Method for locating fault of low-voltage cable, fault locator, device and medium

Abstract

The embodiment of the application provides a low-voltage cable fault positioning method, a fault positioning instrument, equipment and a medium, and belongs to the cable detection field.The method comprises the following steps: arranging a plurality of sensors along a measured low-voltage cable, synchronously collecting electromagnetic wave signals radiated when a cable fault occurs; performing time-sharing gating and filtering processing to obtain a fault signal; performing analog-digital conversion on the fault signal to extract fault waveform data; extracting a fractal feature vector of the fault waveform data based on a fractal theory; inputting the fractal feature vector into a pre-trained fault classification model, performing nonlinear mapping and classification decision by using a radial basis function, and then outputting a fault type; calculating position information of a fault point according to a time difference of the fault signals received by the sensors; and outputting the fault type and the position information of the fault point.The full-process automation from fault signal collection, type diagnosis to accurate positioning is realized, the power-off time is shortened, and the reliability of urban power supply and the user power consumption satisfaction are ensured.

Description

Technical Field

[0001] This invention relates to the field of cable testing technology, and more specifically to a fault location method, fault location instrument, equipment and medium for low-voltage cables. Background Technology

[0002] Urban areas, as regions with highly concentrated electricity loads, have a large number of users with extremely high requirements for power quality and reliability. However, the current urban power distribution network largely uses low-voltage buried cables. Due to factors such as limited underground space resources, frequent construction, and complex environments, low-voltage cables are often laid in a crisscrossing and dense manner, making management and maintenance difficult. Once a cable fails due to insulation aging, external damage, or joint defects, it is often difficult to quickly locate the fault point, leading to an expansion of the power outage area and an extension of the outage time. This seriously affects users' normal power experience and puts considerable pressure on the reliability indicators of power supply companies.

[0003] Existing methods for detecting low-voltage cable faults mainly include pulse reflection, bridge method, and manual line inspection. The pulse reflection method is susceptible to noise interference and is ineffective for detecting high-resistance and leakage faults. The bridge method requires good circuit conditions and is not suitable for multi-branch cable networks. Manual line inspection is inefficient, especially for buried cables, as it cannot visually determine the fault location and often requires excavation at multiple points, which is time-consuming and labor-intensive. Furthermore, most existing equipment has limited functionality, making it difficult to simultaneously perform fault type diagnosis, precise location, and path detection, and its anti-interference capabilities are weak, resulting in unstable detection data in strong electromagnetic environments, such as urban areas.

[0004] Therefore, there is an urgent need to research an intelligent positioning method and instrument that can quickly and timely locate hidden dangers and fault points in low-voltage cables. This instrument should possess strong anti-interference capabilities, accurately locate common faults such as open circuits, short circuits, and ground leakage (insulation resistance within 0.5 megohms), and detect the depth and path of buried cables. This allows for rapid location determination, fault elimination, and power restoration after a cable fault occurs, effectively improving power supply reliability and user satisfaction. Summary of the Invention

[0005] The purpose of this invention is to provide a fault location method, fault location instrument, equipment and medium for low-voltage cables, which realizes full-process automation from fault signal acquisition and type diagnosis to accurate location, shortens power outage time, and ensures the reliability of urban power supply and user satisfaction.

[0006] To achieve the above objectives, embodiments of the present invention provide a fault location method for low-voltage cables, comprising: Multiple sensors are arranged along the low-voltage cable under test to synchronously collect electromagnetic wave signals radiated when the cable is faulty; and the collected multi-channel electromagnetic wave signals are time-division gating and filtering to obtain the fault signal. The fault signal is converted from analog to digital to extract the fault waveform data; The fractal feature vector of the fault waveform data is extracted based on fractal theory; and the fractal feature vector is input into a pre-trained fault classification model. After nonlinear mapping and classification decision using radial basis functions, the fault type is output. Based on the time difference between the fault signals received by each sensor, the location information of the fault point is calculated; and the fault type and location information of the fault point are output.

[0007] Optionally, the step of extracting the fractal feature vector of the fault waveform data based on fractal theory includes: Dimensions and time delays are embedded in the fault waveform data for phase space reconstruction; After the phase space is reconstructed, the fractal dimension is calculated using the box counting method. The calculated fractal dimension and latitude are used to construct the fractal feature vector.

[0008] Alternatively, the formula for calculating the fractal dimension is:

[0009] In the formula, r is the side length of the box. The number of boxes required to cover the phase space trajectory.

