Power distribution network fault positioning method, system and device and storage medium

Abstract

The invention discloses a power distribution network fault positioning method, system and device, and a storage medium, and is applied to the technical field of fault positioning, and the method comprises the steps: determining the topological architecture of a target power distribution network; acquiring an initial node and an initial traveling wave signal based on the topological architecture; in response to a fault signal of the target power distribution network, determining a fault area of the target power distribution network and each target node directly adjacent to the fault area, and determining a traveling wave propagation path between each target node and the fault area; performing wave head calibration correction processing on the initial traveling wave signal to obtain a corrected traveling wave signal; performing feature extraction on the corrected traveling wave signal to obtain a time domain waveform and a frequency domain feature of the corrected traveling wave signal; and inputting the time domain waveform, the frequency domain characteristic and the traveling wave propagation path into a fault positioning model to obtain a fault positioning position of the target power distribution network. According to the method provided by the embodiment of the invention, the fault position of the power distribution network can be quickly and accurately positioned, so that stable operation of the power distribution network and power utilization quality of users are guaranteed.

Description

Technical Field

[0001] This invention relates to the field of fault location technology, and in particular to a method, system, device and storage medium for fault location in power distribution networks. Background Art

[0002] The power distribution network is a crucial component of the power system. As the final link in power transmission and distribution, the distribution network directly serves users, and its operational stability and reliability directly affect the quality of electricity for users and the stable development of the economy.

[0003] In the current routine emergency repair work of distribution network faults, since the exact location of the fault point cannot be given, line inspection personnel need to manually check all the lines in the fault section one by one. This will result in a long time to locate the fault point, which is not conducive to the emergency repair work.

[0004] Therefore, how to quickly and accurately locate the fault location in the power distribution network has become a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] This invention provides a method, system, device, and storage medium for locating faults in power distribution networks, in order to solve the problem that the exact location of the fault point cannot be given in the current emergency repair work of power distribution networks, so as to achieve rapid and accurate location of faults in power distribution networks.

[0006] To address the aforementioned technical problems, embodiments of the present invention provide a method for locating faults in a power distribution network, the method comprising: Obtain the geographical location and connection relationship of the power distribution equipment in the target power distribution network, analyze the geographical location and connection relationship of the power distribution equipment, and determine the current topology of the target power distribution network; Based on the aforementioned topology, the initial traveling wave signals of the initial node and any adjacent initial nodes are obtained. In response to a fault signal in the target distribution network, the fault area of ​​the target distribution network and each target node directly adjacent to the fault area are determined, and based on the fault area of ​​the target distribution network and each target node directly adjacent to the fault area, the traveling wave propagation path between each target node and the fault area is determined. The initial traveling wave signal is subjected to wavefront calibration correction processing to obtain a corrected traveling wave signal; Feature extraction is performed on the modified traveling wave signal to obtain its time-domain waveform and frequency-domain features. The time-domain waveform, the frequency-domain characteristics, and the traveling wave propagation path are input into the constructed fault location model to obtain the fault location of the target distribution network.

[0007] As one preferred embodiment, obtaining the initial traveling wave signal between the initial node and any adjacent initial nodes based on the topology includes: The topology is identified using breadth-first search to obtain the initial nodes of the target distribution network; The electrical parameters of the lines between any two adjacent initial nodes are calculated to obtain the initial traveling wave signal.

[0008] As one preferred embodiment, determining the traveling wave propagation path between each target node and the fault area based on the fault area of ​​the target distribution network and each target node directly adjacent to the fault area includes: The fault area is used as the starting point for path search; The improved Dijkstra algorithm is used to process the topology to obtain several traveling wave propagation paths between the target node and the fault region.

[0009] As one preferred embodiment, the step of correcting the initial traveling wave signal to obtain a corrected traveling wave signal includes: The initial traveling wave signal is subjected to soft thresholding and adaptive filtering in sequence to obtain a noise-suppressed traveling wave signal; The modified traveling wave signal is obtained by performing wavefront calibration on the noise-suppressed traveling wave signal using the Tigger energy operator.

