Fault detection method and device for low-voltage power distribution network, terminal equipment and storage medium

Abstract

The invention discloses a fault detection method and device for a low-voltage power distribution network, terminal equipment and a storage medium, and relates to the technical field of power systems, and the method comprises the steps: collecting operation parameters of key nodes in a target power distribution network, carrying out the abnormality judgment according to the operation parameters, and taking the abnormal operation parameters as observation data; constructing a structured topological relation according to the node and branch connection relation of the target power distribution network; generating state chains according to a node connection relation in the structured topological relation and observation data, and taking the state chains which do not pass the consistency verification as candidate events; and performing fault detection based on the candidate events to obtain a fault type and a fault position of the target power distribution network. The power distribution network fault detection method does not depend on a fixed threshold value and an operation parameter of a single node, and performs fault detection in combination with a topological structure relation and a node connection relation of the whole power distribution network after the abnormal operation parameter is screened out, so that the accuracy of power distribution network fault detection can be effectively improved.

Description

Technical Field

[0001] This invention relates to the field of power systems, and more particularly to a fault detection method, apparatus, terminal equipment, and storage medium for low-voltage distribution networks. Background Technology

[0002] Low-voltage distribution networks are a crucial component of the power system, primarily responsible for transmitting electrical energy from distribution transformers to end users. Their operational status directly impacts the stability and security of the power supply. As users' demands for power quality and reliability continue to rise, low-voltage distribution networks require more sophisticated operational status awareness and fault handling capabilities.

[0003] Existing fault detection methods for low-voltage distribution networks typically rely on fixed thresholds, which are susceptible to noise and interference, resulting in low accuracy in fault detection. Summary of the Invention

[0004] This invention provides a fault detection method, device, terminal equipment, and storage medium for low-voltage distribution networks, which can solve the technical problem that existing technologies usually rely on fixed thresholds and are easily affected by noise and interference, resulting in low accuracy of fault detection.

[0005] This invention provides a fault detection method for low-voltage distribution networks, comprising: Collect the operating parameters of key nodes in the target distribution network, and determine anomalies based on the operating parameters, using the abnormal operating parameters as observation data; Based on the node and branch connection relationships of the target distribution network, a structured topology is constructed; A state chain is generated based on the node connection relationships in the structured topology and the observation data, and the state chain that fails the consistency check is taken as a candidate event. Fault detection is performed based on the candidate events to obtain the fault type and fault location of the target distribution network.

[0006] Furthermore, the step of determining anomalies based on the operating parameters, and using abnormal operating parameters as observation data, includes: The operating parameters are filtered, noise suppressed, and feature extracted to obtain preprocessed data; Anomalies are determined based on each operating parameter and its corresponding preset threshold range, and abnormal operating parameters are used as observation data.

[0007] Furthermore, before generating the state chain based on the node connection relationships in the structured topology and the observation data, the following steps are included: Establish communication links between multiple key nodes, and synchronize and interact observation data among the multiple key nodes based on the communication links.

[0008] Furthermore, after constructing the structured topology based on the node and branch connection relationships of the target distribution network, the process also includes: When the operating status or network structure of the distribution network changes, the node and branch information in the structured topology is updated.

[0009] Furthermore, the step of generating a state chain based on the node connection relationships in the structured topology and the observation data includes: Within a preset time window, timestamp comparison and synchronization processing are performed on multiple observation data to obtain synchronized observation data; Based on the node connection relationships in the structured topology, the synchronized observation data are associated according to the propagation path to generate a state chain.

[0010] Furthermore, the step of performing fault detection based on the candidate events to obtain the fault type and fault location of the target distribution network includes: A pre-built machine learning model is used to perform feature analysis and fault detection on the candidate events to determine the fault type of the distribution network. Based on the structured topology, the fault node is determined, and the fault location corresponding to the current fault type is obtained.

[0011] Furthermore, after performing fault detection based on the candidate events to obtain the fault type and fault location of the target distribution network, the method further includes: Based on the fault type and the fault location, visualized information on operating status and fault distribution is generated respectively.