[0010] Optionally, the training process of the fault classification model includes: Sample data of various cable fault types are collected in advance, and the fractal feature vectors of each sample data are extracted as training samples to form a training sample set; wherein, the cable fault types include open circuit, phase-to-phase short circuit, low resistance leakage to ground, partial discharge, and background noise during normal operation. Construct an RBF neural network consisting of an input layer, hidden layers, and an output layer, where the number of nodes in the input layer is equal to the dimension of the fractal feature vector, and the number of nodes in the output layer is equal to the number of fault types. K samples are randomly selected from the training sample set as initial cluster centers. The Euclidean distance from each sample to the initial cluster center is calculated iteratively and the clusters are re-divided. The initial cluster centers are updated with the mean of each class of samples until the cluster centers converge. The final K cluster centers are used as the centers of the radial basis functions; Calculate the pairwise Euclidean distances between K cluster centers, and take the maximum distance as the width parameter of the radial basis function; The least squares method is used to adjust the weights of the output layer and construct a fault classification model. Training is completed when the network output error is less than a preset threshold or the number of iterations reaches the upper limit.

[0011] Optionally, the radial basis function is:

[0012] In the formula, The input fractal feature vector, Let be the center vector of the j-th hidden layer node. For fractal dimension, Let be the fractal dimension corresponding to the j-th type of fault. The width parameter of the feature vector. This is the width parameter representing the difference in fractal dimension.

[0013] Optionally, the fractal feature vector is input into a pre-trained fault classification model. After nonlinear mapping and classification decision using radial basis functions, the fault type is output, including: The extracted fractal feature vectors are input into the input layer of the fault classification model; Suppose that the hidden layer contains K nodes, each node corresponding to a radial basis function; for the j-th hidden layer node, calculate the response value between the fractal eigenvector and the node center based on the radial basis function; The output layer has L nodes, corresponding to L types of faults; for the k-th output node, its output value is obtained by linearly weighted summation of the hidden layer output vectors:

[0014] In the formula, For the output value, Let be the connection weight from the j-th hidden layer node to the k-th output node. This is a bias term.

[0015] Optionally, based on the time difference between the fault signals received by each sensor, the location information of the fault point is calculated; and the fault type and location information of the fault point are output, including: Suppose that the number of sensors arranged along the cable is N, and the position coordinates of each sensor are known; Record the timestamps of the fault signals received by each sensor; Using the first sensor to receive a signal as the reference sensor, calculate the time difference between the other sensors and the reference sensor; Based on the relationship between time difference and distance difference, establish a system of hyperbolic equations:

[0016] In the formula, The coordinates of the fault point are to be determined. Let be the coordinates of the i-th sensor. This refers to the propagation speed of electromagnetic wave signals in low-voltage cables. The coordinates of the fault point were obtained by solving the hyperbolic equation system using the Taylor series expansion method. Map the coordinates of the fault point to the low-voltage cable line path and output the distance between the fault point and the reference sensor.

[0017] Secondly, the present invention also provides a fault location device for low-voltage cables, comprising: The sensing unit is used to arrange multiple sensors along the low-voltage cable under test to synchronously collect electromagnetic wave signals radiated when the cable is faulty; and to perform time-division gating and filtering on the collected multi-channel electromagnetic wave signals to obtain the fault signal. An analog-to-digital conversion unit is used to perform analog-to-digital conversion on the fault signal and extract fault waveform data; The fault identification unit is used to extract the fractal feature vector of the fault waveform data based on fractal theory; and input the fractal feature vector into a pre-trained fault classification model, and output the fault type after performing nonlinear mapping and classification decision using radial basis functions; The fault location unit is used to calculate the location information of the fault point based on the time difference of the fault signals received by each sensor; and output the fault type and location information of the fault point.

[0018] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the fault location method for low-voltage cables described above.

[0019] Fourthly, the present invention also provides a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the fault location method for low-voltage cables described above.

[0020] The above technical solution utilizes fractal theory to extract waveform fractal feature vectors reflecting the essential characteristics of faults. By employing a pre-trained fault classification model for nonlinear mapping and classification decisions, it achieves intelligent and accurate identification of various fault types, including open circuits, short circuits, and ground leakage. Based on a multi-sensor signal arrival time difference positioning mechanism, it can quickly calculate the precise location of the fault point. This fully automates the entire process from fault signal acquisition and type diagnosis to precise positioning, effectively shortening power outage time and ensuring the reliability of urban power supply and user satisfaction.

