Power distribution network cable short circuit fault detection method in combination with power supply network topological relation

Abstract

The invention relates to the technical field of cable short-circuit fault detection, in particular to a power distribution network cable short-circuit fault detection method combined with a power supply network topological relation, and the method comprises the steps: collecting the three-phase current and three-phase voltage of each node at each moment in a power distribution network, and the impedance of each node; determining the current abrupt change rate of each node at each moment; obtaining primary fault features of each node at each moment; obtaining an attenuation coefficient of each node at each moment; determining each fault isolation area in the power distribution network according to the connection state of a circuit breaker in the power distribution network; determining the propagation attenuation weight of each node at each moment; and performing weighting processing on the primary fault features through the reciprocal of the propagation attenuation weight, and detecting the short-circuit fault of the power distribution network cable by using a hybrid classifier by using the weighted primary fault features of all nodes at each moment and combining the node adjacency matrix of the power distribution network and the three-phase current and the three-phase voltage of all the nodes. According to the invention, the accuracy of cable short-circuit fault detection is improved.

Description

Technical Field

[0001] The present application relates to the technical field of cable short-circuit fault detection, and in particular to a distribution network cable short-circuit fault detection method in combination with a power supply network topology relationship. Background Art

[0002] Distribution network cable short-circuit fault detection is the core link to ensure the safe operation of the power system. The arc high temperature generated by the short-circuit fault will not only cause safety accidents such as fire and equipment explosion, but also the instantaneous overcurrent caused by it will cause line insulation degradation and even permanent damage to the equipment. With the development of new energy high-penetration distribution networks, short-circuit current characteristics are becoming more and more complex, and efficient detection technology has become a key line of defense to ensure the safe and stable operation of new power systems. The topological relationship of the power supply network refers to the structured description of the physical connection logic and power transmission path between electrical equipment in the power system.

[0003] Traditional distribution network cable short-circuit fault detection generally adopts a static network model, which cannot respond to changes in distribution network topology in real time, and lacks the combination of power supply network topology and electrical parameters. Short-circuit fault detection is often performed only on a single electrical parameter, resulting in low accuracy in short-circuit current feature extraction, which interferes with distribution network cable short-circuit fault detection. Summary of the invention

[0004] In order to solve the above technical problems, the present application provides a distribution network cable short-circuit fault detection method combined with the power supply network topology relationship to solve the existing problems.

[0005] The present invention adopts the following technical solutions to detect short-circuit faults in distribution network cables in combination with the topological relationship of the power supply network: An embodiment of the present application provides a method for detecting a short-circuit fault in a distribution network cable in combination with a power supply network topology relationship, the method comprising the following steps: Collect the three-phase current, three-phase voltage and impedance of each node in the distribution network at each time; By traversing the closed circuit breaker paths in the distribution network, the node adjacency matrix at each time is constructed; the current difference between each node at each time and its neighboring time is analyzed to determine the current mutation rate of each node at each time; The primary fault characteristics of each node at each moment are obtained by combining the zero-sequence transient energy and the total harmonic distortion rate in the local time period of each node at each moment with the current mutation rate; Based on the connection distribution between nodes in the node adjacency matrix, the topological connectivity of each node at each time is determined; the attenuation coefficient of each node at each time is obtained by using the line length and line impedance connected to each node at each time; and each fault isolation zone in the distribution network is determined by the connection status of the circuit breaker in the distribution network; Determine the propagation attenuation weight of each node at each moment by using the number of hops from each node to the nearest fault isolation area at each moment, combining the topological connectivity and the attenuation coefficient, and the impedance deviation of each node; The primary fault feature is weighted by the inverse of the propagation attenuation weight, and the weighted primary fault features of all nodes at each moment are used, combined with the node adjacency matrix of the distribution network and the three-phase current and three-phase voltage of all nodes, and a hybrid classifier is used to detect the distribution network cable short-circuit fault.

[0006] In one embodiment, the determination of the current mutation rate includes: The difference between the in-phase current at each moment and the adjacent moments is calculated, and the current mutation rate is positively correlated with the difference and negatively correlated with the in-phase current at the adjacent moments.

[0007] In one embodiment, the ratio of the difference to the same-phase current at the adjacent moments is calculated, and the current mutation rate is the average of the ratios of the three-phase currents at each moment.

[0008] In one embodiment, the topological connectivity is the number of connections between each node and other nodes in the node adjacency matrix at each time.

