Leakage protection method and device based on fault analysis, storage medium and equipment

Abstract

This application discloses a leakage current protection method, device, storage medium, and equipment based on fault analysis, relating to the field of power system technology. Its main purpose is to solve the problem of poor accuracy in existing low-voltage distribution networks for leakage current protection. The method includes: acquiring real-time power grid operation data; identifying faults in the real-time power grid operation data based on a leakage fault type identification model to obtain fault identification results. The leakage fault model is constructed based on historical power grid operation data and a relationship matrix, which includes upstream and downstream relationship matrices, line control relationship matrices, and node control relationship matrices. The relationship matrix is ​​constructed based on a power grid topology diagram, which includes multiple electrical components, circuit lines, and circuit protection nodes. If the fault identification result indicates the existence of a leakage fault, the leakage fault is located based on the relationship matrix, and leakage current protection is implemented based on the leakage fault location result.

Description

Technical Field

[0001] This application relates to the field of power system technology, and in particular to a leakage current protection method, device, storage medium and equipment based on fault analysis. Background Technology

[0002] With the improvement of the intelligence level of distribution networks, the increase in the access of distributed power sources, and the increasingly complex power grid topology, traditional leakage current protection technology can no longer meet the protection requirements of precision, speed, and intelligence. Among them, leakage current protection technology refers to the technology of activating protectors or leakage circuit breakers after detecting leakage current based on electrical quantity detection. The core equipment can include residual current operated protectors (RCDs) and leakage circuit breakers, so as to trigger tripping action when the detected residual current exceeds the rated operating current. However, while leakage current protection (RCD) is widely used in low-voltage distribution networks, it has significant limitations: it can only detect leakage in a single feeder or circuit, failing to accurately locate faulty line segments and nodes; fault diagnosis relies on manual labor, resulting in low efficiency and potentially expanding the outage area; based solely on single electrical quantity analysis, it is susceptible to electromagnetic interference, measurement errors, and changes in environmental humidity, leading to maloperation or failure to operate, thus affecting grid reliability; the operating range of upstream and downstream protection devices lacks precise quantitative division, easily causing cascading trips, resulting in power outages in non-faulty areas, or protection failure to operate, further amplifying the fault; and it does not consider grid topology connections, requiring readjustment of protection parameters when the grid topology changes (addition of lines or equipment), resulting in poor scalability. Therefore, a fault analysis-based RCD method is urgently needed to address these issues. Summary of the Invention

[0003] In view of this, this application provides a leakage current protection method, device, storage medium and equipment based on fault analysis, the main purpose of which is to solve the problem of poor effectiveness of leakage current protection in existing low-voltage distribution networks.

[0004] According to one aspect of this application, a leakage current protection method based on fault analysis is provided, comprising: Obtain real-time power grid operation data; The real-time operation data of the power grid is used to identify faults based on the leakage fault type identification model to obtain the fault identification results. The leakage fault model is constructed based on the historical operation data of the power grid and the relationship matrix. The relationship matrix includes the upstream and downstream relationship matrix, the line control relationship matrix and the node control relationship matrix. The relationship matrix is ​​constructed based on the power grid topology map, which includes multiple electrical components, circuit lines and circuit protection nodes. If the fault identification result indicates the presence of a leakage fault, the leakage fault is located based on the relationship matrix, and leakage protection is implemented based on the leakage fault location result.

[0005] Furthermore, before acquiring the real-time operation data of the power grid, the method further includes: The upstream and downstream relationship matrix is ​​constructed based on the electrical components and the circuit lines; The circuit control relationship matrix is ​​constructed based on the circuit protection nodes and the circuit lines. The elements in the upstream and downstream relationship matrix and the line control relationship matrix are normalized to construct the node control relationship matrix.

[0006] Furthermore, constructing the upstream and downstream relationship matrix based on the electrical components and the circuit lines includes: The upstream and downstream relationships between the electrical components and the independent line segments of the circuit are determined based on the component nodes of the electrical components and the independent line segments of the circuit lines, and the upstream and downstream relationship matrix is ​​generated based on the upstream and downstream relationships. The construction of the line control relationship matrix based on the circuit protection node and the circuit line includes: The control coverage relationship between the independent line and the protection node is determined based on the node equipment of the circuit protection node and the independent line segment of the circuit line, and the line control relationship matrix is ​​generated based on the control coverage relationship.