[0021] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0022] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of a fault location method for low-voltage cables provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a fault location device for low-voltage cables provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0023] Various embodiments of this disclosure will be described more fully in the following detailed description. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0024] In the following, the terms “comprising” or “may include”, which may be used in various embodiments of this disclosure, indicate the presence of the disclosed functions or operations and do not limit the addition of one or more functions or operations. Furthermore, as used in various embodiments of this disclosure, the terms “comprising,” “having,” and their cognates are intended only to indicate a specific feature, number, step, operation, or combination of the foregoing and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, or combinations of the foregoing, or the possibility of adding one or more features, numbers, steps, operations, or combinations of the foregoing.

[0025] In various embodiments of this disclosure, the expression "or" or "at least one of A and / or B" includes any combination or all combinations of the words listed simultaneously. For example, the expression "A or B" or "at least one of A and / or B" may include A, may include B, or may include both A and B.

[0026] 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. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] See Figure 1The diagram shows a flowchart of a fault location method for low-voltage cables in a specific embodiment, including the following execution steps: Step 100: Arrange multiple sensors along the low-voltage cable under test to synchronously collect the electromagnetic wave signals radiated when the cable is faulty; and perform time-division gating and filtering on the collected multi-channel electromagnetic wave signals to obtain the fault signal.

[0028] Specifically, the analog filtering uses a pre-amplified analog bandpass filter whose passband frequency range covers the frequency band of ultra-high frequency fault signals; the digital filtering uses an adaptive filtering algorithm to dynamically adjust the filtering coefficients according to the statistical characteristics of the signal and noise, thereby filtering out residual random noise and impulse interference.

[0029] Step 101: Perform analog-to-digital conversion on the fault signal and extract the fault waveform data.

[0030] Specifically, based on the highest effective frequency component of the fault signal Set the sampling frequency of the analog-to-digital converter. ,satisfy The quantization bit depth is set to 12 bits or more; level-triggered or edge-triggered mode is used, and when the amplitude of the filtered fault signal exceeds a preset threshold, the analog-to-digital converter (ADC) is activated to start acquisition; the preset threshold is set based on the statistical maximum value of the background noise, and is 1.5 to 2 times the peak value of the background noise; the ADC operates at a sampling frequency... Continuously acquire fault signals and store the converted digital values ​​in a first-in-first-out (FIFO) buffer; the acquisition duration T satisfies... Where L is the maximum spacing between adjacent UHF sensors. This represents the speed at which the signal propagates in the cable. The acquired digital sequence is read from the buffer. ,in, The digital sequence is de-biased, and the arithmetic mean of the sequence is subtracted to obtain zero-mean fault waveform data.

[0031] Step 102: Extract the fractal feature vector of the fault waveform data based on fractal theory; and input the fractal feature vector into a pre-trained fault classification model. After performing nonlinear mapping and classification decision using radial basis functions, the fault type is output.

[0032] Specifically, the step of extracting the fractal feature vector of the fault waveform data based on fractal theory includes: embedding the dimension and time delay into the fault waveform data to perform phase space reconstruction; after completing the phase space reconstruction, calculating the fractal dimension using the box counting method; and constructing the fractal feature vector from the calculated fractal dimension and dimension.

[0033] The formula for calculating the fractal dimension is as follows:

[0034] In the formula, r is the side length of the box. The number of boxes required to cover the phase space trajectory.

[0035] Specifically, when executing step 102, the following steps can be performed: S1020: Input the extracted fractal feature vectors into the input layer of the fault classification model.

[0036] S1021: Suppose that the hidden layer contains K nodes, and each node corresponds to a radial basis function; for the j-th hidden layer node, calculate the response value between the fractal eigenvector and the node center based on the radial basis function. S1022: The output layer has L nodes, corresponding to L types of faults; for the k-th output node, its output value is obtained by linearly weighted summation of the hidden layer output vectors:

[0037] In the formula, For the output value, Let be the connection weight from the j-th hidden layer node to the k-th output node. This is a bias term.

[0038] The radial basis function is:

[0039] In the formula, The input fractal feature vector, Let be the center vector of the j-th hidden layer node. For fractal dimension, Let be the fractal dimension corresponding to the j-th type of fault. The width parameter of the feature vector. This is the width parameter representing the difference in fractal dimension.

[0040] In one specific implementation, the training process of the fault classification model includes the following steps: S1: Collect sample data of various cable fault types in advance, and extract the fractal feature vectors of each sample data as training samples to form a training sample set.