[0012] The present invention also provides a fault detection device for a low-voltage distribution network, comprising: The observation data determination module is used to collect the operating parameters of key nodes in the target distribution network, and to determine anomalies based on the operating parameters, using the abnormal operating parameters as observation data. The topology construction module is used to construct a structured topology based on the node and branch connection relationships of the target distribution network. The state chain generation module is used to generate a state chain based on the node connection relationship in the structured topology and the observation data, and to take the state chain that fails the consistency check as a candidate event. The fault detection module is used to perform fault detection based on the candidate events to obtain the fault type and fault location of the target distribution network.

[0013] The present invention also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the fault detection method for low-voltage distribution networks as described above.

[0014] The present invention also provides a computer-readable storage medium, comprising: a stored computer program, wherein, when the computer program is executed, it controls the device in which the computer-readable storage medium is located to perform the fault detection method for a low-voltage power distribution network as described above.

[0015] The following benefits can be obtained by implementing the present invention: This invention generates observation data by collecting operating parameters of key nodes and determining anomalies. It then generates state chains based on the node connection relationships in the structured topology and the observation data. State chains that fail consistency checks are used as candidate events for distribution network fault detection. This method does not rely on fixed thresholds or the operating parameters of individual nodes. Instead, it detects faults by combining the topology and node connection relationships of the entire distribution network after screening out abnormal operating parameters. This effectively reduces the impact of noise and interference, thereby significantly improving the accuracy of distribution network fault detection. Attached Figure Description

[0016] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating a fault detection method for a low-voltage distribution network provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a fault detection device for a low-voltage power distribution network provided in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] Unless otherwise defined, 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 pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0020] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0021] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0022] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0023] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0024] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0025] See Figure 1To address the technical problem that existing technologies typically rely on fixed thresholds, are easily affected by noise and interference, leading to low accuracy in fault detection, an embodiment of the present invention provides a fault detection method for low-voltage distribution networks, comprising: S1. Collect the operating parameters of key nodes in the target distribution network, and determine anomalies based on the operating parameters, using the abnormal operating parameters as observation data; In this embodiment of the invention, the operating parameters include voltage parameters, current parameters, power parameters, power quality parameters, and harmonic parameters.

[0026] In this embodiment of the invention, a key node refers to a node that has an important function or location in the power distribution network, such as a power supply node, a branch node, and a load node.

[0027] Voltage and current sensors can be installed at key points. The collected signals are converted and conditioned before being input into the acquisition circuit. They are then converted into digital quantities by an analog-to-digital converter to obtain quantitative data such as voltage amplitude, current amplitude, power value, frequency, and harmonic content, forming the basic operating data of the system.

[0028] In this embodiment of the invention, the anomaly determination can be that when the operating parameters exceed a preset threshold range, they are determined to be abnormal operating parameters.

[0029] In this embodiment of the invention, observation data can be shared with adjacent nodes in the distribution network topology, enabling adjacent nodes to obtain each other's observation results, realizing distributed data processing and collaborative decision-making based on local data. By sharing data layer by layer with neighboring nodes, rather than directly aggregating all node data, communication and storage overhead is reduced, while providing continuous observation data support for state chain generation.

[0030] In this embodiment of the invention, the operating parameters determined to be abnormal are used as observation data. Based on the observation data, fault detection is performed on the distribution network. Only the refined observation results need to be uploaded. There is no need to upload continuous sampling waveforms and original spectrum data such as voltage, current, power, power quality and harmonics. This can effectively reduce the need for large-scale uploading of original data and help speed up the response speed of fault detection.

[0031] S2. Construct a structured topology based on the node and branch connection relationships of the target distribution network; S3. Generate a state chain based on the node connection relationship in the structured topology and the observation data, and take the state chain that fails the consistency check as a candidate event; S4. Based on candidate events, perform fault detection to obtain the fault type and fault location of the target distribution network.

[0032] This invention generates observation data by collecting operating parameters of key nodes and determining anomalies. It then generates state chains based on node connections in a structured topology and the observation data. State chains that fail consistency checks are used as candidate events for distribution network fault detection. This method does not rely on fixed thresholds or the operating parameters of individual nodes. Instead, it detects faults by combining the topology and node connections of the entire distribution network after filtering out abnormal operating parameters. This effectively reduces the impact of noise and interference, thereby improving the accuracy of distribution network fault detection.

[0033] In one embodiment, step S1, determining anomalies based on operating parameters and using abnormal operating parameters as observation data, includes: S11. Filter, suppress noise and extract features from the operating parameters to obtain preprocessed data; S12. Based on each operating parameter and its corresponding preset threshold range, anomaly determination is made, and the abnormal operating parameters are used as observation data.