[0007] Furthermore, before obtaining the fault identification result by performing fault identification on the real-time operation data of the power grid based on the leakage fault type identification model, the method further includes: Acquire historical power grid operation data and extract fused feature vectors based on the historical power grid operation data; The classification model is trained based on the fused feature vector that identifies the type of leakage fault to obtain the leakage fault type identification model.

[0008] Furthermore, the extraction and fusion of feature vectors based on the historical operation data of the power grid includes: Extract leakage fault characteristics from the historical operation data of the power grid. The leakage fault characteristics include zero-sequence current amplitude, residual current change rate, voltage distortion rate, and grounding resistance change. The topological features of the leakage fault characteristics are extracted based on the upstream and downstream relationship matrix and the line control relationship matrix. The topological features include the current difference between upstream and downstream nodes of each independent line segment and the average residual current within the coverage area of ​​each leakage protection device. The topological features and the leakage fault features are integrated to obtain the fused feature vector.

[0009] Furthermore, the leakage fault location based on the relationship matrix includes: Obtain the residual current amplitude and residual current change rate of each independent line segment in the real-time operation data of the power grid; The leakage fault characteristic value of each independent line segment is calculated based on the node current difference correction coefficient, the residual current amplitude, the residual current change rate, and the upstream and downstream relationship in the upstream and downstream relationship matrix. The leakage fault characteristic value is then weighted and corrected based on the line control relationship matrix to obtain the weighted fault characteristic value. The target faulty line segment is determined based on the weighted fault feature value, and the node fault correlation degree of each electrical component node connected to the faulty line segment is calculated based on the upstream and downstream relationship matrix. Based on the node fault correlation, the fault-related nodes are determined, and the leakage fault location result is determined.

[0010] Furthermore, the leakage current protection based on the leakage current fault location result includes: Based on the leakage fault location results, the line control relationship matrix, and the node control relationship matrix, calculate the protection matching degree of the leakage protection device at each leakage protection node to the fault location; Based on the protection matching degree, the target leakage current protection device is determined for leakage current protection.

[0011] According to another aspect of this application, a leakage current protection device based on fault analysis is provided, comprising: The acquisition module is used to acquire real-time operating data of the power grid; The identification module is used to identify faults in the real-time operation data of the power grid based on the leakage fault type identification model, and obtain the fault identification result. The leakage fault model is constructed based on the historical operation data of the power grid and the relationship matrix. The relationship matrix includes the upstream and downstream relationship matrix, the line control relationship matrix and the node control relationship matrix. The relationship matrix is ​​constructed based on the power grid topology diagram, which includes multiple electrical components, circuit lines and circuit protection nodes. The protection module is used to locate the leakage fault based on the relationship matrix and perform leakage protection based on the leakage fault location result if the fault identification result indicates that there is a leakage fault.

[0012] Furthermore, the device also includes: The first construction module is used to construct the upstream and downstream relationship matrix based on the electrical components and the circuit lines; The second construction module is used to construct the circuit control relationship matrix based on the circuit protection node and the circuit line; The third construction module is used to normalize the elements in the upstream and downstream relationship matrix and the line control relationship matrix to construct the node control relationship matrix.

[0013] Furthermore, The first construction module is specifically used to determine the upstream and downstream relationship between the electrical component and the independent line segment based on the component node of the electrical component and the independent line segment of the circuit line, and to generate the upstream and downstream relationship matrix based on the upstream and downstream relationship; The second construction module is specifically used to determine the control coverage relationship between the independent line and the protection node based on the node device of the circuit protection node and the independent line segment of the circuit line, and to generate the line control relationship matrix based on the control coverage relationship.

[0014] Furthermore, the device also includes: a training module, The acquisition module is also used to acquire historical power grid operation data and extract fused feature vectors based on the historical power grid operation data; The training module is used to train the classification model based on the fused feature vector that identifies the leakage fault type, so as to obtain the leakage fault type identification model.

[0015] Furthermore, The acquisition module is further configured to extract leakage fault features from the historical operation data of the power grid, including zero-sequence current amplitude, residual current change rate, voltage distortion rate, and grounding resistance change; extract topological features of the leakage fault features based on the upstream and downstream relationship matrix and the line control relationship matrix, including the current difference between upstream and downstream nodes of each independent line segment and the average residual current within the coverage area of ​​each leakage protection device; and integrate the topological features and the leakage fault features to obtain the fused feature vector.

