graph data construction, fault line identification, multi-link ranging fusion and fault point location. In the traveling wave signal preprocessing stage, the variational mode decomposition algorithm is used to decompose the traveling wave signal, highlight the transient characteristics of the traveling wave head, and filter out the baseband signal and noise interference, so that the local mutation of the signal is clearer and more identifiable, which improves the efficiency and accuracy of subsequent processing. Compared with traditional signal processing methods, variational mode decomposition has higher adaptability and denoising ability, and is particularly suitable for complex multi-T-connected transmission line fault location. The extracted traveling wave features are normalized by "maximum-minimum value" to obtain standardized node features, thereby improving the generalization ability and positioning accuracy of the model.

[0122] In terms of wide-area traveling wave graph data construction, the present invention constructs a wide-area traveling wave graph data structure, with traveling wave measurement points as nodes and transmission lines as edges, and uses electrical distance, impedance characteristics or historical traveling wave propagation data to weight the topological relationship to make it more consistent with the law of traveling wave propagation. The graph convolutional network is used to aggregate the features near the nodes to achieve effective modeling of the topological structure of the transmission network; the graph attention network adaptively calculates the adjacency weights between measurement points, highlights important traveling wave transmission paths, and improves the accuracy of fault location.

[0123] In the fault line identification link, the graph recognition network combines the global feature extraction capability of the graph convolution network and the local attention mechanism of the graph attention network to achieve accurate identification of the fault line by mining the wide-area traveling wave features and learning the nonlinear relationship between multiple measuring points and the fault line. The graph recognition network adopts an adaptive weight adjustment mechanism to interpolate between the graph convolution network and the graph attention network through two scalar parameters to generate a more robust model, better adapt to the changes in traveling wave features at different fault locations, and improve the robustness and accuracy of fault location.

[0124] In terms of fault point distance measurement, a multi-link distance measurement fusion method is adopted to select the double-end measurement points of the fault line and its first-order adjacent measurement points to form multiple distance measurement links, and the distance measurement results are weighted averaged using the weights output by the graph recognition network to improve the accuracy of fault distance measurement. The fault point location measurement method based on the graph recognition network integrates the distance measurement results of multiple lines crossing the fault, and uses adaptive weights to fuse the distance measurement results to achieve accurate measurement of the fault point.

[0125] Compared with the traditional method, the innovation of the present invention is: 1) The variational mode decomposition algorithm decomposes the traveling wave signal, reduces the signal complexity, and enhances the transient characteristics; 2) Adaptive weight fusion of graph recognition network model, combined with information from multiple measurement points, to achieve accurate fault location; 3) The combination of graph convolutional network and graph attention network can not only aggregate node features, but also highlight key measurement points, thus improving the accuracy of fault identification; 4) Multi-link ranging fusion strategy to improve ranging stability and accuracy under complex topology structures.

[0126] Therefore, the fault location system of the graph recognition network model provided by the present invention covers the arrangement of traveling wave measurement points, graph data construction, model training optimization, fault line identification and fault point calculation, providing a complete solution for the rapid and accurate location of transmission line faults.

[0127] The power transmission network fault locating method provided in the embodiment of the present invention can be executed by a power transmission network fault locating device. In the embodiment of the present invention, the power transmission network fault locating device executing the power transmission network fault locating method is taken as an example to illustrate the power transmission network fault locating device provided in the embodiment of the present invention.

[0128] The embodiment of the present invention also provides a power transmission network fault location device, which is applied to computer equipment. Figure 7 As shown, the transmission network fault location device includes a topology module 701, an identification module 702 and a location module 703. Among them: The topology module 701 is used to determine the wide-area traveling wave topology of the transmission network. The wide-area traveling wave topology uses traveling wave measurement points as nodes and transmission lines as edges. Each traveling wave measurement point corresponds to a traveling wave feature, which is obtained by performing modal decomposition on the traveling wave signal collected by the traveling wave measurement point.

[0129] The identification module 702 is used to identify faults of each transmission line based on the wide area traveling wave topology through a graph recognition network to locate the faulty line.

[0130] The positioning module 703 is used to determine multiple distance measurement lines related to the faulty line with the traveling wave measurement points at both ends of the faulty line as the starting point, and locate the fault position in the multiple distance measurement lines.

