Method and system for detecting high-resistance grounding fault of small-resistance grounding system

Abstract

The invention provides a low-resistance grounding system high-resistance grounding fault detection method and system, and the method comprises the steps: employing an outgoing line zero-sequence current amplitude, a zero-sequence current phase, a slope at a zero crossing point of a zero-sequence current waveform, and the concavity and convexity at a peak point of the zero-sequence current waveform as fault feature criteria of a high-resistance grounding fault detection model; and then the network model is used for detecting the high-resistance grounding fault, so that the problem that the fault cannot be detected or the detection is inaccurate due to a single fault feature is avoided, and the fault detection accuracy of the high-resistance grounding fault under different fault conditions is improved.

Description

Technical Field

[0001] The invention belongs to the technical field of distribution network fault detection, and particularly relates to a high-resistance grounding fault detection method and system for a low-resistance grounding system. Background Technique

[0002] The statements in this part only provide background technical information related to the present invention, and do not necessarily constitute prior art.

[0003] The low-resistance grounding system is widely used in urban distribution networks for its advantages such as fast fault removal speed and low overvoltage level. At present, the main protection of the low-resistance grounding system is the definite-time zero-sequence overcurrent protection, which is set according to the maximum capacitive current, and the setting value is relatively high, generally 40A - 60A. According to actual experience, this setting value can only detect grounding faults with a grounding resistance of 85Ω - 140Ω at most. When a high-resistance grounding fault with a grounding resistance greater than 140Ω occurs, the zero-sequence current amplitude of the line may be less than this operating value, resulting in the failure to detect the occurrence of the fault, and the protection of the faulty line may refuse to operate. If the high-resistance grounding fault cannot be detected in time, the degree of the fault may further intensify, damaging the operation stability of the power system.

[0004] Therefore, how to accurately detect high-resistance grounding faults is a problem that needs to be solved currently. Summary of the Invention

[0005] To overcome the deficiencies of the above-mentioned prior art, the present invention provides a high-resistance grounding fault detection method and system for a low-resistance grounding system, which detects high-resistance grounding faults in the low-resistance grounding system based on multiple fault characteristics, and improves the accuracy of fault detection for high-resistance grounding faults in different fault situations.

[0006] To achieve the above object, the present invention adopts the following technical solutions: In the first aspect, the present invention provides a high-resistance grounding fault detection method for a low-resistance grounding system, including: Based on a high-resistance grounding fault simulation model of the low-resistance grounding system, multiple fault characteristics corresponding to different fault situations are simulated; wherein, the multiple fault characteristics at least include the amplitude of the zero-sequence current of the outgoing line, the phase of the zero-sequence current, the slope at the zero-crossing point of the zero-sequence current waveform, and the concavity and convexity at the peak point of the zero-sequence current waveform; According to the multiple fault characteristics and their corresponding fault line judgment result labels, a training data set is constructed; Based on the training data set, a high-resistance grounding fault detection model is trained, and the trained high-resistance grounding fault detection model is used to detect multiple characteristics of the low-resistance grounding system to obtain the high-resistance grounding fault detection result of the low-resistance grounding system.

[0007] In a second aspect, the present invention provides a high-resistance grounding fault detection system for a low-resistance grounding system, comprising: A multi-fault feature acquisition module, which is configured to simulate and obtain multi-fault features respectively corresponding to different fault conditions based on a high-resistance grounding fault simulation model of a low-resistance grounding system; wherein, the multi-fault features at least include the magnitude of the zero-sequence current of the outgoing line, the phase of the zero-sequence current, the slope at the zero-crossing point of the zero-sequence current waveform, and the concavity and convexity at the peak point of the zero-sequence current waveform; A training dataset construction module, which is configured to construct a training dataset according to the multi-fault features and the corresponding fault line judgment result labels; A fault detection module, which is configured to train a high-resistance grounding fault detection model based on the training dataset, and use the trained high-resistance grounding fault detection model to detect multi-features of a low-resistance grounding system, so as to obtain a high-resistance grounding fault detection result of the low-resistance grounding system.

[0008] In a third aspect of the present invention, a computer-readable storage medium is provided.