[0041] The cable fault types include open circuit, phase-to-phase short circuit, low resistance to ground leakage, partial discharge, and background noise during normal operation.

[0042] S2: Construct an RBF neural network consisting of an input layer, hidden layers, and an output layer.

[0043] The number of nodes in the input layer is equal to the dimension of the fractal feature vector, and the number of nodes in the output layer is equal to the number of fault types.

[0044] S3: Randomly select K samples from the training sample set as initial cluster centers, iteratively calculate the Euclidean distance from each sample to the initial cluster center and re-divide the clusters, and update the initial cluster centers with the mean of each class of samples until the cluster centers converge.

[0045] S4: Use the final K cluster centers as the centers of the radial basis functions.

[0046] In one specific implementation, let the training sample set be... Each sample is an extracted fractal feature vector, and the preset number of hidden layer nodes is K. The center of the radial basis function is determined according to the following steps: Step 1: Randomly select K samples from the training sample set as initial cluster centers. Step 2: Calculate each sample with each cluster center The Euclidean distance between them will The cluster centers are assigned to the nearest cluster center. Step 3: For each cluster center, the mean of all samples in that cluster center is recalculated and used as the updated cluster center. Steps 2 and 3 are repeated until the cluster centers no longer change or the preset maximum number of iterations is reached. The final K cluster centers are used as the centers of the radial basis functions.

[0047] S5: Calculate the Euclidean distance between each pair of K cluster centers, and take the maximum distance as the width parameter of the radial basis function.

[0048] Specifically, maximum distance .

[0049] Specifically, the width parameter of the radial basis function , where K is the number of hidden layer nodes.

[0050] S6: The least squares method is used to adjust the weights of the output layer and construct a fault classification model. Training is completed when the network output error is less than the preset threshold or the number of iterations reaches the upper limit.

[0051] Step 103: Calculate the location information of the fault point based on the time difference of the fault signals received by each sensor; and output the fault type and location information of the fault point.

[0052] Specifically, when executing step 103, the following steps can be performed: S1030: Suppose that the number of sensors arranged along the cable is N, and the position coordinates of each sensor are known.

[0053] S1031: Record the timestamp of each sensor receiving a fault signal.

[0054] S1032: Using the first sensor to receive a signal as the reference sensor, calculate the time difference between the other sensors and the reference sensor.

[0055] S1033: Based on the relationship between time difference and distance difference, establish a system of hyperbolic equations:

[0056] In the formula, The coordinates of the fault point are to be determined. Let be the coordinates of the i-th sensor. This represents the propagation speed of electromagnetic wave signals in low-voltage cables.

[0057] Specifically, the propagation speed can be obtained by consulting the parameter manual of the cable being tested, or by conducting actual measurements on a cable segment of known length. The calculation formula is as follows: In the formula, L is the known length of the cable segment. To determine the propagation time difference between sensors at both ends of the cable, or when the cable type is unknown and cannot be measured and calibrated in practice, the double-end ranging method is used for online calibration. The propagation speed is inferred by using the time difference between the reflected signal and the direct signal at the fault point.

[0058] S1034: The Taylor series expansion method is used to solve the hyperbolic equation system to obtain the coordinates of the fault point.

[0059] S1035: Maps the coordinates of the fault point to the low-voltage cable line path and outputs the distance between the fault point and the reference sensor.

[0060] In this embodiment, fractal theory is used to extract waveform fractal feature vectors that reflect the essential characteristics of the fault, and a pre-trained fault classification model is used for nonlinear mapping and classification decision-making, which realizes intelligent and accurate identification of various fault types such as open circuit, short circuit, and ground leakage; based on the positioning mechanism of multi-sensor signal arrival time difference, the precise location of the fault point can be quickly calculated.

[0061] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0062] like Figure 2As shown, the following are embodiments of the fault location device for low-voltage cables provided in this disclosure. It belongs to the same inventive concept as the fault location method for low-voltage cables in the above embodiments. For details not described in detail in the embodiments of the fault location device for low-voltage cables, please refer to the embodiments of the fault location method for low-voltage cables described above.