[0131] According to the transmission network fault location device provided by the embodiment of the present invention, by constructing a wide-area traveling wave graph data structure, taking the traveling wave measuring points as nodes and the overhead lines as edges, and using the graph data structure to represent the topological relationship of the transmission network, basic data support is provided for fault location; and the wide-area traveling wave topology is taken as input, and a learnable graph recognition network is proposed to mine the wide-area traveling wave characteristics and learn the nonlinear relationship between multiple measuring points and the fault line, so that the fault line identification can be made more accurate, especially in the power grid with a multi-T connection structure, the robustness of the fault line identification is greatly improved; finally, multiple ranging lines are formed based on the double-end measuring points of the fault line, the topological range of the fault location is further narrowed, and a multi-link ranging fusion mechanism is used to locate the fault, so as to avoid the error of a single ranging path and improve the accuracy and stability of ranging.

[0132] In some embodiments, the identification module is also used to determine the adjacent measuring points of each traveling wave measuring point based on the correlation relationship between each traveling wave measuring point in the wide-area traveling wave topology; generate global features based on the traveling wave characteristics of each traveling wave measuring point and its adjacent measuring points; determine the importance of each traveling wave measuring point and its adjacent measuring points, and generate multiple positioning features based on the importance; fuse the global features and the positioning features to generate target features corresponding to each transmission line; perform fault identification on each transmission line based on the target features to obtain a determination result for each transmission line, and locate the faulty line based on the determination result of each transmission line.

[0133] In some embodiments, the identification module is also used to perform multiple aggregation processes on the traveling wave characteristics of any traveling wave measurement point and the traveling wave characteristics of all adjacent measurement points of the traveling wave measurement point to obtain multiple aggregated characteristics; wherein the traveling wave characteristics of the traveling wave measurement point in each aggregation process are obtained based on the aggregated characteristics obtained in the previous aggregation process; and the aggregated characteristics obtained in the last aggregation are used as global characteristics.

[0134] In some embodiments, the identification module is also used to determine, for any traveling wave measurement point, the correlation between the targeted traveling wave measurement point and any adjacent measurement point of the targeted traveling wave measurement point; determine the attention weight between the targeted traveling wave measurement point and any adjacent measurement point of the targeted traveling wave measurement point based on the correlation between the targeted traveling wave measurement point and any adjacent measurement point of the targeted traveling wave measurement point; and aggregate the traveling wave features of all adjacent measurement points based on the attention weight between the targeted traveling wave measurement point and any adjacent measurement point of the targeted traveling wave measurement point to obtain a positioning feature corresponding to the targeted traveling wave measurement point.

[0135] In some embodiments, the identification module is also used to obtain a total correlation based on the sum of the correlations between the targeted traveling wave measurement point and all adjacent measurement points of the targeted traveling wave measurement point; for any adjacent measurement point of the targeted traveling wave measurement point, determine the proportion of the correlation between the targeted traveling wave measurement point and the targeted adjacent measurement point to the total correlation; based on the proportion, obtain the attention weight between the targeted traveling wave measurement point and the targeted adjacent measurement point.

[0136] In some embodiments, the identification module is also used to determine a first fusion coefficient and a second fusion coefficient; based on the first fusion coefficient, the global features and positioning features corresponding to each traveling wave measurement point are feature fused to obtain the initial target features corresponding to each traveling wave measurement point; based on the second fusion coefficient, the initial target features corresponding to each traveling wave measurement point are adjusted to obtain the target features between each traveling wave measurement point and its adjacent measurement points; wherein, any traveling wave measurement point and any adjacent measurement point of any traveling wave measurement point correspond to a transmission line.

[0137] In some embodiments, the positioning module is also used to use the traveling wave measurement points at both ends of the fault line as candidate traveling wave measurement points, and determine the adjacent measurement points of the candidate traveling wave measurement points; based on the candidate traveling wave measurement points and their adjacent measurement points, multiple ranging lines associated with the fault line are formed.