[0010] As one preferred embodiment, the step of extracting features from the modified traveling wave signal to obtain the time-domain waveform and frequency-domain features of the modified traveling wave signal includes: The arrival time of the traveling wave front of the modified traveling wave signal is obtained by monitoring the modified traveling wave signal using the threshold method. Based on the arrival time of the traveling wave front and the obtained signal amplitude of the modified traveling wave signal, the time-domain waveform of the modified traveling wave signal is obtained; The modified traveling wave signal is subjected to frequency domain framing processing using short-time Fourier transform to obtain the frequency domain characteristics of the modified traveling wave signal.

[0011] As one preferred embodiment, the step of inputting the time-domain waveform, the frequency-domain characteristics, and the traveling wave propagation path into the constructed fault location model to obtain the fault location of the target distribution network includes: The time-domain waveform and the frequency-domain features are input into a fault location model constructed using a deep learning network to obtain the fault feature waveform; Based on the fault characteristic waveform and the traveling wave propagation path, the fault location is determined.

[0012] As a preferred embodiment, after obtaining the fault location of the target distribution network, the distribution network fault location method further includes: Obtain the target fault point of the current fault signal; The actual path distance along the route between the fault location and the target fault point is input into the fault location model to optimize the fault location model.

[0013] Another embodiment of the present invention provides a power distribution network fault location system, comprising: The first acquisition module is used to acquire the geographical location and connection relationship of the power distribution equipment in the target power distribution network, analyze the geographical location and connection relationship of the power distribution equipment, and determine the current topology of the target power distribution network. The second acquisition module is used to acquire the initial traveling wave signal between the initial node and any adjacent initial nodes based on the topology. The determination module is configured to, in response to a fault signal of the target distribution network, determine the fault area of ​​the target distribution network and each target node directly adjacent to the fault area, and, based on the fault area of ​​the target distribution network and each target node directly adjacent to the fault area, determine the traveling wave propagation path between each target node and the fault area. The correction module is used to perform wavefront calibration correction processing on the initial traveling wave signal to obtain a corrected traveling wave signal; The extraction module is used to extract features from the modified traveling wave signal to obtain the time-domain waveform and frequency-domain features of the modified traveling wave signal. The positioning module is used to input the time-domain waveform, the frequency-domain characteristics, and the traveling wave propagation path into the constructed fault location model to obtain the fault location of the target distribution network.

[0014] Another embodiment of the present invention provides a power distribution network fault location device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the power distribution network fault location method as described above.

[0015] In another embodiment of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, wherein when the device containing the computer-readable storage medium executes the computer program, the power distribution network fault location method described above is implemented.

[0016] Compared with the prior art, the beneficial effects of the embodiments of the present invention are at least one of the following: This invention obtains the geographical location and connection relationship of power distribution equipment in a target power distribution network, analyzes the geographical location and connection relationship of the power distribution equipment, and determines the current topology of the target power distribution network; based on the topology, it obtains initial traveling wave signals between initial nodes and any adjacent initial nodes; in response to a fault signal in the target power distribution network, it determines the fault region of the target power distribution network and each target node directly adjacent to the fault region, and based on the fault region and each target node directly adjacent to the fault region, it determines the traveling wave propagation path between each target node and the fault region; it performs wavefront calibration correction processing on the initial traveling wave signal to obtain a corrected traveling wave signal; it extracts features from the corrected traveling wave signal to obtain the time-domain waveform and frequency-domain features of the corrected traveling wave signal; and it inputs the time-domain waveform, the frequency-domain features, and the traveling wave propagation path into a constructed fault location model to obtain the fault location of the target power distribution network.

[0017] Compared with existing technologies, this invention establishes the topology of the distribution network, acquires initial traveling wave signals based on the topology, and ensures effective capture of traveling waves during faults. Based on the determined fault area and each target node directly adjacent to the fault area, it dynamically generates traveling wave propagation paths, adapting to the complex branch structure of the distribution network. Through signal correction and feature engineering, it reduces the impact of noise on location. The model only requires fine-tuning of parameters and can be transferred to distribution networks with different topologies. This invention achieves accurate fault location in distribution networks through a closed-loop process of "physical topology analysis - signal optimization - feature learning - model application." Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating a power distribution network fault location method in one embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of a power distribution network fault location system in one embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a power distribution network fault location device in one embodiment of the present invention.