[0063] A fault location device for low-voltage cables, comprising: The sensing unit is used to arrange multiple sensors along the low-voltage cable under test to synchronously collect electromagnetic wave signals radiated when the cable is faulty; and to perform time-division gating and filtering on the collected multi-channel electromagnetic wave signals to obtain the fault signal. An analog-to-digital conversion unit is used to perform analog-to-digital conversion on the fault signal and extract fault waveform data; The fault identification unit is used to extract the fractal feature vector of the fault waveform data based on fractal theory; and input the fractal feature vector into a pre-trained fault classification model, and output the fault type after performing nonlinear mapping and classification decision using radial basis functions; The fault location unit is used to calculate the location information of the fault point based on the time difference of the fault signals received by each sensor; and output the fault type and location information of the fault point.

[0064] Figure 3 This is a schematic diagram of the hardware structure of an electronic device that implements various embodiments of the present invention.

[0065] The fault location method for low-voltage cables provided in this application can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiments of this invention does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, the electronic device includes, but is not limited to, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.

[0066] Electronic devices may include processors, external memory interfaces, internal memory, universal serial bus (USB) interfaces, charging management modules, power management modules, batteries, wireless communication modules, audio modules, speakers, microphones, sensor modules, buttons, cameras, displays, and SIM card interfaces, etc.

[0067] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device. In other embodiments of this application, the electronic device may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0068] A processor may include one or more processing units, such as: a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0069] The processor can serve as the nerve center and command center of an electronic device. The controller can generate operation control signals based on the instruction opcode and timing signals to control the fetching and execution of instructions.

[0070] The processor may also include memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or that are used repeatedly. If the processor needs to use the instruction or data again, it can retrieve it directly from this memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0071] An external storage interface (ESI) can be used to connect external memory cards, such as microSD cards, to expand the storage capacity of electronic devices. The external memory card communicates with the processor through the ESI to perform data storage functions, such as saving music and video files on the external memory card.

[0072] Internal memory can be used to store computer executable program code, which includes instructions. The processor executes various functional applications and data processing of electronic devices by running the instructions stored in internal memory. Internal memory can include a program storage area and a data storage area. Internal memory can include high-speed random access memory, and can also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0073] Wireless communication functionality in electronic devices can be achieved through antennas, wireless communication modules, modem processors, and baseband processors.

[0074] Wireless communication modules can provide solutions for wireless communication applications in electronic devices, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies.

[0075] Electronic devices can implement audio functions through audio modules, speakers, receivers, microphones, headphone jacks, and application processors.

[0076] Electronic devices can achieve shooting functions through ISPs, cameras, video codecs, GPUs, displays, and application processors.

[0077] Electronic devices can achieve display functions through GPUs, displays, and application processors.

[0078] A GPU is a microprocessor for image processing, connected to the display screen and application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering. A processor may include one or more GPUs, which execute program instructions to generate or modify display information.

[0079] A display screen is used to display images, videos, etc. A display screen includes a display panel.

[0080] The storage medium provided in this application stores a program product capable of implementing a fault location method for low-voltage cables.

[0081] The fault location method for low-voltage cables includes: arranging multiple sensors along the tested low-voltage cable to synchronously collect electromagnetic wave signals radiated when a cable fault occurs; performing time-division gating and filtering on the collected multi-channel electromagnetic wave signals to obtain a fault signal; performing analog-to-digital conversion on the fault signal to extract fault waveform data; extracting fractal feature vectors from the fault waveform data based on fractal theory; inputting the fractal feature vectors into a pre-trained fault classification model, performing nonlinear mapping and classification decision using radial basis functions, and outputting the fault type; calculating the location information of the fault point based on the time difference between the fault signals received by each sensor; and outputting the fault type and location information of the fault point.

[0082] In some possible implementations, the subject matter of this disclosure, namely, "Method and System for Fault Location of Low-Voltage Cables," can be implemented as a program product comprising program code that, when run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0083] The storage medium disclosed herein may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0084] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for fault location in low-voltage cables, characterized in that, include: Multiple sensors are arranged along the low-voltage cable under test to synchronously collect electromagnetic wave signals radiated when the cable fails. The acquired multi-channel electromagnetic wave signals are then time-division gating and filtering to obtain the fault signal; The fault signal is converted from analog to digital to extract the fault waveform data; The fractal feature vector of the fault waveform data is extracted based on fractal theory; and the fractal feature vector is input into a pre-trained fault classification model. After nonlinear mapping and classification decision using radial basis functions, the fault type is output. Based on the time difference between the fault signals received by each sensor, the location information of the fault point is calculated; and the fault type and location information of the fault point are output.