[0009] A computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps in a high-resistance grounding fault detection method for a low-resistance grounding system as described above are implemented.

[0010] In a fourth aspect of the present invention, a computer program product is provided.

[0011] A computer program product, comprising a computer program / instructions, and when the computer program / instructions are executed by a processor, the steps in a high-resistance grounding fault detection for a low-resistance grounding system as described above are implemented.

[0012] In a fifth aspect of the present invention, an electronic device is provided.

[0013] An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the steps in a high-resistance grounding fault detection for a low-resistance grounding system as described above are implemented.

[0014] Compared with the prior art, the beneficial effects of the present invention are: The present invention uses the magnitude of the zero-sequence current of the outgoing line, the phase of the zero-sequence current, the slope at the zero-crossing point of the zero-sequence current waveform, and the concavity and convexity at the peak point of the zero-sequence current waveform as the fault feature criteria for the high-resistance grounding fault detection model, and then uses a network model to detect high-resistance grounding faults, avoiding the problem that a single fault feature cannot detect faults or the detection is inaccurate, and improving the fault detection accuracy of high-resistance grounding faults under different fault conditions.

[0015] Advantages of additional aspects of the present invention will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings forming a part of this specification are used to provide a further understanding of the present invention. The schematic embodiments and descriptions thereof of the present invention are used to explain the present invention and do not constitute an improper limitation to the present invention.

[0017] Figure 1 is a schematic diagram of the zero-sequence equivalent network of a single-phase grounding fault in a small-resistance grounding system in the first embodiment of the present invention; Figure 2 is a schematic diagram of phasor analysis of a single-phase grounding fault in a small-resistance grounding system in the first embodiment of the present invention; Figure 3 is the waveform of the zero-sequence current of the faulty line obtained by running the simulation model in the first embodiment of the present invention; Figure 4 is the waveform of the zero-sequence current of the non-faulty line obtained by running the simulation model in the first embodiment of the present invention; Figure 5 is a schematic diagram of part of the code for optimizing the BP neural network using the gray wolf algorithm in the first embodiment of the present invention; Figure 6 is a simulation model of a high-resistance grounding fault in a small-resistance grounding system built using MATLAB / Simulink in the first embodiment of the present invention; Figure 7 is a schematic diagram of the training state obtained by running the GWO-BP neural network in the first embodiment of the present invention; Figure 8 is a schematic diagram of the training performance obtained by running the GWO-BP neural network in the first embodiment of the present invention; Figure 9 is the confusion matrix of the training set obtained by running the GWO-BP neural network in the first embodiment of the present invention; Figure 10 is the confusion matrix of the test set obtained by running the GWO-BP neural network in the first embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0019] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention.

[0020] Without conflict, the embodiments in the present invention and the features in the embodiments may be combined with each other.

[0021] Embodiment 1 This embodiment discloses a method for detecting high-resistance grounding faults in a small-resistance grounding system, including: Step 1: Based on a high-resistance grounding fault simulation model of a small-resistance grounding system, simulate and obtain multiple fault characteristics corresponding to different fault conditions; among them, the multiple fault characteristics at least include the amplitude of the zero-sequence current of the outgoing line, the phase of the zero-sequence current, the slope at the zero-crossing point of the zero-sequence current waveform, and the concavity and convexity at the peak point of the zero-sequence current waveform.

[0022] Build a high-resistance grounding fault simulation model of a 10kV neutral point grounded through a small resistance as shown in Figure 6 MATLAB / Simulink environment. The grounding resistance of the neutral point in this system is set to 10 ohms. This system contains a total of six feeders, and the lengths of the six feeders are 2km, 6km, 8km, 10km, 12km, and 20km respectively. The positive-sequence parameters of the line are: R1 = 0.28Ω / km, X1 = 0.26mh / km, C1 = 0.38μF / km; the zero-sequence parameters are: R0 = 2.8Ω / km, X0 = 1.11mh / km, C0 = 0.28μF / km. Set single-phase high-resistance grounding faults under different fault conditions (different fault lines (the lines are: Line L1, Line L2, Line L3, Line L4, Line L5, Line L6), different fault times (the fault time is 0.04s - 0.05s), different transition resistances (the transition resistance is 0.01 ohm - 3000 ohms), with / without grounding arc), and obtain information such as the amplitude of the zero-sequence current of each outgoing line, the phase of the zero-sequence current, the zero-sequence current waveform, and the amplitude of the zero-sequence current of the neutral line under different high-resistance grounding fault conditions.