[0016] Furthermore, the protection module is specifically used to calculate the leakage fault characteristic value of each independent line segment based on the node current difference correction coefficient, the residual current amplitude, the residual current change rate, and the upstream and downstream relationships in the upstream and downstream relationship matrix; and to perform weighted correction on the leakage fault characteristic value based on the line control relationship matrix to obtain a weighted fault characteristic value; to determine the target fault line segment based on the weighted fault characteristic value; and to calculate the node fault correlation degree of each electrical component node connected to the fault line segment based on the upstream and downstream relationship matrix; and to determine the fault-related node based on the node fault correlation degree to determine the leakage fault location result.

[0017] Furthermore, the protection module is specifically used to calculate the protection matching degree of the leakage protection device at each leakage protection node to the fault location based on the leakage fault location result, the line control relationship matrix, and the node control relationship matrix; and to determine the target leakage protection device for leakage protection based on the protection matching degree.

[0018] According to another aspect of this application, a storage medium is provided, wherein at least one executable instruction is stored therein, the executable instruction causing a processor to perform an operation corresponding to the above-described leakage protection method based on fault analysis.

[0019] According to another aspect of this application, a device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the above-described leakage protection method based on fault analysis.

[0020] By employing the above technical solutions, the technical solutions provided in the embodiments of this application have at least the following advantages: This application provides a leakage current protection method, device, storage medium, and equipment based on fault analysis. Compared with the prior art, the embodiments of this application acquire real-time power grid operation data; perform fault identification on the real-time power grid operation data based on a leakage current fault type identification model to obtain fault identification results. The leakage current fault model is constructed based on historical power grid operation data and a relationship matrix. The relationship matrix includes an upstream and downstream relationship matrix, a line control relationship matrix, and a node control relationship matrix. The relationship matrix is ​​constructed based on a power grid topology diagram, which includes multiple electrical components, circuit lines, and circuit protection nodes. If the fault identification result indicates the existence of a leakage current fault, the leakage current fault is located based on the relationship matrix, and leakage current protection is performed based on the leakage current fault location result. This avoids redundancy in the protection range caused by ambiguous location and unclear correspondence of leakage current protection devices, greatly improving the effectiveness and accuracy of leakage current protection.

[0021] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0022] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A flowchart of a leakage current protection method based on fault analysis provided in an embodiment of this application is shown; Figure 2This paper shows a block diagram of a leakage current protection device based on fault analysis provided in an embodiment of this application; Figure 3 A schematic diagram of the structure of a device provided in an embodiment of this application is shown. Detailed Implementation

[0023] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] The embodiments of this invention can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0026] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0027] This application provides a leakage current protection method based on fault analysis, such as... Figure 1 As shown, the method includes: 101. Obtain real-time power grid operation data.

[0028] In this embodiment of the application, the real-time operation data of the power grid in the power system may include, but is not limited to, voltage, power and current data. For example, voltage data includes the real-time voltage, voltage phase angle and frequency of each bus or substation bus; power data includes active power, reactive power and apparent power, such as lines, transformers, generator sets, load nodes, etc.; current data includes the real-time current of each side of transmission lines, buses, transformers, three-phase current imbalance, etc. This embodiment of the application does not make specific limitations.

[0029] 102. Based on the leakage fault type identification model, fault identification is performed on the real-time operation data of the power grid to obtain the fault identification results.

[0030] In this embodiment, the leakage fault model can be based on a classification model, constructed using historical power grid operating data and a relationship matrix. The classification model can be an artificial intelligence model, including but not limited to random forest, XGBoost, or convolutional neural network (CNN). Furthermore, the relationship matrix includes upstream and downstream relationship matrices, line control relationship matrices, and node control relationship matrices. These relationship matrices are constructed based on a power grid topology diagram, which includes multiple electrical components, circuit lines, and circuit protection nodes.

[0031] It should be noted that the power grid topology diagram is represented as follows: ; ; ; ; in, This is a diagram of the power grid topology. It is the set of nodes for electrical components; For the first One electrical component node; For the first One electrical component node; This represents the total number of electrical component nodes. A collection of circuit segments; For the first The electrical component node and the first Independent line segments for each electrical component node; For the first The index of adjacent electrical component nodes of each electrical component node; This is the set of nodes for the circuit protection nodes of a leakage current protection device; For the first The electrical component node where the leakage current protection device is located; For the first The electrical component node where the leakage current protection device is located; This represents the total number of leakage protection devices.