[0034] In this embodiment of the invention, a preset threshold range is set for each operating parameter. When the operating parameter exceeds the preset range, it is determined to be abnormal and an observation result is generated.

[0035] For example, when the voltage amplitude is lower than a certain percentage of the rated value, a voltage drop is detected and a flag is output.

[0036] This invention determines anomalies based on each operating parameter and its corresponding preset threshold range, using abnormal operating parameters as observation data. This effectively reduces the amount of data processing required for fault detection, improving both the response time and accuracy of fault detection.

[0037] In one embodiment, before step S2, generating the state chain based on the node connection relationships in the structured topology and the observation data, the following steps are included: Establish communication links between multiple key nodes, and synchronize and interact observation data among the key nodes based on the communication links.

[0038] In this embodiment of the invention, multiple observation data and corresponding timestamp information can be received, and the observation information and timestamp information can be centrally stored and organized. On this basis, a communication link between multiple key nodes can be established, and observation data can be synchronized and interacted between multiple key nodes according to the communication link, so as to realize collaborative communication between multiple nodes.

[0039] In this embodiment of the invention, a receiving port can be opened at the communication node and a queue or cache can be set up to write data from different sources into a unified database or buffer. The data can be merged and organized according to the measurement point identifier and time index, while the field normalization and format standardization are completed to form an observation data set with consistent structure that can be quickly retrieved by time window. This provides directly callable input for subsequent topology queries and state chain generation, reduces repeated cleaning and alignment work, and improves analysis efficiency.

[0040] In one embodiment, step S3, generating a state chain based on the node connection relationships in the structured topology and the observation data, includes: S31. Within a preset time window, perform timestamp comparison and synchronization processing on multiple observation data to obtain synchronized observation data. In this embodiment of the invention, multiple observation data are compared and synchronized within a preset time window. That is, different observation results are arranged in the order of timestamps, and data with deviations are corrected by interpolation or discarding. This ensures that the data of each node are aligned under a unified time reference, avoiding analysis errors caused by asynchronous sampling.

[0041] S33. Based on the node connection relationship in the structured topology, the synchronized observation data are associated according to the propagation path to generate a state chain.

[0042] In this embodiment of the invention, based on the node connection relationships in the structured topology and the synchronized observation data, the synchronized observation data can be associated in the upstream and downstream order of the power grid propagation path to generate a state chain representing the state transmission path. In this process, the connection information of nodes and branches can be obtained from the knowledge graph, and the observation results that conform to the topological order can be combined in sequence to form a chain-like data sequence, thereby realizing the unified integration of scattered observations, reproducing the propagation process of electrical quantities in the topology, and thus providing a clear description of the abnormal propagation path.

[0043] For example, within a preset time window at a certain moment, nodes A, B, C, and D report their respective observation results. Node A is located at the outlet of the distribution transformer, nodes B and C are located on the downstream branches of A, and node D is located downstream of C. After timestamp alignment, it is found that node A first experiences a current surge, followed by nodes B, C, and D successively detecting voltage drops. Based on the upstream and downstream connections in the topology knowledge graph, these observation results are sequentially associated to form a state chain from node A to node D. At the same time, within the same time window, nodes E and F also detect voltage fluctuations, but they are not on the same path as nodes A and D. The system will generate another EF state chain separately based on the topology relationship. Thus, multiple observation data sets can generate multiple state chains, each chain corresponding to a possible anomaly propagation path.

[0044] In one embodiment, a consistency analysis can also be performed on the generated state chain to verify the degree of matching between the observed data of each node in the state chain in terms of amplitude changes and temporal propagation. The consistency scoring formula can be set as follows: ; in, For consistency scoring, The number of nodes in the state chain. For the first Node voltage change. For the first Node timestamp, The theoretical propagation time interval between adjacent nodes is calculated. The value is compared with a threshold. When the consistency check of the chain fails (e.g., the C value is greater than the threshold), the state chain is marked as abnormal and identified as a candidate event. This quantitative indicator is used to screen state chains that conform to the propagation law, thereby improving the accuracy and reliability of candidate events and the accuracy of distribution network fault detection.