[0023] When a single-phase grounding fault occurs in a small-resistance grounding system, the amplitude of the zero-sequence current of the system neutral line will increase. This disclosure studies using the amplitude of the zero-sequence current of the neutral line as the starting criterion for the high-resistance grounding fault detection model of the small-resistance grounding system. When the amplitude of the zero-sequence current of the system neutral line is greater than the setting value, it is determined that the system may have a high-resistance grounding fault.

[0024] The setting of the amplitude of the zero-sequence current of the neutral line is as follows: According to the general parameters of engineering experience, the maximum unbalanced zero-sequence current corresponding to a single-phase grounding fault in a pure overhead line and a pure cable line is about 0.37A and 0.26A respectively. Since the protection device accesses a 3-fold zero-sequence current electrical signal, the setting value of the zero-sequence current of the neutral line should be greater than 1.11A.

[0025] Therefore, this embodiment sets the setting value of the amplitude of the zero-sequence current of the neutral line to 1.5A, which can detect high-resistance grounding faults of 3000 ohms.

[0026] The analysis of the amplitude and phase characteristics of the zero-sequence current of each outgoing line under single-phase grounding faults is as follows: When a single outgoing line grounding fault occurs in a small-resistance grounding system, the zero-sequence equivalent network is as Figure 1 shown, where is the voltage of the virtual power source at the fault point, is the phase voltage before the fault at the fault point, is the transition resistance at the fault point, is the neutral grounding resistance, is the zero-sequence current of the fault outgoing line, is the zero-sequence current of the neutral grounding resistance, is the zero-sequence current of each healthy outgoing line, is the zero-sequence voltage of the bus.

[0027] According to Figure 1 the analysis of the relationship between the amplitude and phase of the zero-sequence current of each outgoing line and the neutral line, from Figure 1 it can be seen that the zero-sequence impedance is equal to the sum of the parallel impedances of the zero-sequence capacitances to the ground of all outgoing lines and the neutral grounding resistance.

[0028] The derivation of the distribution law of the zero-sequence current of each outgoing line and the neutral line is as follows: (1) Among them, is the sum of the zero-sequence capacitances to the ground of all outgoing lines.

[0029] The zero-sequence voltage of the bus is: (2) It can be seen from Equation (2) that the zero-sequence voltage of the bus is mainly related to the neutral grounding resistance and the fault transition resistance.

[0030] The zero-sequence current of each non-faulty line is: (3) The zero-sequence current of the neutral line is: (4) The zero-sequence current of the fault outgoing line is: (5) Among them, is the sum of the zero-sequence capacitances to the ground of all non-faulty lines.

[0031] From equations (3) to (5), it can be seen that the magnitudes of the zero-sequence currents of the faulty outgoing line and the zero-sequence current of the neutral line are mainly related to the fault transition resistance. As the fault transition resistance increases, the zero-sequence currents of the faulty outgoing line and the neutral line decrease significantly; the magnitude of the zero-sequence current of the non-faulty line is closely related to the fault transition resistance and the zero-sequence capacitance to the ground, that is, the outgoing line length. Since the zero-sequence capacitance to the ground is much smaller than the transition resistance and the neutral-point grounding resistance, the phase changes of the zero-sequence currents of each outgoing line and the zero-sequence current of the neutral line are not obvious. From equations (3) and (4), the ratio of the zero-sequence current of the neutral line to the zero-sequence current of the non-faulty line can be obtained as: (6) According to equation (6), it can be seen that due to the extremely small value of the zero-sequence capacitance to the ground, the magnitude of the zero-sequence current of the neutral line is much larger than the magnitude of the zero-sequence current of the non-faulty line, and the phase lags the phase of the zero-sequence current of the non-faulty line by 90°.