[0009] In one embodiment, the attenuation coefficient is the product of the sum of the actual lengths of all lines connected to each node at each moment and the impedance per unit length of the line.

[0010] In one embodiment, the determination of the fault isolation area includes: If the circuit breaker at node Y is disconnected, node Y and all nodes directly connected to node Y are marked as a fault isolation zone; if the circuit breaker between node Y and node X is disconnected, node Y and node X are marked as a fault isolation zone.

[0011] In one embodiment, the determination of the propagation attenuation weight includes: A calculation result of an exponential function with the attenuation coefficient as the base and the number of hops as the exponent is obtained, and a multiplication result of the calculation result and the topological connectivity is calculated, and the propagation attenuation weight is positively correlated with the multiplication result and the impedance deviation.

[0012] In one embodiment, the impedance deviation is the absolute value of the difference between the impedance measurement value of each node at each moment and the nominal value.

[0013] In one embodiment, the hybrid classifier is composed of a graph neural network, a deep belief network, and a DS evidence theory fusion layer.

[0014] This application has at least the following beneficial effects: The present application first collects the three-phase current, three-phase voltage and impedance of each node at each time in the distribution network; constructs the node adjacency matrix at each time by traversing the closed circuit breaker path in the distribution network; analyzes the current difference between each node at each time and its adjacent time, and determines the current mutation rate of each node at each time; the current mutation rate reflects the possibility of short-circuit fault at each node at each time, and improves the reliability of short-circuit fault detection at the node; the zero-sequence transient energy and total harmonic distortion rate in the local time period of each node at each time, combined with the current mutation rate, obtain the primary fault characteristics of each node at each time; the primary fault characteristics of each node at each time are obtained ... The fault characteristics of the first level integrate characteristic signals of multiple aspects of electrical parameters, which can more sensitively capture the transient characteristics of the initial stage of cable short-circuit faults and improve the accuracy of cable short-circuit fault detection; based on the connection distribution between nodes in the node adjacency matrix, the topological connectivity of each node at each time is determined; the topological connectivity reflects the number of connections between each node and other nodes at each time, and reflects the closeness of the connection between each node and other nodes, which helps to measure the fault propagation effect between nodes; the attenuation coefficient of each node at each time is obtained by using the line length and line impedance connected to each node at each time; through the interruption of the distribution network The connection status of the circuit breaker is used to determine the fault isolation areas in the distribution network. The determination of the fault isolation areas improves the efficiency of cable short-circuit fault detection; the propagation attenuation weight of each node at each moment is determined by using the number of hops from each node to the nearest fault isolation area at each moment, combined with the topological connectivity and the attenuation coefficient, and the impedance deviation of each node; the propagation attenuation weight reflects the degree of influence of the short-circuit fault on each node at each moment, comprehensively considers the real-time topological relationship of the power supply network, and improves the accuracy and reliability of cable short-circuit fault detection; the primary fault feature is weighted by the inverse of the propagation attenuation weight, and the weighted primary fault features of all nodes at each moment are used, combined with the node adjacency matrix of the distribution network and the three-phase current and three-phase voltage of all nodes, and a hybrid classifier is used to detect the distribution network cable short-circuit fault; the present application achieves a triple breakthrough in detection accuracy, response speed and adaptability to complex scenarios in distribution network short-circuit detection through the synergy of multi-dimensional feature fusion and topology perception mechanism; the traditional single electrical quantity analysis is expanded into a multi-physical field joint perception system: the power supply network topology is mapped in real time through a dynamic node adjacency matrix, and the distribution network cable short-circuit fault detection is effectively and accurately performed. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 A flow chart of the steps of the distribution network cable short-circuit fault detection method combined with the power supply network topology relationship provided by the present application; Figure 2 This is a flow chart of the relationship between distribution network cable short-circuit fault detection indicators. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of the distribution network cable short-circuit fault detection method combined with the power supply network topology proposed by the present application in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0019] The specific scheme of the distribution network cable short-circuit fault detection method combined with the power supply network topology relationship provided by the present application is described in detail below with reference to the accompanying drawings.

[0020] An embodiment of the present application provides a distribution network cable short-circuit fault detection method in combination with the power supply network topology relationship. Specifically, the following distribution network cable short-circuit fault detection method in combination with the power supply network topology relationship is provided. Figure 1 , the method comprises the following steps: Step S001, collecting the three-phase current, three-phase voltage and impedance of each node in the distribution network at each time.