[0138] In some embodiments, the positioning module is also used to respectively determine the initial distance between the fault location and the traveling wave measurement points at both ends of each ranging line; determine the path weight between the traveling wave measurement points at both ends of the fault line; based on the path weight, perform weighted fusion on the distance between the fault location and the traveling wave measurement points at both ends of all ranging lines to obtain the target distance between the fault location and the reference measurement points; the reference measurement points include the traveling wave measurement points at both ends of the fault line.

[0139] In some embodiments, the above-mentioned device also includes a preprocessing module, which is used to respectively obtain the original traveling wave signals collected by each traveling wave measurement point; for any traveling wave measurement point, the original traveling wave signal collected by the traveling wave measurement point is modally decomposed to obtain the multi-dimensional modal components corresponding to the traveling wave measurement point; by setting window parameters, the energy values ​​of the multi-dimensional modal components in multiple windows are determined respectively; based on the energy values ​​of the multi-dimensional modal components in each window, the modal components are subjected to dimensionality reduction processing to obtain the traveling wave characteristics of preset dimensions.

[0140] In some embodiments, the preprocessing module is also used to perform multi-layer decomposition on the original traveling wave signal collected at any traveling wave measurement point to obtain multiple initial modal components; determine the initial center frequency of each initial modal component; and iteratively update each initial modal component and the corresponding initial center frequency multiple times with the constraint that the sum of the multiple initial modal components is equal to the original traveling wave signal until the iteration stop condition is met to obtain the multi-dimensional modal component corresponding to the targeted traveling wave measurement point.

[0141] In some embodiments, the topology module is also used to construct a graph data model with traveling wave measurement points as nodes and transmission lines as edges based on the structural information in the transmission network; based on at least one of the electrical distance, impedance characteristics or historical traveling wave propagation data of the transmission lines, the topological connection relationship in the graph data model is weighted to obtain the wide-area traveling wave topology of the transmission network.

[0142] The transmission network fault location device in the embodiment of the present invention may be a computer device, or a component in the computer device, such as an integrated circuit or a chip. The computer device may be a terminal device or a server. Exemplarily, the computer device may be a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted computer device, a mobile Internet device (Mobile Internet Device, MID), an augmented reality (Augmented Reality, AR) / virtual reality (Virtual Reality, VR) device, a robot, a wearable device, an ultra-mobile personal computer (Ultra-mobile Personal Computer, UMPC), a netbook or a personal digital assistant (Personal Digital Assistant, PDA), etc. It may also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (Personal Computer, PC), a television (Television, TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present invention.

[0143] The power transmission network fault location device in the embodiment of the present invention may be a device having an operating system. The operating system may be a Microsoft (Windows) operating system, an Android (Android) operating system, an IOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present invention.

[0144] The power transmission network fault location device provided by the embodiment of the present invention can realize Figure 1 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0145] In some embodiments, Figure 8 As shown, an embodiment of the present invention further provides a computer device 800, including a processor 801, a memory 802, and a computer program stored in the memory 802 and executable on the processor 801. When the program is executed by the processor 801, each process of the above-mentioned method embodiments is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0146] It should be noted that the computer device in the embodiment of the present invention includes the mobile computer device and the non-mobile computer device mentioned above.

[0147] An embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned power transmission network fault location method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0148] The processor is the processor in the computer device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0149] An embodiment of the present invention further provides a computer program product, including a computer program, which implements the above-mentioned power transmission network fault location method when executed by a processor.

[0150] The processor is the processor in the computer device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0151] An embodiment of the present invention further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned power transmission network fault location method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0152] It should be understood that the chip mentioned in the embodiment of the present invention may also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0153] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article 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, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and device in the embodiment of the present invention is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0154] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the relevant technology, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0155] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

[0156] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0157] If not otherwise specified, all embodiments and optional embodiments of the present invention can be combined with each other to form a new technical solution.

[0158] Unless otherwise specified, all technical features and optional technical features of the present invention can be combined with each other to form a new technical solution.

[0159] If not otherwise specified, all steps of the present invention may be performed sequentially or randomly, preferably sequentially. For example, the method includes steps (a) and (b), which means that the method may include steps (a) and (b) performed sequentially, or may include steps (b) and (a) performed sequentially. For example, mentioning that the method may also include step (c) means that step (c) may be added to the method in any order, for example, the method may include steps (a), (b) and (c), or may include steps (a), (c) and (b), or may include steps (c), (a) and (b), etc.