[0032] From equations (3) and (5), the ratio of the zero-sequence current of the faulty outgoing line to the zero-sequence current of the non-faulty line can be obtained as: (7) According to equation (7), it can be seen that since , the phase of the zero-sequence current of the faulty outgoing line leads the phase of the zero-sequence current of the neutral line by about 90°. From equations (4) and (5), the ratio of the zero-sequence current of the faulty outgoing line to the zero-sequence current of the neutral line can be obtained as: (8) According to equation (8), it can be seen that since , the magnitude of the zero-sequence current of the faulty outgoing line is slightly larger than the magnitude of the zero-sequence current of the neutral line, and the phase difference between the zero-sequence current of the faulty outgoing line and the zero-sequence current of the neutral line is about 180°. Due to the effect of the zero-sequence capacitance to the ground, the phase of the zero-sequence current of the faulty outgoing line leads the phase of the zero-sequence current of the neutral line by about 180°. Taking the common parameters of the cable outgoing line in the domestic 10 kV system as an example, substituting the common parameters into equations (3) to (8) to obtain the relationship between the magnitudes of the zero-sequence currents of the faulty outgoing line, the zero-sequence current of the neutral line and the zero-sequence current of the non-faulty line. That is, the neutral-point grounding resistance is 10 Ω, the power-frequency angular frequency , the maximum magnitude of the zero-sequence current of a single healthy cable outgoing line is 19 A. Substituting the above reference values, it can be known that the ratio of the zero-sequence current of the system neutral line to the magnitude of the zero-sequence current of any healthy outgoing line is: (9) The ratio of the magnitude of the zero-sequence current of the faulty outgoing line to the magnitude of the zero-sequence current of any non-faulty line is: (10) According to Equation (9) and Equation (10), it can be known that when a single outgoing line has a ground fault, the amplitude of the zero-sequence current in the neutral line is more than 14 times that of the zero-sequence current in the non-faulty line, and the amplitude of the zero-sequence current in the faulty outgoing line is more than 15 times that of the zero-sequence current in the non-faulty line. According to the above analysis, the relationship among the zero-sequence current in the faulty outgoing line, the zero-sequence current in the healthy outgoing line, and the zero-sequence current in the neutral line is as Figure 2 shown. According to Figure 2 the obtained included angle is as follows: (11) where is the sum of the zero-sequence currents of all healthy outgoing lines.

[0033] Substituting the parameters of the common cable outgoing line into the above formula, we can get: (12) where L is the total length of all healthy outgoing lines. Taking the total length of the system cable as 0 - 100 km and substituting it into Equation (12), the obtained value range of is

[0034] When L is 100 km. It can be seen that under the above conditions, the zero-sequence current phase of the faulty outgoing line leads the zero-sequence current phase of the healthy outgoing line by about 90° - 104.78°, and the zero-sequence current phase of the faulty outgoing line leads the zero-sequence current phase of the neutral line by about 180° - 194.78°.

[0035] Through the above analysis, it can be known that when a single outgoing line has a ground fault, the amplitude of the zero-sequence current in the faulty outgoing line is more than 15 times that of the zero-sequence current in the healthy outgoing line, and the phase leads by slightly more than 90°. Figure 3 and Figure 4 shown.

[0036] According to theoretical analysis, when a high-resistance grounding fault occurs in a low-resistance grounding system, it has the following characteristics: the zero-sequence current amplitude of the fault line is more than 10 times greater than that of the non-fault line; there is a significant difference in the zero-sequence current phase between the fault line and the non-fault line; the influence of the arc on the zero-sequence current waveform of the fault line and the non-fault line is different. The above three points can all be used as fault characteristic criteria for detecting high-resistance grounding faults in a low-resistance grounding system under certain conditions, but each single characteristic has certain limitations. Limitations of the amplitude characteristic criterion: When a single-phase grounding fault occurs, the ratio of the zero-sequence current amplitudes between non-fault lines is approximately equal to the ratio of the lengths of non-fault lines. When the length difference between non-fault lines is large, there will be a large difference in the zero-sequence current between non-fault lines, affecting the comparison of zero-sequence current amplitudes; Limitations of the phase characteristic criterion: When a high-resistance grounding fault occurs, the grounding current signal is weak, and it is difficult to measure the phase of the zero-sequence current of non-fault lines; Limitations of the arc characteristic criterion: Although high-resistance grounding faults are often accompanied by intermittent arcs, not all high-resistance grounding faults are accompanied by grounding arcs. When there is no grounding arc, the arc characteristic criterion will not be able to achieve correct fault detection. Therefore, this embodiment proposes to use fault characteristic criteria from multiple different aspects, namely amplitude characteristics, phase characteristics, the manifestation characteristics of the arc in the fault line, and the manifestation characteristics of the arc in the non-fault line, and utilize the complementarity between different criteria to better achieve the detection of high-resistance grounding faults.