[0021] In this embodiment, distributed sensors are deployed at each node in the distribution network to continuously collect the three-phase current, three-phase voltage, impedance of each node and impedance of each line of each node, wherein the three-phase current, three-phase voltage and impedance of the node are collected synchronously. In this embodiment, the collection frequency is 20kHz, which can be set by the implementer according to the actual situation, and this embodiment does not impose any restrictions on this.

[0022] Step S002, constructing a node adjacency matrix at each time by traversing the closed circuit breaker paths in the distribution network; analyzing the current difference between each node at each time and its adjacent time, and determining the current mutation rate of each node at each time.

[0023] During the operation of the distribution network, its topology is not static. The opening and closing operations of the circuit breaker and the access and exit of distributed power sources will cause the distribution network topology to change in real time. Therefore, in order to accurately analyze the propagation path and range of the fault current and provide a reliable basis for fault diagnosis, it is necessary to build an accurate and real-time updated power supply network topology.

[0024] This embodiment uses a breadth-first search algorithm to construct a real-time topology of the distribution network. During the construction process, the adjacency matrix is ​​updated in real time and the line impedance parameters are marked for subsequent short-circuit fault feature analysis and fault location.

[0025] The substation outgoing switch is the starting point of the power output of the distribution network. Taking it as the root node and searching along the closed circuit breaker path, the lines and nodes in the distribution network that are energized can be fully covered. In this way, the physical connection relationship of the distribution network can be converted into a mathematical matrix form, namely the adjacency matrix. The elements in the adjacency matrix are used to represent the connection status between nodes. If there is a direct connection between two nodes, the corresponding matrix element is 1, otherwise it is 0.

[0026] Cable short circuit faults usually cause the current to change sharply in an instant. During normal operation, the current in the distribution network is relatively stable and the change amplitude is small. When a short circuit fault occurs, the current near the fault point will increase rapidly. Therefore, in order to be able to keenly capture this rapid change, it provides an important basis for the early detection of short circuit faults. This embodiment calculates the current mutation rate of each node at each moment, and the specific calculation method is: ; In the formula, is the current mutation rate of node Y at the jth moment, is the current value of phase A at node Y at the jth moment, is the current value of phase A at node Y at the j-1th moment, is the B-phase current value of node Y at the jth moment, is the B-phase current value of node Y at the j-1th moment, is the C-phase current value of node Y at the jth moment, is the C-phase current value of node Y at the j-1th moment.

[0027] The current mutation rate of node Y at the jth moment reflects the possibility of a short circuit fault occurring at node Y at the jth moment. The greater the current mutation rate, the greater the possibility of a short circuit fault occurring at node Y at the jth moment.

[0028] Step S003, obtaining the primary fault characteristics of each node at each moment through the zero-sequence transient energy and the total harmonic distortion rate in the local time period of each node at each moment, combined with the current mutation rate.

[0029] When the power system is operating normally, the waveforms of current and voltage are basically sinusoidal. However, short circuit faults will disrupt the normal operation of the power system, resulting in a large number of harmonic components in the current and voltage. The harmonic distortion rate is used to measure the proportion of these harmonic components in the total power. By monitoring the changes in the harmonic distortion rate, it can be determined whether a fault has occurred and the severity of the fault.

[0030] Therefore, in this embodiment, for node Y at the jth moment, if node Y is not in a power-off state, all moments within 2s before and 2s after the jth moment of node Y are taken as the local time period of node Y at the jth moment; if node Y is in a power-off state at the jth moment, all moments within 4s before and 4s after the jth moment of node Y are taken as the local time period of node Y at the jth moment; it should be noted that the local time period includes the jth moment.

[0031] The total harmonic distortion rate of the three-phase voltage data at all times in the local time period at the j-th moment of the node Y is calculated as the total harmonic distortion rate of the node Y at the j-th moment, wherein the calculation of the total harmonic distortion rate is an existing well-known technology and is not described in detail in this embodiment.

[0032] In a three-phase AC power system, the zero-sequence component mainly reflects the asymmetry of the power system. Short-circuit faults often cause asymmetry in the power system, thereby generating zero-sequence current and zero-sequence voltage. Zero-sequence transient energy is the energy accumulation of zero-sequence current and zero-sequence voltage in the transient process. It is very sensitive to asymmetric faults and can effectively detect and distinguish different types of asymmetric faults. Therefore, this embodiment calculates the zero-sequence transient energy based on the three-phase current and three-phase voltage at all times in the local time period of node Y at the jth moment, as the zero-sequence transient energy of node Y at the jth moment. The calculation of zero-sequence transient energy is an existing well-known technology, and the specific process is not repeated here.