[0160] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for locating a transmission network fault, characterized in that: The transmission network includes a plurality of transmission lines, and traveling wave measurement points are arranged at both ends of each transmission line; the method includes: Determine a wide-area traveling wave topology of the power transmission network, wherein the wide-area traveling wave topology has the traveling wave measuring points as nodes and the transmission lines as edges, each traveling wave measuring point corresponds to a traveling wave feature, and the traveling wave feature is obtained by performing modal decomposition on traveling wave signals collected by the traveling wave measuring points; Based on the wide-area traveling wave topology, fault identification is performed on each transmission line through a graph recognition network to locate the faulty line; Taking the traveling wave measurement points at both ends of the fault line as starting points, multiple distance measurement lines related to the fault line are determined, and the fault position is located in the multiple distance measurement lines.

2. The method according to claim 1, characterized in that Based on the wide-area traveling wave topology, fault identification is performed on each transmission line through a graph recognition network to locate the faulty line, including: Based on the correlation relationship between each traveling wave measurement point in the wide-area traveling wave topology, adjacent measurement points of each traveling wave measurement point are determined respectively; Generate global features based on the traveling wave features of each traveling wave measuring point and its adjacent measuring points; Determine the importance of each traveling wave measuring point and its adjacent measuring points respectively, and generate a plurality of positioning features based on the importance; Fusion of the global features and the positioning features to generate target features corresponding to each transmission line; Fault identification is performed on each transmission line based on the target feature to obtain a determination result of each transmission line, and the fault line is located based on the determination result of each transmission line.

3. The method according to claim 2, characterized in that The generating of global features based on the respective traveling wave features of each traveling wave measuring point and its adjacent measuring points comprises: For any traveling wave measuring point, the traveling wave characteristics of the traveling wave measuring point and the traveling wave characteristics of all adjacent measuring points of the traveling wave measuring point are aggregated multiple times to obtain multiple aggregated characteristics; wherein the traveling wave characteristics of the traveling wave measuring point in each aggregation process are obtained based on the aggregated characteristics obtained in the previous aggregation process; The aggregated features obtained from the last aggregation are used as global features.

4. The method according to claim 2, characterized in that: The step of respectively determining the importance of each traveling wave measuring point and its adjacent measuring points, and generating a plurality of positioning features based on the importance, includes: For any traveling wave measuring point, determining the correlation between the traveling wave measuring point and any adjacent measuring point of the traveling wave measuring point; Determine an attention weight between the targeted traveling wave measurement point and any adjacent measurement point of the targeted traveling wave measurement point based on a correlation between the targeted traveling wave measurement point and any adjacent measurement point of the targeted traveling wave measurement point; Based on the attention weight between the targeted traveling wave measurement point and any adjacent measurement point of the targeted traveling wave measurement point, the traveling wave features of all adjacent measurement points are aggregated to obtain the positioning feature corresponding to the targeted traveling wave measurement point.

5. The method according to claim 4, characterized in that The step of determining the attention weight between the targeted traveling wave measurement point and any adjacent measurement point of the targeted traveling wave measurement point based on the correlation between the targeted traveling wave measurement point and any adjacent measurement point of the targeted traveling wave measurement point comprises: Based on the sum of the correlations between the targeted traveling wave measurement point and all adjacent measurement points of the targeted traveling wave measurement point, a total correlation is obtained; For any adjacent measuring point of the targeted traveling wave measuring point, determining the proportion of the correlation between the targeted traveling wave measuring point and the targeted adjacent measuring point to the total correlation; Based on the ratio, an attention weight between the targeted traveling wave measurement point and the targeted adjacent measurement point is obtained.

6. The method according to any one of claims 2 to 5, characterized in that The fusing the global feature and the positioning feature to generate a target feature corresponding to each transmission line includes: Determine a first fusion coefficient and a second fusion coefficient; Based on the first fusion coefficient, feature fusion is performed on the global features and positioning features corresponding to each traveling wave measurement point to obtain initial target features corresponding to each traveling wave measurement point; Based on the second fusion coefficient, the initial target features corresponding to each traveling wave measurement point are adjusted to obtain the target features between each traveling wave measurement point and its adjacent measurement points; wherein any traveling wave measurement point and its adjacent measurement point correspond to a transmission line.