[0037] Step 2: Form a training data set according to the multiple fault characteristics and their corresponding fault type labels.

[0038] Process the data obtained from the simulation to obtain information on the zero-sequence current amplitude, zero-sequence current phase, slope at the zero-crossing point of the zero-sequence current waveform, and the number of inflection points near the peak of the zero-sequence current waveform for each outgoing line under different fault conditions. Use the above fault characteristic data as the fault characteristic criteria for the high-resistance grounding fault detection model. Given the judgment result of the fault line corresponding to the fault characteristic criterion as its label, construct a fault characteristic data set for high-resistance grounding faults in a low-resistance grounding system.

[0039] Divide the high-resistance grounding fault characteristic data set into a training data set and a test data set according to 7:3, and input it into the GWO-BP neural network model for training. Use the GWO-BP neural network model to judge whether the same outgoing line is a fault line based on multiple fault characteristic criteria under different fault conditions, and utilize the complementarity between different fault characteristic criteria to achieve high-resistance grounding fault detection in a low-resistance grounding system based on multiple fault characteristics. The training status, training performance, training set confusion matrix, and test set confusion matrix of the GWO-BP neural network are as Figure 7 、 Figure 8 、 Figure 9 、 Figure 10 shown.

[0040] Step 3: Train a fault detection model based on the training data set, and use the trained fault detection model to detect multiple features of the low-resistance grounded system to obtain the high-resistance grounding fault detection results of the low-resistance grounded system.

[0041] The GWO-BP neural network is used as the fault detection model. The GWO-BP neural network is an optimized model that combines the Grey Wolf Optimization (GWO) algorithm with the BP neural network. It optimizes the weights and biases of the BP neural network through the GWO algorithm, thereby improving the performance of the network.

[0042] In this embodiment, the optimization of the BP neural network by the GWO algorithm is realized by writing code. The implementation steps of the GWO algorithm are as follows: (1) Initialize the grey wolf population.

[0043] Initialize the number of wolves in the wolf pack to 5 and the number of iterations to 30. Each wolf represents a possible combination of BP neural network weights; define the lower bound of the parameter as -1 and the upper bound of the parameter as 1; set the learning rate to 0.01, set the number of training times to 1000, and set the target error to 1e-9.

[0044] (2) Calculate the fitness.

[0045] Take the objective function of the GWO algorithm, that is, the position of the target prey, as the fitness function of the BP neural network; determine the relative positions of all individuals in the grey wolf population to the prey, that is, the fitness values of all individuals, and select the positions of α (optimal solution), β (sub-optimal solution), and δ (third-best solution) based on this. The position of the grey wolf individual with the largest fitness value corresponds to the optimal solution; use the fitcal function to decode the grey wolf position into weights and biases, and substitute them into the BP network to calculate the error.

[0046] (3) Update the grey wolf position.

[0047] Update the positions of the grey wolf individuals and the values of parameters α, β, and δ to simulate the hunting behavior. The grey wolf position update formula is: (13) Where , , are the positions of wolves α, β, and δ respectively.

[0048] (4) Update the optimal solution.

[0049] Through the above process, the optimized weights and thresholds are obtained, the BP neural network is trained and tested, the optimal weights and biases found by GWO are assigned to the BP neural network, and the output error and the optimal solution are recorded.

[0050] (5) Execute the BP algorithm.