[0032] In another embodiment of this application, for further definition and explanation, before the step of obtaining real-time power grid operation data, the method further includes: The upstream and downstream relationship matrix is ​​constructed based on the electrical components and the circuit lines; The circuit control relationship matrix is ​​constructed based on the circuit protection nodes and the circuit lines. The elements in the upstream and downstream relationship matrix and the line control relationship matrix are normalized to construct the node control relationship matrix.

[0033] In order to perform digital conversion of power grid components for fault analysis, a relationship matrix is ​​pre-constructed in this embodiment. Specifically, the upstream and downstream relationship matrix is ​​first constructed based on electrical components and circuit lines.

[0034] In another embodiment of this application, for further definition and explanation, the step of constructing the upstream and downstream relationship matrix based on the electrical components and the circuit lines includes: The upstream and downstream relationships between the electrical components and the independent line segments of the circuit are determined based on the component nodes of the electrical components and the independent line segments of the circuit lines, and the upstream and downstream relationship matrix is ​​generated based on the upstream and downstream relationships. The upstream and downstream relationship matrix represents the relationship between electrical components in the circuit, and can be expressed in matrix form as follows: ; in, This is a matrix representing upstream and downstream relationships. For the first The electrical component node and the first The upstream and downstream relationships of each independent line segment; For the first One electrical component node; For the first A separate line segment; This represents the total number of electrical component nodes. This represents the total number of independent line segments.

[0035] In another embodiment of this application, for further definition and explanation, the step of constructing the circuit control relationship matrix based on the circuit protection node and the circuit line includes: The control coverage relationship between the independent line and the protection node is determined based on the node equipment of the circuit protection node and the independent line segment of the circuit line, and the line control relationship matrix is ​​generated based on the control coverage relationship.

[0036] The line control relationship matrix represents the control relationship of the leakage current protection device in the line, and can be expressed in matrix form as follows: ; ; in, This is the line control relationship matrix; This represents the total number of leakage protection devices. This represents the total number of independent line segments; For the first The leakage protection device is for the first Control coverage relationship of each independent line segment; For the first One leakage protection device; For the first A separate line segment; To protect the weighting coefficients; For the first The leakage protection device to the first The topology hop count for each independent line segment, with adjacent electrical component nodes being 1 hop; For the first The load importance coefficient of each independent line segment.

[0037] Furthermore, the elements in the upstream / downstream relationship matrix and the line control relationship matrix can be normalized to construct the node control relationship matrix. The node control relationship matrix represents the control relationship between each leakage protection device and the electrical component nodes in the line, and can be expressed in matrix form as follows: ; in, The node control relationship matrix; For the first The leakage protection device is for the first Quantitative value of the control capability of each electrical component node; This represents the total number of leakage protection devices. This represents the total number of electrical component nodes. for The middle represents the first The leakage protection device is for the first The control element value of each electrical component node; This is a maximum value function used to extract... The maximum value of the elements in; For transpose; This is the line control relationship matrix; This is a matrix representing upstream and downstream relationships.

[0038] 103. If the fault identification result indicates the presence of a leakage fault, the leakage fault is located based on the relationship matrix, and leakage protection is implemented based on the leakage fault location result.

[0039] In this embodiment, after obtaining the fault identification result based on the leakage fault type identification model, the fault identification result is analyzed to indicate the presence of a leakage fault in the power grid. Therefore, the leakage fault in the power grid is located based on the relationship matrix, and then the leakage protection device is activated.

[0040] In another embodiment of this application, for further definition and explanation, the step of locating leakage faults based on the relationship matrix includes: Obtain the residual current amplitude and residual current change rate of each independent line segment in the real-time operation data of the power grid; The leakage fault characteristic value of each independent line segment is calculated based on the node current difference correction coefficient, the residual current amplitude, the residual current change rate, and the upstream and downstream relationship in the upstream and downstream relationship matrix. The leakage fault characteristic value is then weighted and corrected based on the line control relationship matrix to obtain the weighted fault characteristic value. The target faulty line segment is determined based on the weighted fault feature value, and the node fault correlation degree of each electrical component node connected to the faulty line segment is calculated based on the upstream and downstream relationship matrix. Based on the node fault correlation, the fault-related nodes are determined, and the leakage fault location result is determined.