[0019] Figure label: Among them, 11, first acquisition module; 12, second acquisition module; 13, determination module; 14, correction module; 15, extraction module; 16, positioning module; 21, processor; 22, memory. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0021] In the description of this invention, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined with "first," "second," "third," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0022] In the description of this invention, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to communication within two components. The terms "vertical," "horizontal," "left," "right," "upper," "lower," and similar expressions used herein are for illustrative purposes only and do not indicate or imply that the device or component referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as limiting the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0023] In the description of this invention, it should be noted that, unless otherwise defined, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this specification is for the purpose of describing specific embodiments only and is not intended to limit the invention. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0024] One embodiment of the present invention provides a method for locating faults in a distribution network. For details, please refer to [link to relevant documentation]. Figure 1 , Figure 1 The diagram shown is a flowchart illustrating a power distribution network fault location method according to one embodiment of the present invention. The method includes: S1: Obtain the geographical location and connection relationship of the power distribution equipment in the target power distribution network, analyze the geographical location and connection relationship of the power distribution equipment, and determine the current topology of the target power distribution network; S2: Based on the topology, obtain the initial traveling wave signal between the initial node and any adjacent initial nodes; S3: In response to the fault signal of the target distribution network, determine the fault area of ​​the target distribution network and each target node directly adjacent to the fault area, and based on the fault area of ​​the target distribution network and each target node directly adjacent to the fault area, determine the traveling wave propagation path between each target node and the fault area. S4: Perform wavefront calibration correction processing on the initial traveling wave signal to obtain a corrected traveling wave signal; S5: Perform feature extraction on the modified traveling wave signal to obtain the time-domain waveform and frequency-domain features of the modified traveling wave signal; S6: Input the time-domain waveform, the frequency-domain characteristics, and the traveling wave propagation path into the constructed fault location model to obtain the fault location of the target distribution network.

[0025] Specifically, in step S1, the geographical coordinates and physical connection relationships of the power distribution equipment are obtained through a Geographic Information System (GIS), equipment ledger, or Supervisory Control and Data Acquisition (SCADA) system. The power distribution equipment includes at least transformers, circuit breakers, switches, and feeders.

[0026] Among them, the SCADA system focuses on monitoring real-time dynamic data, while the GIS system focuses on analyzing static geographic information.

[0027] Graph theory algorithms are used to construct node-edge models, forming a complete power grid topology graph, and determining the topology of the current target distribution network.

[0028] In step S2, the initial traveling wave signal between the initial node and any adjacent initial node is obtained based on the topology, including: identifying the topology using breadth-first search to obtain the initial node of the target distribution network; and calculating the electrical parameters of the lines between any adjacent initial nodes to obtain the initial traveling wave signal.

[0029] Specifically, the process begins with the power source point of the distribution network, serving as the initial node for breadth-first search (BFS) traversal. Preferably, the power source point includes at least substations and the starting point of main feeders. All adjacent nodes of the current power source point are then visited, such as connected distribution transformers and switchgear.

[0030] Key nodes are selected as initial nodes according to preset rules, and preferably, all primary power distribution nodes are selected as initial nodes.

[0031] Electrical parameters of the lines between adjacent initial nodes are calculated. Specifically, basic data such as line length, conductor material, and cross-sectional area are obtained, and the resistance, inductance, and capacitance per unit length are calculated to establish a distributed parameter model. By establishing the distributed parameter model, accurate electrical parameters can be provided for traveling wave propagation. The electrical parameters are simulated through electromagnetic transient simulation to obtain the traveling wave signal between adjacent nodes.

[0032] Preferably, the distributed parameter model is the Bergeron model.

[0033] Preferably, traveling wave sensors, such as high-frequency current transformers, can also be deployed in the power grid to collect traveling wave signals during normal operation.

[0034] In this process, the initial nodes are systematically identified through breadth-first search (BFS), and combined with electrical parameter calculation and traveling wave signal acquisition, a reliable topology and signal benchmark is provided for distribution network fault location, ensuring full coverage and accurate modeling of key nodes, and laying a data foundation for subsequent fault detection and location.

[0035] In step S3, in response to the fault signal of the target distribution network, the fault area of ​​the target distribution network and each target node directly adjacent to the fault area are determined.