[0033] The current mutation rate, total harmonic distortion rate, and zero-sequence transient energy of node Y at the jth moment are arranged in sequence to form the primary fault characteristics of node Y at the jth moment. The primary fault characteristics can comprehensively describe the fault state from multiple dimensions. Different fault types and fault locations may cause these characteristics to present different change patterns. Comprehensive consideration of these characteristics can greatly improve the accuracy and reliability of fault diagnosis and reduce the possibility of misjudgment and missed judgment.

[0034] The same method as that used to obtain the primary fault feature of node Y at the jth moment is used to obtain the primary fault feature of each node at each moment.

[0035] Step S004, based on the connection distribution between nodes in the node adjacency matrix, determine the topological connectivity of each node at each moment; use the line length and line impedance connected to each node at each moment to obtain the attenuation coefficient of each node at each moment; determine each fault isolation area in the distribution network through the connection status of the circuit breaker in the distribution network.

[0036] The fault features extracted above only describe the characteristics of the fault itself, without considering the impact of the complex topological structure of the distribution network on the propagation of the fault. In the distribution network, after a fault occurs, the fault signal will propagate along the network topological structure, and nodes at different locations will be affected by the fault to different degrees. Therefore, it is necessary to integrate the topological information of the distribution network into the fault features so that the fused features can more comprehensively and accurately reflect the propagation characteristics of the fault in the entire distribution network, thereby improving the accuracy of fault diagnosis.

[0037] Based on the dynamic topological relationship of the distribution network, that is, the adjacency matrix at each moment, for each node, the number of connections between it and other nodes is calculated as the topological connectivity of each node. The topological connectivity of a node reflects the importance and location characteristics of the node in the topological structure of the distribution network. The higher the topological connectivity, the closer the connection between the node and other nodes, and the greater its role in the fault propagation process.

[0038] The attenuation coefficient of the short-circuit fault when propagating between nodes is determined based on factors such as the distance between nodes and line impedance. Generally speaking, the longer the distance and the greater the line impedance, the greater the attenuation of the fault propagation. In this embodiment, at each moment, the product of the sum of the actual lengths of all lines connected to each node and the impedance per unit length of the line is used as the attenuation coefficient of each node at each moment, so that during the short-circuit fault propagation process, the farther the node is from the fault point, the more obvious the attenuation of its fault characteristics.

[0039] Secondly, the tripping of the circuit breaker in the distribution network is an important sign of a change in the topological structure of the distribution network. When the circuit breaker tripping signal is detected, the adjacency matrix needs to be quickly updated to reflect the new topological structure. Specifically, if the circuit breaker at node Y trips, this embodiment marks node Y and all nodes directly connected to node Y as a fault isolation zone; if the circuit breaker between node Y and node X trips, node Y and node X are marked as a fault isolation zone. Marking the fault isolation zone is to clarify the scope of the fault impact and improve the efficiency of fault detection.

[0040] Step S005, using the number of hops from each node to the nearest fault isolation area at each moment, combined with the topological connectivity and the attenuation coefficient, and the impedance deviation of each node, to determine the propagation attenuation weight of each node at each moment.

[0041] The propagation attenuation weight of the fault feature of each node is calculated by comprehensively considering the topological connectivity and attenuation coefficient of each node at each moment. For nodes with high topological connectivity and close to the fault point, the propagation attenuation weight of the fault feature should be relatively large, indicating that the fault feature of the node has a greater impact on the overall fault detection result; while for nodes with low topological connectivity or far from the fault point, the propagation attenuation weight of the fault feature should be relatively small.

[0042] Based on this, this embodiment calculates the propagation attenuation weight of each node at each time, and the specific calculation method is: ; In the formula, is the propagation attenuation weight of node W at the jth moment, is the topological connectivity of node W at the jth moment, is the attenuation coefficient of node W at the jth moment, is the number of hops from node W to the nearest fault isolation area at time j, is the absolute value of the difference between the impedance measurement value of node W at the jth moment and the nominal value.

[0043] It should be understood that the number of hops reflects the topological distance between the node and the fault isolation area. The more hops, the farther the node is from the fault point. The more lines and nodes the fault signal passes through during the propagation process, and the greater the attenuation degree. Impedance is one of the important factors affecting the propagation of fault current. In actual operation, due to equipment aging, environmental factors and other reasons, the impedance measurement value may deviate from the nominal value. This deviation will affect the propagation and attenuation of the fault signal. The larger it is, the greater the actual change in impedance is, and the greater the impact on the propagation of the fault signal is. Therefore, the propagation attenuation weight of the node should be increased. The propagation attenuation weight indicates the attenuation degree of the fault feature of the node during the propagation process. The larger the propagation attenuation weight is, the smaller the contribution of the fault feature of the node to fault detection is.