[0051] Use the updated weights and biases to perform one BP iteration, i.e., the forward propagation and backpropagation processes. Calculate the gradients based on the training data and use the gradient descent algorithm to update the weights and biases.

[0052] (6) Determine the termination condition.

[0053] Check whether the termination condition is satisfied. When the maximum number of iterations is reached or the preset fitness threshold is reached, return the global optimal solution as the optimized neural network model.

[0054] Part of the code for optimizing the BP neural network by the Grey Wolf Optimizer algorithm is as Figure 5 shown.

[0055] A method for detecting high-resistance grounding faults in a low-resistance grounding system provided in this embodiment includes: establishing a simulation model for high-resistance grounding faults in a low-resistance grounding system, and obtaining information such as the zero-sequence current amplitude, zero-sequence current phase, zero-sequence current waveform, and neutral zero-sequence current amplitude of each outgoing line when the low-resistance grounding system has high-resistance grounding faults under different fault conditions by setting different fault conditions; detecting whether there is a high-resistance grounding fault in the system by setting a value for the neutral zero-sequence current amplitude, and using this neutral zero-sequence current amplitude setting value as the startup criterion for the high-resistance grounding fault detection model proposed in this disclosure; using fault characteristics such as the zero-sequence current amplitude, zero-sequence current phase, slope at the zero-crossing point of the zero-sequence current waveform, and concavity / convexity at the peak point of the zero-sequence current waveform of each outgoing line as the fault characteristic criteria for the fault detection model; constructing a high-resistance grounding fault detection model for a low-resistance grounding system based on multi-fault characteristics using a GWO-BP neural network. Verify the fault detection accuracy of this model for high-resistance grounding faults under different fault conditions.

[0056] Embodiment 2 The purpose of this embodiment is to provide a high-resistance grounding fault detection system for a low-resistance grounding system, including: A multi-fault feature acquisition module, which is used to simulate and obtain corresponding multi-fault features under different fault conditions based on a high-resistance grounding fault simulation model for a low-resistance grounding system; wherein, the multi-fault features at least include the zero-sequence current amplitude of the outgoing line, zero-sequence current phase, slope at the zero-crossing point of the zero-sequence current waveform, and concavity / convexity at the peak point of the zero-sequence current waveform; A training data set construction module, which is used to construct a training data set according to the multi-fault features and their corresponding fault line judgment result labels; A fault detection module, which is used to train a high-resistance grounding fault detection model based on the training data set, and use the trained high-resistance grounding fault detection model to detect the multi-features of a low-resistance grounding system to obtain the high-resistance grounding fault detection result of the low-resistance grounding system.

[0057] In more embodiments, the following is also provided: An electronic device includes a memory and a processor, and computer instructions stored on the memory and running on the processor. When the computer instructions are run by the processor, the method described in Embodiment 1 is completed. For the sake of brevity, it will not be elaborated here.

[0058] It should be understood that in this embodiment, the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0059] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A part of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0060] A computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by the processor, the method described in Embodiment 1 is completed.

[0061] The method in Embodiment 1 can be directly embodied as being executed and completed by a hardware processor, or by a combination of hardware and software modules in the processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method. To avoid repetition, it will not be described in detail here.

[0062] A computer program product includes a computer program. When the computer program is executed by the processor, the method described in Embodiment 1 is implemented and completed.

[0063] The present invention also provides at least one computer program product tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as instructions included in program modules, which are executed in a device on a target real or virtual processor to perform the processes / methods described above. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functions of program modules can be combined or divided among program modules as needed. The machine-executable instructions for program modules can be executed within local or distributed devices. In a distributed device, program modules can be located in local and remote storage media.

[0064] The computer program code for implementing the method of the present invention can be written in one or more programming languages. This computer program code can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the program code is executed by the computer or other programmable data processing device, the functions / operations specified in the flowchart and / or block diagram are implemented. The program code can be executed entirely on the computer, partially on the computer, as a stand-alone software package, partially on the computer and partially on a remote computer, or entirely on a remote computer or server.

[0065] In the context of the present invention, the computer program code or related data can be carried by any suitable carrier so that a device, apparatus, or processor can perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, etc. Examples of signals can include electrical, optical, radio, acoustic, or other forms of propagated signals, such as carrier waves, infrared signals, etc.