[0036] When an abnormal electrical quantity is detected, a fault alarm is triggered. Preferably, the abnormal electrical quantity includes at least a sudden increase in current amplitude, voltage distortion, and a sudden appearance of a traveling wave signal.

[0037] The fault area here is mainly determined based on the power outage area.

[0038] Starting from the initially identified fault area boundary, based on the distribution network topology, all nodes directly electrically connected to this area are extracted from the initial nodes, i.e., target nodes. Target nodes include at least adjacent nodes near the power source side, adjacent nodes near the load side, and opposite nodes in parallel lines.

[0039] Based on the fault area of ​​the target distribution network and each target node directly adjacent to the fault area, the traveling wave propagation path between each target node and the fault area is determined. Specifically, the fault area is used as the starting point for path search. The improved Dijkstra algorithm is used to process the topology to obtain several traveling wave propagation paths between the target node and the fault area.

[0040] Specifically, based on the shortest path algorithm in graph theory, the shortest electrical path to the fault region is calculated starting from each target node. Here, the preferred shortest path algorithm is the improved Dijkstra algorithm.

[0041] It should be noted that for structures with loops, the K-shortest path algorithm is used to enumerate all possible paths to avoid missing any.

[0042] Specifically, the K-shortest path algorithm is used in complex multi-path networks (such as power distribution networks and transportation networks) to enumerate all possible shortest paths, overcoming the limitation of traditional shortest path algorithms that can only output a single path.

[0043] After obtaining the propagation path, the initial traveling wave waveforms between adjacent nodes under normal conditions can be retrieved and compared with the fault signal to verify whether the waveform distortion of the path is consistent. Alternatively, the fault location can be solved by using the arrival time difference of the traveling waves of multiple target nodes through overdetermined equations, thereby inferring the rationality of the path.

[0044] In step S4, the initial traveling wave signal is subjected to wavefront calibration correction processing to obtain a corrected traveling wave signal. Specifically, the initial traveling wave signal is subjected to soft thresholding and adaptive filtering processing in sequence to obtain a noise-suppressed traveling wave signal; the noise-suppressed traveling wave signal is subjected to wavefront calibration processing using the Tigger energy operator to obtain the corrected traveling wave signal.

[0045] Specifically, the initial traveling wave signal is decomposed into wavelet coefficients at multiple scales to obtain wavelet coefficients for different frequency sub-bands. A soft threshold is determined based on the statistical characteristics of noise. The soft threshold function is applied to the high-frequency detail coefficients while keeping the low-frequency approximation coefficients unchanged. The signal is then reconstructed using the corrected coefficients to obtain the initially denoised traveling wave signal.

[0046] In this process, by suppressing noise components in wavelet coefficients and preserving signal abrupt changes such as wavefronts, soft thresholding avoids the truncation effect of hard thresholding and reduces signal distortion.

[0047] Specifically, an adaptive filter is constructed using the normalized least mean square algorithm. The traveling wave signal after soft thresholding is input into the adaptive filter to obtain a noise estimate. The noise estimate is then removed from the traveling wave signal after soft thresholding to obtain a noise-suppressed traveling wave signal.

[0048] By applying the Tigger energy operator point by point to the noise-suppressed traveling wave signal, the local maxima of the energy sequence are found. The signal corresponding to the arrival time of the traveling wave front is the corrected traveling wave signal.

[0049] Among them, the Tigger energy operator can efficiently capture nonlinear transient features in signals and is more sensitive to local transients.

[0050] In step S5, feature extraction is performed on the modified traveling wave signal to obtain its time-domain waveform and frequency-domain features. This includes monitoring the modified traveling wave signal using a threshold method to obtain the arrival time of the traveling wave front; obtaining the time-domain waveform of the modified traveling wave signal based on the arrival time of the traveling wave front and the obtained signal amplitude of the modified traveling wave signal; and performing frequency-domain framing processing on the modified traveling wave signal using short-time Fourier transform to obtain its frequency-domain features.

[0051] Specifically, based on the statistical characteristics of the modified traveling wave signal, such as the mean and standard deviation of the signal amplitude, a dynamic threshold is set, and then a sliding time window is used to traverse the signal. When the signal amplitude exceeds the dynamic threshold, the arrival time of the traveling wave front of the modified traveling wave signal is obtained.