7. The method according to claim 1, characterized in that The method of determining a plurality of distance measurement lines associated with the fault line by taking the traveling wave measurement points at both ends of the fault line as starting points comprises: Taking the traveling wave measuring points at both ends of the fault line as candidate traveling wave measuring points, and determining the adjacent measuring points of the candidate traveling wave measuring points; Based on the candidate traveling wave measuring points and their adjacent measuring points, a plurality of ranging lines associated with the faulty line are formed.

8. The method according to claim 1 or 7, characterized in that: The locating the fault position in the plurality of ranging lines comprises: Determine the initial distances between the fault location and the traveling wave measurement points at both ends of each ranging line respectively; Determining the path weights between the traveling wave measuring points at both ends of the fault line; Based on the path weight, the distances between the fault location and the traveling wave measurement points at both ends of all the distance measurement lines are weightedly fused to obtain the target distance between the fault location and the reference measurement points; the reference measurement points include the traveling wave measurement points at both ends of the fault line.

9. The method according to claim 1, characterized in that: The method further comprises: Respectively obtain the original traveling wave signals collected by each traveling wave measuring point; For any traveling wave measuring point, modal decomposition is performed on the original traveling wave signal collected at the traveling wave measuring point to obtain a multi-dimensional modal component corresponding to the traveling wave measuring point; By setting window parameters, energy values ​​of the multidimensional modal components in multiple windows are determined respectively; Based on the energy values ​​of the multidimensional modal components in each window, the modal components are subjected to dimensionality reduction processing to obtain traveling wave features of a preset dimension.

10. The method according to claim 9, characterized in that For any traveling wave measuring point, modal decomposition is performed on the original traveling wave signal collected at the traveling wave measuring point to obtain a multi-dimensional modal component corresponding to the traveling wave measuring point, including: For any traveling wave measuring point, the original traveling wave signal collected at the traveling wave measuring point is subjected to multi-layer decomposition to obtain multiple initial modal components; Determine the initial center frequency of each initial modal component; Taking the sum of the multiple initial modal components equal to the original traveling wave signal as a constraint condition, each initial modal component and the corresponding initial center frequency are iteratively updated multiple times until the iteration stop condition is met, thereby obtaining a multidimensional modal component corresponding to the targeted traveling wave measurement point.

11. The method according to claim 1 or 9, characterized in that: The determining of the wide-area traveling wave topology of the transmission network comprises: Based on the structural information in the transmission network, a graph data model is constructed with traveling wave measurement points as nodes and transmission lines as edges; Based on at least one of the electrical distance, impedance characteristics or historical traveling wave propagation data of the transmission line, the topological connection relationship in the graph data model is weighted to obtain the wide-area traveling wave topology of the transmission network.

12. A transmission network fault location device, characterized in that: The transmission network includes a plurality of transmission lines, and traveling wave measuring points are arranged at both ends of each transmission line; the device includes: A topology module, used for determining a wide-area traveling wave topology of a power transmission network, wherein the wide-area traveling wave topology has the traveling wave measuring points as nodes and the transmission lines as edges, each traveling wave measuring point corresponding to a traveling wave feature, and the traveling wave feature is obtained by performing modal decomposition on traveling wave signals collected by the traveling wave measuring points; An identification module, used to identify faults of each transmission line through a graph recognition network based on the wide area traveling wave topology and locate the faulty line; The positioning module is used to determine a plurality of distance measurement lines related to the fault line with the traveling wave measurement points at both ends of the fault line as the starting point, and locate the fault position in the plurality of distance measurement lines.

13. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for locating a fault in a power transmission network according to any one of claims 1 to 11 is implemented.

14. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for locating a fault in a power transmission network according to any one of claims 1 to 11 is implemented.

15. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for locating a fault in a power transmission network according to any one of claims 1 to 11 is implemented.

16. A chip, characterized in that: The chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the power transmission network fault location method according to any one of claims 1-11.

Images