[0066] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with this embodiment can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0067] Although the specific implementation manners of the present invention have been described above in conjunction with the accompanying drawings, it is not a limitation to the protection scope of the present invention. Those skilled in the art should understand that based on the technical solution of the present invention, various modifications or deformations that can be made by those skilled in the art without creative efforts are still within the protection scope of the present invention.

Claims

1. A method for detecting high-resistance grounding faults in a small-resistance grounding system, characterized in that, Including: Based on a high-resistance grounding fault simulation model of a low-resistance grounded system, multi-fault features corresponding to different fault conditions are simulated and obtained; wherein, the multi-fault features at least include the magnitude of the zero-sequence current of the outgoing line, the phase of the zero-sequence current, the slope at the zero-crossing point of the zero-sequence current waveform, and the concavity and convexity at the peak point of the zero-sequence current waveform; According to the multi-fault features and their corresponding fault line judgment result labels, a training data set is constructed; Based on the training data set, a high-resistance grounding fault detection model is trained, and the trained high-resistance grounding fault detection model is used to detect the multi-features of the low-resistance grounded system to obtain the high-resistance grounding fault detection result of the low-resistance grounded system.

2. The high-resistance grounding fault detection method for a small-resistance grounding system according to claim 1, wherein The GWO-BP neural network model is used as the high-resistance grounding fault detection model, and the GWO-BP neural network model is used to optimize the weights and biases of the BP neural network through the grey wolf algorithm to determine the detection result of the high-resistance grounding fault line.

3. The high-resistance grounding fault detection method for a small-resistance grounding system according to claim 1, characterized in that, The magnitude of the zero-sequence current of the neutral line is used as the starting criterion for detecting the high-resistance grounding fault of the low-resistance grounded system; when the magnitude of the zero-sequence current of the neutral line of the low-resistance grounded system is greater than the rated value of the magnitude of the zero-sequence current of the neutral line, it is determined that the high-resistance grounding fault may have occurred in the low-resistance grounded system.

4. The high-resistance grounding fault detection method for a small-resistance grounding system according to claim 3, characterized in that, The rated value of the magnitude of the zero-sequence current of the neutral line is greater than 1.11 A.

5. The high-resistance grounding fault detection method for a small-resistance grounding system according to claim 2, characterized in that In the GWO-BP neural network model, the position of the target prey is used as the fitness function of the BP neural network.

6. A high-resistance grounding fault detection system for a small-resistance grounding system, characterized in that, Including: A multi-fault feature acquisition module, which is used to simulate and obtain multi-fault features corresponding to different fault conditions based on a high-resistance grounding fault simulation model of a low-resistance grounded system; wherein, the multi-fault features at least include the magnitude of the zero-sequence current of the outgoing line, the phase of the zero-sequence current, the slope at the zero-crossing point of the zero-sequence current waveform, and the concavity and convexity at the peak point of the zero-sequence current waveform; A training data set construction module, which is used to construct a training data set according to the multi-fault features and their corresponding fault line judgment result labels; A fault detection module, which is used to train a high-resistance grounding fault detection model based on the training data set, and use the trained high-resistance grounding fault detection model to detect the multi-features of the low-resistance grounded system to obtain the high-resistance grounding fault detection result of the low-resistance grounded system.

7. A high-resistance grounding fault detection system for a small-resistance grounding system according to claim 6, characterized in that, The GWO-BP neural network model is used as the high-resistance grounding fault detection model, and the GWO-BP neural network model is used to optimize the weights and biases of the BP neural network through the grey wolf algorithm to determine the detection result of the high-resistance grounding fault line.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the steps in a method for detecting high-resistance grounding faults in a low-resistance grounded system according to any one of claims 1-5.

9. A computer program product, characterized in that, Including a computer program / instructions, when the computer program / instructions are executed by a processor, it implements the steps in the method for detecting high-resistance grounding faults in a low-resistance grounded system according to any one of claims 1-5.

10. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in a method for detecting high-resistance grounding faults in a low-resistance grounded system according to any one of claims 1-5.

Images