[0052] Centered on the arrival time of the traveling wave front, a time domain signal segment of fixed duration is extracted. Preferably, the fixed duration is from 1 millisecond before the arrival time of the traveling wave front to 5 milliseconds after the arrival time of the traveling wave front.

[0053] By performing amplitude normalization on a time-domain signal segment of a fixed duration to eliminate the influence of sensor range differences, the signal amplitude during this period can be obtained, thus correcting the time-domain waveform of the traveling wave signal.

[0054] Among them, the degree of amplitude attenuation reflects the distance of the fault; the greater the attenuation, the farther the distance.

[0055] The modified traveling wave signal is divided into short time frames, and a window is applied to each frame of data. The window can be a Hamming window or a Gaussian window to suppress spectral leakage.

[0056] Among them, the Hamming window and the Gaussian window are two commonly used window functions in signal processing, mainly used to truncate signals to reduce spectral leakage.

[0057] The short-time Fourier transform is used to perform a Fourier transform on each frame of signal to obtain a time-frequency matrix. Frequency domain features are extracted from the time-frequency matrix, including at least the dominant frequency component, harmonic distribution, and frequency band energy ratio.

[0058] The fault location of the target distribution network is obtained by inputting the time-domain waveform, the frequency-domain features, and the traveling wave propagation path into the constructed fault location model. This includes inputting the time-domain waveform and the frequency-domain features into the fault location model constructed using a deep learning network to obtain the fault feature waveform; and determining the fault location based on the fault feature waveform and the traveling wave propagation path.

[0059] In this process, by inputting the time-domain waveform and the frequency-domain features into a deep learning network, multimodal fault features are extracted, and then combined with the physical constraints of the traveling wave propagation path, a high-precision mapping from data to location is achieved.

[0060] After obtaining the fault location of the target distribution network, the distribution network fault location method further includes: obtaining the target fault point of the current fault signal; inputting the actual path distance along the line between the fault location and the target fault point into the fault location model, and optimizing the fault location model.

[0061] One embodiment of the present invention provides a distribution network fault location system. For details, please refer to [link / reference]. Figure 2 , Figure 2 The diagram shown illustrates the structure of a power distribution network fault location system according to one embodiment of the present invention. The system includes: The first acquisition module 11 is used to acquire the geographical location and connection relationship of the power distribution equipment in the target power distribution network, analyze the geographical location and connection relationship of the power distribution equipment, and determine the current topology of the target power distribution network. The second acquisition module 12 is used to acquire the initial traveling wave signal between the initial node and any adjacent initial nodes based on the topology. The determination module 13 is used to determine the fault area of ​​the target distribution network and each target node directly adjacent to the fault area in response to the fault signal of the target distribution network, and to determine the traveling wave propagation path between each target node and the fault area based on the fault area of ​​the target distribution network and each target node directly adjacent to the fault area. Correction module 14 is used to perform wavefront calibration correction processing on the initial traveling wave signal to obtain a corrected traveling wave signal; Extraction module 15 is used to extract features from the modified traveling wave signal to obtain the time-domain waveform and frequency-domain features of the modified traveling wave signal; The positioning module 16 is used to input the time-domain waveform, the frequency-domain characteristics and the traveling wave propagation path into the constructed fault location model to obtain the fault location of the target distribution network.

[0062] See Figure 3 This is a schematic diagram of the structure of a power distribution network fault location device provided in an embodiment of the present invention. The power distribution network fault location device 20 provided in this embodiment includes a processor 21, a memory 22, and a computer program stored in the memory 22 and configured to be executed by the processor 21. When the processor 21 executes the computer program, it implements the steps as described in the above embodiment of the power distribution network fault location method, for example... Figure 1The steps S1 to S6 described above; or, when the processor 21 executes the computer program, it implements the functions of each module in the above-described device embodiments, such as the first acquisition module 11.