[0044] Step S006, weighting the primary fault feature by the inverse of the propagation attenuation weight, using the weighted primary fault features of all nodes at each moment, combined with the node adjacency matrix of the distribution network and the three-phase current and three-phase voltage of all nodes, using a hybrid classifier, to detect the distribution network cable short circuit fault.

[0045] This embodiment obtains the propagation attenuation weight of each node at each time by analyzing the real-time power supply network topology relationship, and combines the primary fault characteristics of each node at each time, so that the cable short-circuit fault detection of the distribution network deeply integrates the power supply network topology relationship and real-time electrical parameters, breaking through the traditional detection method's reliance on local information.

[0046] Based on this, this embodiment calculates the product of the inverse of the propagation attenuation weight of each node at each time and each element in the primary fault feature as the weighted primary fault feature of each node at each time, and uses the weighted primary fault features of all nodes at each time, the adjacency matrix at each time, and the three-phase current and three-phase voltage of all nodes at each time as the input of the hybrid classifier, and the output is the node where the short-circuit fault occurs, thus completing the detection and location of the distribution network cable short-circuit fault. The distribution network cable short-circuit fault detection indicator relationship flow chart is as follows: Figure 2 shown.

[0047] It should be noted that the hybrid classifier in this embodiment specifically includes: (1) Graph Neural Network (GNN): GNN is a neural network model specifically designed to process data with graph structure. In the distribution network fault detection scenario, the topology of the distribution network can be abstracted as a graph, where nodes represent various electrical devices in the distribution network and edges represent electrical connections between nodes. GNN uses a message passing mechanism to allow each node to interact and aggregate information with its adjacent nodes.

[0048] By aggregating the topological neighborhood features of the distribution network through GNN, the potential associations and mutual influences between nodes in the distribution network can be fully explored. In a complex distribution network topology, short-circuit fault signals often propagate between different nodes through electrical connections. GNN can capture this propagation law and thus more accurately determine the possibility of short-circuit faults at each node.

[0049] (2) Deep Belief Network (DBN). DBN is a generative model based on deep learning, which is composed of multiple stacked restricted Boltzmann machines (RBMs). In fault detection, DBN is mainly used to analyze the characteristics of time series waveforms. The waveforms of three-phase current and three-phase voltage in the distribution network that change over time contain rich fault information. DBN learns the characteristic patterns of these waveforms through unsupervised pre-training and supervised fine-tuning. In the pre-training stage, each RBM learns the local features of the input data, and by continuously adjusting its own weights and biases, the RBM can reconstruct the input data as accurately as possible. After stacking multiple RBMs, the entire DBN can learn the multi-level and abstract feature representation of the input data. In the fine-tuning stage, DBN is supervised by labeled training data so that it can accurately classify fault types.

[0050] DBN can automatically extract deep features from timing waveforms without manually designing complex feature extraction methods. It has high accuracy and robustness in fault type classification, can process fault data under different working conditions, and can better identify fault types even in the presence of noise and interference.

[0051] (3) DS evidence theory fusion layer. DS evidence theory is a method for processing uncertain information fusion. In fault detection, there is a certain degree of uncertainty in the node-level fault probability output by the graph neural network layer and the fault type classification results output by the deep belief network. DS evidence theory defines the basic probability distribution function (BPA) to represent the degree of support of different evidence for cable short circuit faults. Then, the Dempster synthesis rule is used to fuse the BPAs of multiple evidences and calculate the joint BPA, thereby obtaining more accurate and reliable fault detection results.

[0052] The DS evidence theory fusion layer can make full use of the respective advantages of GNN and DBN to organically integrate different types of information. It can effectively reduce the risk of misjudgment and missed judgment that may be caused by a single model and improve the overall accuracy and reliability of fault detection.

[0053] The input of the DS evidence theory fusion layer is the fault probability and fault type of each node. These are the output results of the graph neural network layer and the deep belief network layer, which serve as the input evidence of the DS evidence theory fusion layer. The final short-circuit fault node will be output. By fusing two different types of evidence, comprehensively considering the topological neighborhood characteristics and timing waveform characteristics, a more accurate node short-circuit fault detection result is obtained. Among them, graph neural networks, deep belief networks, and DS evidence theory are all existing publicly known technologies, and the specific process will not be repeated.