[0041] To achieve accurate location of leakage faults and activate effective leakage protection devices, specifically, the residual current amplitude and residual current change rate of each independent line segment are first obtained from the real-time operation data of the power grid. That is, the current amplitude and current change rate can be calculated using the real-time operation data of the power grid; this embodiment does not impose specific limitations. Furthermore, based on the node current difference correction coefficient, the residual current amplitude, the residual current change rate, and the upstream and downstream relationships in the upstream and downstream relationship matrix, the leakage fault characteristic value of each independent line segment is calculated, which can be expressed as: ; in, For the first The characteristic values ​​of leakage faults in an independent line segment; For the first The residual current amplitude of each independent line segment; For the first The rate of change of residual current in each independent line segment; For the first The number of nodes connected to each independent line segment; For the first The current difference between upstream and downstream nodes of an independent line segment; It is an absolute value.

[0042] By weighting and correcting the leakage fault characteristic values ​​based on the line control relationship matrix, the weighted fault characteristic values ​​are obtained, which can be expressed as:

[0043] in, For the first Weighted fault characteristic values ​​for each independent line segment; For the line control relationship matrix, the first The maximum protection weight coefficient for each independent line segment; For the first The leakage protection device is for the first The control coverage relationship of each independent line segment is set. In this case, when determining the target faulty line segment based on weighted fault characteristic values, the independent line segment corresponding to the maximum weighted fault characteristic value can be taken as the target faulty line segment. Simultaneously, the node fault correlation degree of each electrical component node connected to the faulty line segment is calculated based on the upstream and downstream relationship matrix. That is, combining the upstream and downstream relationship matrix, the node fault correlation degree of each electrical component node connected to the faulty line segment is calculated, which can be expressed as: ; in, For the connected first The correlation degree of node faults among electrical component nodes; For the connected first The upstream and downstream relationships between each electrical component node and the faulty line segment; It is the absolute value; The first line segment connected to the faulty line segment Voltage at the moment of failure of each electrical component node; This refers to the rated voltage of the faulty line segment. When determining the fault-related node based on the node fault correlation, the electrical component node with the highest node fault correlation can be selected as the fault-related node to obtain the leakage fault location result. ; The faulty line section; This is a fault-related node.

[0044] In another embodiment of this application, for further definition and explanation, the step of performing leakage protection based on leakage fault location results includes: Based on the leakage fault location results, the line control relationship matrix, and the node control relationship matrix, calculate the protection matching degree of the leakage protection device at each leakage protection node to the fault location; Based on the protection matching degree, the target leakage current protection device is determined for leakage current protection.

[0045] To effectively activate the leakage current protection device and ensure the effectiveness of protection under power grid leakage faults, the protection matching degree of the leakage current protection device at each leakage current protection node to the fault location can be calculated based on the leakage fault location results, the line control relationship matrix, and the node control relationship matrix, and expressed as:

[0046] in, For the first The protection matching degree of each leakage current protection device to the fault location; for The weights; For the first The control coverage relationship of each leakage protection device for the faulty line section; for The weights; For the first The control capability of each residual current device (RCD) over the fault-related node is quantified. Finally, when determining the target RCD for RCD protection based on the protection matching degree, the RCD with the highest protection matching degree is selected as the device to be operated.

[0047] In another embodiment of this application, for further definition and explanation, before the step of performing fault identification on the real-time operation data of the power grid based on the leakage fault type identification model to obtain the fault identification result, the method further includes: Acquire historical power grid operation data and extract fused feature vectors based on the historical power grid operation data; The classification model is trained based on the fused feature vector that identifies the type of leakage fault to obtain the leakage fault type identification model.

[0048] To improve the accuracy of leakage fault detection through fault analysis based on artificial intelligence technology, historical power grid operation data is acquired before fault identification. This involves extracting a fused feature vector from the historical power grid operation data. The fused feature vector represents a feature vector that combines fault features with topological features. The topological features include the current difference between upstream and downstream nodes of each independent line segment and the average residual current within the coverage area of ​​each leakage protection device, thereby improving the effectiveness of the features in leakage fault identification. Furthermore, a classification model is trained based on the fused feature vectors identifying leakage fault types to obtain the leakage fault type identification model. This can be achieved by manually labeling or using a machine learning model to label the leakage fault type of each historical sample, and then integrating the fused feature vectors of each historical sample to obtain a leakage fault type identification training set. Finally, the classification model is trained using this training set to obtain the leakage fault type identification model.