[0063] For example, the computer program can be divided into one or more modules, which are stored in the memory 22 and executed by the processor 21 to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the power grid fault location device 20. For example, the computer program can be divided into a first acquisition module 11, a second acquisition module 12, a determination module 13, etc., with the specific functions of each module as follows: The first acquisition module 11 is used to acquire the geographical location and connection relationship of the power distribution equipment in the target power distribution network, analyze the geographical location and connection relationship of the power distribution equipment, and determine the current topology of the target power distribution network. The second acquisition module 12 is used to acquire the initial traveling wave signal between the initial node and any adjacent initial nodes based on the topology. The determination module 13 is used to determine the fault area of ​​the target distribution network and each target node directly adjacent to the fault area in response to the fault signal of the target distribution network, and to determine the traveling wave propagation path between each target node and the fault area based on the fault area of ​​the target distribution network and each target node directly adjacent to the fault area. Correction module 14 is used to perform wavefront calibration correction processing on the initial traveling wave signal to obtain a corrected traveling wave signal; Extraction module 15 is used to extract features from the modified traveling wave signal to obtain the time-domain waveform and frequency-domain features of the modified traveling wave signal; The positioning module 16 is used to input the time-domain waveform, the frequency-domain characteristics and the traveling wave propagation path into the constructed fault location model to obtain the fault location of the target distribution network.

[0064] The power distribution network fault location device 20 may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will understand that the schematic diagram is merely an example of a power distribution network fault location device and does not constitute a limitation on the power distribution network fault location device 20. It may include more or fewer components than shown in the diagram, or combine certain components, or use different components. For example, the power distribution network fault location device 20 may also include input / output devices, network access devices, buses, etc.

[0065] The processor 21 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor 21 is the control center of the power distribution network fault location device 20, connecting various parts of the device through various interfaces and lines.

[0066] The memory 22 can be used to store the computer programs and / or modules. The processor 21 implements various functions of the power distribution network fault location device 20 by running or executing the computer programs and / or modules stored in the memory 22 and calling the data stored in the memory 22. The memory 22 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 22 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0067] If the integrated module of the power distribution network fault location device 20 is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0068] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0069] Accordingly, embodiments of the present invention provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform steps in the power distribution network fault location method of the above embodiments, for example... Figure 1 Steps S1 to S6 as described above.

[0070] Compared with the prior art, the beneficial effects of the embodiments of the present invention are at least one of the following: This invention obtains the geographical location and connection relationship of power distribution equipment in a target power distribution network, analyzes the geographical location and connection relationship of the power distribution equipment, and determines the current topology of the target power distribution network; based on the topology, it obtains initial traveling wave signals between initial nodes and any adjacent initial nodes; in response to a fault signal in the target power distribution network, it determines the fault region of the target power distribution network and each target node directly adjacent to the fault region, and based on the fault region and each target node directly adjacent to the fault region, it determines the traveling wave propagation path between each target node and the fault region; it performs wavefront calibration correction processing on the initial traveling wave signal to obtain a corrected traveling wave signal; it extracts features from the corrected traveling wave signal to obtain the time-domain waveform and frequency-domain features of the corrected traveling wave signal; and it inputs the time-domain waveform, the frequency-domain features, and the traveling wave propagation path into a constructed fault location model to obtain the fault location of the target power distribution network.

[0071] Compared with existing technologies, this invention establishes the topology of the distribution network, acquires initial traveling wave signals based on the topology, and ensures effective capture of traveling waves during faults. Based on the determined fault area and each target node directly adjacent to the fault area, it dynamically generates traveling wave propagation paths, adapting to the complex branch structure of the distribution network. Through signal correction and feature engineering, it reduces the impact of noise on location. The model only requires fine-tuning of parameters and can be transferred to distribution networks with different topologies. This invention achieves accurate fault location in distribution networks through a closed-loop process of "physical topology analysis - signal optimization - feature learning - model application."

[0072] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A method for locating faults in a power distribution network, characterized in that, include: Obtain the geographical location and connection relationship of the power distribution equipment in the target power distribution network, analyze the geographical location and connection relationship of the power distribution equipment, and determine the current topology of the target power distribution network; Based on the aforementioned topology, the initial traveling wave signals of the initial node and any adjacent initial nodes are obtained. In response to a fault signal in the target distribution network, the fault area of ​​the target distribution network and each target node directly adjacent to the fault area are determined, and based on the fault area of ​​the target distribution network and each target node directly adjacent to the fault area, the traveling wave propagation path between each target node and the fault area is determined. The initial traveling wave signal is subjected to wavefront calibration correction processing to obtain a corrected traveling wave signal; Feature extraction is performed on the modified traveling wave signal to obtain its time-domain waveform and frequency-domain features. The time-domain waveform, the frequency-domain characteristics, and the traveling wave propagation path are input into the constructed fault location model to obtain the fault location of the target distribution network.