[0054] This embodiment can fully utilize the topological structure information of the distribution network and the timing waveform information of the electrical parameters through the collaborative work of the three levels of hybrid classifiers, realize rapid and accurate detection of cable short-circuit faults in the distribution network, and provide a strong guarantee for the safe and stable operation of the distribution network.

[0055] It should be noted that the above sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above is a description of a specific embodiment of this specification. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0056] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0057] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Modifications to the technical solutions recorded in the aforementioned embodiments, or equivalent replacement of some of the technical features therein, do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for detecting short-circuit faults in a distribution network cable in combination with the topological relationship of a power supply network, characterized in that: The method comprises the following steps: Collect the three-phase current, three-phase voltage and impedance of each node in the distribution network at each time; By traversing the closed circuit breaker paths in the distribution network, the node adjacency matrix at each time is constructed; the current difference between each node at each time and its neighboring time is analyzed to determine the current mutation rate of each node at each time; The primary fault characteristics of each node at each moment are obtained by combining the zero-sequence transient energy and the total harmonic distortion rate in the local time period of each node at each moment with the current mutation rate; Based on the connection distribution between nodes in the node adjacency matrix, the topological connectivity of each node at each time is determined; the attenuation coefficient of each node at each time is obtained by using the line length and line impedance connected to each node at each time; and each fault isolation zone in the distribution network is determined by the connection status of the circuit breaker in the distribution network; Determine the propagation attenuation weight of each node at each moment by using the number of hops from each node to the nearest fault isolation area at each moment, combining the topological connectivity and the attenuation coefficient, and the impedance deviation of each node; The primary fault feature is weighted by the inverse of the propagation attenuation weight, and the weighted primary fault features of all nodes at each moment are used, combined with the node adjacency matrix of the distribution network and the three-phase current and three-phase voltage of all nodes, and a hybrid classifier is used to detect the distribution network cable short-circuit fault.

2. The method for detecting short-circuit faults in a distribution network cable in combination with the topological relationship of the power supply network according to claim 1, characterized in that: The determination of the current mutation rate includes: The difference between the in-phase current at each moment and the adjacent moments is calculated, and the current mutation rate is positively correlated with the difference and negatively correlated with the in-phase current at the adjacent moments.

3. The method for detecting short-circuit faults in a distribution network cable in combination with the topological relationship of the power supply network according to claim 2, characterized in that: The ratio of the difference to the same-phase current at the adjacent moments is calculated, and the current mutation rate is the average of the ratios of the three-phase currents at each moment.

4. The method for detecting short-circuit faults in a distribution network cable in combination with the topological relationship of the power supply network according to claim 1, characterized in that: The topological connectivity is the number of connections between each node and other nodes in the node adjacency matrix at each moment.

5. The method for detecting short-circuit faults in a distribution network cable in combination with the topological relationship of a power supply network according to claim 1, characterized in that: The attenuation coefficient is the product of the sum of the actual lengths of all lines connected to each node at each moment and the impedance per unit length of the line.

6. The method for detecting short-circuit faults in a distribution network cable in combination with the topological relationship of the power supply network according to claim 1, characterized in that: The determination of the fault isolation area includes: If the circuit breaker at node Y is disconnected, node Y and all nodes directly connected to node Y are marked as a fault isolation zone; if the circuit breaker between node Y and node X is disconnected, node Y and node X are marked as a fault isolation zone.

7. The method for detecting short-circuit faults in a distribution network cable in combination with the topological relationship of the power supply network according to claim 1, characterized in that: The determination of the propagation attenuation weight includes: A calculation result of an exponential function with the attenuation coefficient as the base and the number of hops as the exponent is obtained, and a multiplication result of the calculation result and the topological connectivity is calculated, and the propagation attenuation weight is positively correlated with the multiplication result and the impedance deviation.

8. The method for detecting short-circuit faults in a distribution network cable in combination with the topological relationship of a power supply network according to claim 1, characterized in that: The impedance deviation is the absolute value of the difference between the impedance measurement value of each node at each moment and the nominal value.

9. The method for detecting short-circuit faults in a distribution network cable in combination with the topological relationship of a power supply network according to claim 1, characterized in that: The hybrid classifier consists of a graph neural network, a deep belief network, and a DS evidence theory fusion layer.

Images