[0049] In another embodiment of this application, for further definition and explanation, the step of extracting the fused feature vector based on the historical power grid operation data includes: Extract leakage fault characteristics from the historical power grid operation data; The topological features of the leakage fault characteristics are extracted based on the upstream and downstream relationship matrix and the line control relationship matrix. The topological features and the leakage fault features are integrated to obtain the fused feature vector.

[0050] To improve the accuracy of leakage current fault extraction, the extraction of the fused feature vector specifically involves first extracting leakage current fault features from the historical operation data of the power grid. These features include zero-sequence current amplitude, residual current rate of change, voltage distortion rate, and grounding resistance variation. Then, based on the upstream-downstream relationship matrix and the line control relationship matrix, topological features of the leakage current fault features are extracted. These topological features include the current difference between upstream and downstream nodes of each independent line segment and the average residual current within the coverage area of ​​each leakage protection device. This extraction can be based on numerical calculations or pre-trained machine learning models; this embodiment does not impose specific limitations. Finally, the topological features and the leakage current fault features are integrated to obtain the fused feature vector. This integration can be a direct feature combination; duplicate features can be filtered, and different features can be directly combined; this embodiment does not impose specific limitations.

[0051] This application provides a fault analysis-based leakage current protection method that abstracts electrical components, line segments, and protection devices into sets, clearly defining the hierarchical relationships between sets to avoid topological ambiguity. Each set element is associated with parameters of actual equipment / lines, achieving a two-way association between topological abstraction and physical mapping, facilitating engineering implementation. Through matrix elements and weight coefficients, abstract upstream and downstream relationships and control relationships are transformed into quantitative indicators, replacing traditional qualitative descriptions, improving analysis accuracy, and forming a complete quantitative model of the control chain from device to line to node, covering the entire topological correlation field of leakage current protection. Matrix elements can be dynamically updated with changes in the power grid topology (addition of nodes and lines) without requiring algorithm reconstruction, adapting to power grid transformation needs. By integrating electrical quantities, equipment status, and environmental data, and combining topological features, the method enhances the anti-interference capability of fault identification, effectively distinguishing between real and false leakage current, achieving dual positioning of line segments and nodes, breaking through the limitation of traditional leakage current protection that can only locate feeders, with positioning accuracy reaching the smallest topological unit level. Quantitative screening of optimal devices through protection matching avoids cascading tripping and protection failure to operate, improving the coordination of power grid protection. Differentiated action logic is executed based on fault type, balancing rapid fault clearing with reliable power supply to critical loads. A backup device linkage mechanism addresses faults in devices awaiting operation, enhancing the fault tolerance of the protection system and ensuring normal operation of non-faulty areas of the power grid.

[0052] Furthermore, as a response to the above Figure 1 The implementation of the method shown in this application provides a leakage current protection device based on fault analysis, such as... Figure 2 As shown, the device includes: Module 21 is used to acquire real-time power grid operation data; The identification module 22 is used to identify faults in the real-time operation data of the power grid based on the leakage fault type identification model, and obtain the fault identification result. The leakage fault model is constructed based on the historical operation data of the power grid and the relationship matrix. The relationship matrix includes the upstream and downstream relationship matrix, the line control relationship matrix and the node control relationship matrix. The relationship matrix is ​​constructed based on the power grid topology diagram. The power grid topology diagram includes multiple electrical components, circuit lines and circuit protection nodes. The protection module 23 is used to locate the leakage fault based on the relationship matrix and perform leakage protection based on the leakage fault location result if the fault identification result is that there is a leakage fault.

[0053] Furthermore, the device also includes: The first construction module is used to construct the upstream and downstream relationship matrix based on the electrical components and the circuit lines; The second construction module is used to construct the circuit control relationship matrix based on the circuit protection node and the circuit line; The third construction module is used to normalize the elements in the upstream and downstream relationship matrix and the line control relationship matrix to construct the node control relationship matrix.

[0054] Furthermore, The first construction module is specifically used to determine the upstream and downstream relationship between the electrical component and the independent line segment based on the component node of the electrical component and the independent line segment of the circuit line, and to generate the upstream and downstream relationship matrix based on the upstream and downstream relationship; The second construction module is specifically used to determine the control coverage relationship between the independent line and the protection node based on the node device of the circuit protection node and the independent line segment of the circuit line, and to generate the line control relationship matrix based on the control coverage relationship.