2. The method for locating faults in a distribution network as described in claim 1, characterized in that, The step of obtaining the initial traveling wave signal between the initial node and any adjacent initial nodes based on the topology includes: The topology is identified using breadth-first search to obtain the initial nodes of the target distribution network; The electrical parameters of the lines between any two adjacent initial nodes are calculated to obtain the initial traveling wave signal.

3. The distribution network fault location method as described in claim 1, characterized in that, The step of determining the traveling wave propagation path between each target node and the fault area based on the fault area of ​​the target distribution network and each target node directly adjacent to the fault area includes: The fault area is used as the starting point for path search; The improved Dijkstra algorithm is used to process the topology to obtain several traveling wave propagation paths between the target node and the fault region.

4. The method for locating faults in a distribution network as described in claim 1, characterized in that, The step of correcting the initial traveling wave signal to obtain the corrected traveling wave signal includes: The initial traveling wave signal is subjected to soft thresholding and adaptive filtering in sequence to obtain a noise-suppressed traveling wave signal; The modified traveling wave signal is obtained by performing wavefront calibration on the noise-suppressed traveling wave signal using the Tigger energy operator.

5. The distribution network fault location method as described in claim 1, characterized in that, The step of extracting features from the modified traveling wave signal to obtain its time-domain waveform and frequency-domain features includes: The arrival time of the traveling wave front of the modified traveling wave signal is obtained by monitoring the modified traveling wave signal using the threshold method. Based on the arrival time of the traveling wave front and the obtained signal amplitude of the modified traveling wave signal, the time-domain waveform of the modified traveling wave signal is obtained; The modified traveling wave signal is subjected to frequency domain framing processing using short-time Fourier transform to obtain the frequency domain characteristics of the modified traveling wave signal.

6. The method for locating faults in a distribution network as described in claim 1, characterized in that, The step of inputting the time-domain waveform, the frequency-domain characteristics, and the traveling wave propagation path into the constructed fault location model to obtain the fault location of the target distribution network includes: The time-domain waveform and the frequency-domain features are input into a fault location model constructed using a deep learning network to obtain the fault feature waveform; Based on the fault characteristic waveform and the traveling wave propagation path, the fault location is determined.

7. The method for locating faults in a distribution network as described in claim 1, characterized in that, After obtaining the fault location of the target distribution network, the distribution network fault location method further includes: Obtain the target fault point of the current fault signal; The actual path distance along the route between the fault location and the target fault point is input into the fault location model to optimize the fault location model.

8. A power distribution network fault location system, characterized in that, include: The first acquisition module is used to acquire the geographical location and connection relationship of the power distribution equipment in the target power distribution network, analyze the geographical location and connection relationship of the power distribution equipment, and determine the current topology of the target power distribution network. The second acquisition module is used to acquire the initial traveling wave signal between the initial node and any adjacent initial nodes based on the topology. The determination module is configured to, in response to a fault signal of the target distribution network, determine the fault area of ​​the target distribution network and each target node directly adjacent to the fault area, and, based on the fault area of ​​the target distribution network and each target node directly adjacent to the fault area, determine the traveling wave propagation path between each target node and the fault area. The correction module is used to perform wavefront calibration correction processing on the initial traveling wave signal to obtain a corrected traveling wave signal; The extraction module is used to extract features from the modified traveling wave signal to obtain the time-domain waveform and frequency-domain features of the modified traveling wave signal. The positioning module is used to input the time-domain waveform, the frequency-domain characteristics, and the traveling wave propagation path into the constructed fault location model to obtain the fault location of the target distribution network.

9. A power distribution network fault location device, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the power distribution network fault location method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the device containing the computer-readable storage medium executes the computer program, it implements the power distribution network fault location method as described in any one of claims 1 to 7.

Images