2. The fault location method for low-voltage cables according to claim 1, characterized in that, The extraction of fractal feature vectors from the fault waveform data based on fractal theory includes: Dimensions and time delays are embedded in the fault waveform data for phase space reconstruction; After the phase space is reconstructed, the fractal dimension is calculated using the box counting method. The calculated fractal dimension and latitude are used to construct the fractal feature vector.

3. The fault location method for low-voltage cables according to claim 2, characterized in that, The formula for calculating fractal dimension is: In the formula, r is the side length of the box. The number of boxes required to cover the phase space trajectory.

4. The fault location method for low-voltage cables according to claim 3, characterized in that, The training process of the fault classification model includes: Sample data of various cable fault types are collected in advance, and the fractal feature vectors of each sample data are extracted as training samples to form a training sample set; wherein, the cable fault types include open circuit, phase-to-phase short circuit, low resistance leakage to ground, partial discharge, and background noise during normal operation. Construct an RBF neural network consisting of an input layer, hidden layers, and an output layer, where the number of nodes in the input layer is equal to the dimension of the fractal feature vector, and the number of nodes in the output layer is equal to the number of fault types. K samples are randomly selected from the training sample set as initial cluster centers. The Euclidean distance from each sample to the initial cluster center is calculated iteratively and the clusters are re-divided. The initial cluster centers are updated with the mean of each class of samples until the cluster centers converge. The final K cluster centers are used as the centers of the radial basis functions; Calculate the pairwise Euclidean distances between K cluster centers, and take the maximum distance as the width parameter of the radial basis function; The least squares method is used to adjust the weights of the output layer and construct a fault classification model. Training is completed when the network output error is less than a preset threshold or the number of iterations reaches the upper limit.

5. The fault location method for low-voltage cables according to claim 4, characterized in that, The radial basis function is: In the formula, The input fractal feature vector, Let be the center vector of the j-th hidden layer node. For fractal dimension, Let be the fractal dimension corresponding to the j-th type of fault. The width parameter of the feature vector. This is the width parameter representing the difference in fractal dimension.

6. The fault location method for low-voltage cables according to claim 5, characterized in that, The fractal feature vector is input into a pre-trained fault classification model. After nonlinear mapping and classification decision using radial basis functions, the fault type is output, including: The extracted fractal feature vectors are input into the input layer of the fault classification model; Suppose that the hidden layer contains K nodes, each node corresponding to a radial basis function; for the j-th hidden layer node, calculate the response value between the fractal eigenvector and the node center based on the radial basis function; The output layer has L nodes, corresponding to L types of faults; for the k-th output node, its output value is obtained by linearly weighted summation of the hidden layer output vectors: In the formula, For the output value, Let be the connection weight from the j-th hidden layer node to the k-th output node. This is a bias term.

7. The fault location method for low-voltage cables according to claim 1, characterized in that, The location information of the fault point is calculated based on the time difference between the fault signals received by each sensor; It also outputs the fault type and location information of the fault point, including: Suppose that the number of sensors arranged along the cable is N, and the position coordinates of each sensor are known; Record the timestamps of the fault signals received by each sensor; Using the first sensor to receive a signal as the reference sensor, calculate the time difference between the other sensors and the reference sensor; Based on the relationship between time difference and distance difference, establish a system of hyperbolic equations: In the formula, The coordinates of the fault point are to be determined. Let be the coordinates of the i-th sensor. This refers to the propagation speed of electromagnetic wave signals in low-voltage cables. The coordinates of the fault point were obtained by solving the hyperbolic equation system using the Taylor series expansion method. Map the coordinates of the fault point to the low-voltage cable line path and output the distance between the fault point and the reference sensor.

8. A fault location device for low-voltage cables, characterized in that, include: The sensing unit is used to arrange multiple sensors along the low-voltage cable under test to synchronously collect electromagnetic wave signals radiated when the cable is faulty. The acquired multi-channel electromagnetic wave signals are then time-division gating and filtering to obtain the fault signal; An analog-to-digital conversion unit is used to perform analog-to-digital conversion on the fault signal and extract fault waveform data; The fault identification unit is used to extract the fractal feature vector of the fault waveform data based on fractal theory; and input the fractal feature vector into a pre-trained fault classification model, and output the fault type after performing nonlinear mapping and classification decision using radial basis functions; The fault location unit is used to calculate the location information of the fault point based on the time difference of the fault signals received by each sensor; and output the fault type and location information of the fault point.

9. An electronic 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 program, it implements the steps of the fault location method for low-voltage cables as described in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the fault location method for low-voltage cables as described in any one of claims 1 to 7.

Images