[0055] Furthermore, the device also includes: a training module, The acquisition module is also used to acquire historical power grid operation data and extract fused feature vectors based on the historical power grid operation data; The training module is used to train the classification model based on the fused feature vector that identifies the leakage fault type, so as to obtain the leakage fault type identification model.

[0056] Furthermore, The acquisition module is further configured to extract leakage fault features from the historical operation data of the power grid, including zero-sequence current amplitude, residual current change rate, voltage distortion rate, and grounding resistance change; extract topological features of the leakage fault features based on the upstream and downstream relationship matrix and the line control relationship matrix, including the current difference between upstream and downstream nodes of each independent line segment and the average residual current within the coverage area of ​​each leakage protection device; and integrate the topological features and the leakage fault features to obtain the fused feature vector.

[0057] Furthermore, the protection module is specifically used to calculate the leakage fault characteristic value of each independent line segment based on the node current difference correction coefficient, the residual current amplitude, the residual current change rate, and the upstream and downstream relationships in the upstream and downstream relationship matrix; and to perform weighted correction on the leakage fault characteristic value based on the line control relationship matrix to obtain a weighted fault characteristic value; to determine the target fault line segment based on the weighted fault characteristic value; and to calculate the node fault correlation degree of each electrical component node connected to the fault line segment based on the upstream and downstream relationship matrix; and to determine the fault-related node based on the node fault correlation degree to determine the leakage fault location result.

[0058] Furthermore, the protection module is specifically used to calculate the protection matching degree of the leakage protection device at each leakage protection node to the fault location based on the leakage fault location result, the line control relationship matrix, and the node control relationship matrix; and to determine the target leakage protection device for leakage protection based on the protection matching degree.

[0059] This application provides a leakage current protection device based on fault analysis. This embodiment acquires real-time power grid operation data; it then performs fault identification on the real-time power grid operation data based on a leakage current fault type identification model to obtain fault identification results. The leakage current fault model is constructed based on historical power grid operation data and a relationship matrix. The relationship matrix includes an upstream-downstream relationship matrix, a line control relationship matrix, and a node control relationship matrix. The relationship matrix is ​​constructed based on a power grid topology diagram, which includes multiple electrical components, circuit lines, and circuit protection nodes. If the fault identification result indicates the presence of a leakage current fault, the leakage current fault is located based on the relationship matrix, and leakage current protection is performed based on the leakage current fault location result. This avoids redundancy in the protection range caused by ambiguous location and unclear correspondence of leakage current protection devices, greatly improving the effectiveness and accuracy of leakage current protection.

[0060] According to one embodiment of this application, a storage medium is provided, the storage medium storing at least one executable instruction that can execute the leakage current protection method based on fault analysis in any of the above method embodiments.

[0061] Figure 3 The diagram shows a structural schematic of a device according to one embodiment of the present application. The specific embodiments of the present application do not limit the specific implementation of the device.

[0062] like Figure 3 As shown, the device may include: a processor 302, a communications interface 304, a memory 306, and a communications bus 308.

[0063] The processor 302, communication interface 304, and memory 306 communicate with each other via communication bus 308.

[0064] Communication interface 304 is used to communicate with other network elements such as clients or other servers.

[0065] The processor 302 is used to execute program 310, which can specifically execute the relevant steps in the above-described embodiment of the leakage current protection method based on fault analysis.

[0066] Specifically, program 310 may include program code that includes computer operation instructions.

[0067] Processor 302 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. The device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or they may be processors of different types, such as one or more CPUs and one or more ASICs.

[0068] Memory 306 is used to store program 310. Memory 306 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0069] Specifically, program 310 can be used to cause processor 302 to perform the following operations: Obtain real-time power grid operation data; The real-time operation data of the power grid is used to identify faults based on the leakage fault type identification model to obtain the fault identification results. The leakage fault model is constructed based on the historical operation data of the power grid and the relationship matrix. The relationship matrix includes the upstream and downstream relationship matrix, the line control relationship matrix and the node control relationship matrix. The relationship matrix is ​​constructed based on the power grid topology map, which includes multiple electrical components, circuit lines and circuit protection nodes. If the fault identification result indicates the presence of a leakage fault, the leakage fault is located based on the relationship matrix, and leakage protection is implemented based on the leakage fault location result.

[0070] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0071] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A leakage current protection method based on fault analysis, characterized in that, include: Obtain real-time power grid operation data; The real-time operation data of the power grid is used to identify faults based on the leakage fault type identification model to obtain the fault identification results. The leakage fault model is constructed based on the historical operation data of the power grid and the relationship matrix. The relationship matrix includes the upstream and downstream relationship matrix, the line control relationship matrix and the node control relationship matrix. The relationship matrix is ​​constructed based on the power grid topology map, which includes multiple electrical components, circuit lines and circuit protection nodes. If the fault identification result indicates the presence of a leakage fault, the leakage fault is located based on the relationship matrix, and leakage protection is implemented based on the leakage fault location result.

2. The method according to claim 1, characterized in that, Before acquiring real-time power grid operation data, the method further includes: The upstream and downstream relationship matrix is ​​constructed based on the electrical components and the circuit lines; The circuit control relationship matrix is ​​constructed based on the circuit protection nodes and the circuit lines. The elements in the upstream and downstream relationship matrix and the line control relationship matrix are normalized to construct the node control relationship matrix.

3. The method according to claim 2, characterized in that, The construction of the upstream and downstream relationship matrix based on the electrical components and the circuit lines includes: The upstream and downstream relationships between the electrical components and the independent line segments of the circuit are determined based on the component nodes of the electrical components and the independent line segments of the circuit lines, and the upstream and downstream relationship matrix is ​​generated based on the upstream and downstream relationships. The construction of the line control relationship matrix based on the circuit protection node and the circuit line includes: The control coverage relationship between the independent line and the protection node is determined based on the node equipment of the circuit protection node and the independent line segment of the circuit line, and the line control relationship matrix is ​​generated based on the control coverage relationship.

4. The method according to claim 3, characterized in that, Before obtaining the fault identification result by performing fault identification on the real-time operation data of the power grid based on the leakage fault type identification model, the method further includes: Acquire historical power grid operation data and extract fused feature vectors based on the historical power grid operation data; The classification model is trained based on the fused feature vector that identifies the type of leakage fault to obtain the leakage fault type identification model.

5. The method according to claim 4, characterized in that, The extraction and fusion of feature vectors based on the historical operation data of the power grid includes: Extract leakage fault characteristics from the historical operation data of the power grid. The leakage fault characteristics include zero-sequence current amplitude, residual current change rate, voltage distortion rate, and grounding resistance change. The topological features of the leakage fault characteristics are extracted based on the upstream and downstream relationship matrix and the line control relationship matrix. The topological features include the current difference between upstream and downstream nodes of each independent line segment and the average residual current within the coverage area of ​​each leakage protection device. The topological features and the leakage fault features are integrated to obtain the fused feature vector.

6. The method according to claim 1, characterized in that, The leakage fault location based on the relationship matrix includes: Obtain the residual current amplitude and residual current change rate of each independent line segment in the real-time operation data of the power grid; The leakage fault characteristic value of each independent line segment is calculated based on the node current difference correction coefficient, the residual current amplitude, the residual current change rate, and the upstream and downstream relationship in the upstream and downstream relationship matrix. The leakage fault characteristic value is then weighted and corrected based on the line control relationship matrix to obtain the weighted fault characteristic value. The target faulty line segment is determined based on the weighted fault feature value, and the node fault correlation degree of each electrical component node connected to the faulty line segment is calculated based on the upstream and downstream relationship matrix. Based on the node fault correlation, fault-related nodes are determined, and the leakage fault location result is determined.

7. The method according to claim 6, characterized in that, The leakage current protection based on the leakage current fault location result includes: Based on the leakage fault location results, the line control relationship matrix, and the node control relationship matrix, calculate the protection matching degree of the leakage protection device at each leakage protection node to the fault location; Based on the protection matching degree, the target leakage current protection device is determined for leakage current protection.

8. A leakage current protection device based on fault analysis, characterized in that, include: The acquisition module is used to acquire real-time operating data of the power grid; The identification module is used to identify faults in the real-time operation data of the power grid based on the leakage fault type identification model, and obtain the fault identification result. The leakage fault model is constructed based on the historical operation data of the power grid and the relationship matrix. The relationship matrix includes the upstream and downstream relationship matrix, the line control relationship matrix and the node control relationship matrix. The relationship matrix is ​​constructed based on the power grid topology diagram, which includes multiple electrical components, circuit lines and circuit protection nodes. The protection module is used to locate the leakage fault based on the relationship matrix and perform leakage protection based on the leakage fault location result if the fault identification result indicates that there is a leakage fault.

9. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method of claim 1.

10. A computer device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method of claim 1.

Images