[0045] In one embodiment, after step S3, which involves constructing a structured topology based on the node and branch connection relationships of the target distribution network, the method further includes: When the operating status or network structure of the distribution network changes, the node and branch information in the structured topology is updated.

[0046] In this embodiment of the invention, the nodes, branches and their connections in the distribution network are recorded and stored in a structured form as a knowledge graph. When the operating status or network structure of the distribution network changes, the node and branch information in the knowledge graph is updated.

[0047] In this embodiment of the invention, nodes and branches can be abstracted as points and edges in a graph model. During storage, each node is configured with a unique identifier, device attributes, and information about the branches connected to it. This allows complex power grid topology relationships to be stored in a unified form in the database, intuitively representing the network structure of the power grid and establishing a reliable data foundation for subsequent topology queries and invocations.

[0048] When the operating status or network structure of the distribution network changes, the node and branch information in the knowledge graph is updated. For example, when a new user is connected, a line is upgraded, or a switch operation occurs, the new node is inserted into the knowledge graph, or the existing node and branch relationships are modified to ensure that the knowledge graph always remains consistent with the actual power grid structure and to avoid analysis deviations caused by the lag in topology data.

[0049] In one embodiment, step S4, fault detection based on candidate events to obtain the fault type and fault location of the target distribution network, includes: S41. Use a pre-built machine learning model to perform feature analysis and fault detection on candidate events to determine the fault type of the distribution network; In this embodiment of the invention, before step S41, anomaly detection can be performed on candidate events based on preset electronic parameter thresholds and topology rules. For example, features such as voltage, current, power, frequency, and harmonic content from the state chain can be compared with thresholds. For example, when the voltage amplitude is lower than 80% of the rated value or the current amplitude exceeds 150% of the rated value, it is determined to be abnormal. At the same time, the topology relationship is combined to determine whether there are corresponding related changes in upstream and downstream nodes, quickly eliminating normal fluctuation data and performing initial screening of anomalies. The effect is to improve the accuracy of subsequent identification.

[0050] In this embodiment of the invention, a machine learning model can be trained using historical candidate events obtained from historical data and their corresponding labels as training data.

[0051] In this embodiment of the invention, the multidimensional feature vectors of candidate events can be input into a trained classification model, such as an artificial intelligence model, to identify and determine the type of the event candidates. The artificial intelligence model includes machine learning models such as support vector machines and neural networks, used to automatically classify and determine abnormal patterns based on features such as voltage, current, power, and harmonics. Then, the event type is determined based on the probability results output by the model, as expressed below: ; in, It is an eigenvector composed of voltage change, current change, power deviation, frequency offset, and harmonic distortion rate. Label the event category (e.g., short circuit, overload, harmonic pollution). The trained model parameters are used to identify specific anomaly patterns from complex observation features, thereby completing anomaly type identification and improving classification accuracy and generalization ability.

[0052] S42. Determine the fault node based on the structured topology relationship to obtain the fault location corresponding to the current fault type.

[0053] In this embodiment of the invention, the current fault type can be combined with the node and branch relationships in the structured topology to find the node that first shows an anomaly in the anomaly propagation path as the fault location. For example, when multiple downstream nodes experience voltage drops while upstream nodes simultaneously experience current surges, the location result will point to that branch or node, achieving precise spatial positioning and narrowing the fault range to a specific node or branch, thereby providing a basis for rapid isolation and repair.

[0054] In one embodiment, after step S4, which involves fault detection based on candidate events to obtain the fault type and location of the target distribution network, the method further includes: S5. Generate visual information on operating status and fault distribution based on fault type and fault location.

[0055] In this embodiment of the invention, the graphical interface uses the power grid topology diagram as the background and dynamically marks the operating parameters, state chains, and fault locations to intuitively display the operating status.

[0056] This invention can also invoke a digital twin model to verify the fault location results. When the verification meets the conditions, a control command is issued to the field switching equipment for fault isolation and recovery. The digital twin model can establish a virtual topology and operating parameter model corresponding to the distribution network, receive observation data and location results, perform power flow calculations or fault calculations in a simulation environment, verify the consistency of the fault location results, and trigger a control command when the verification results meet preset conditions.

[0057] In one embodiment, the received observation data, state chain information, and fault location results can also be stored and classified for management. For example, an index can be created based on timestamps, node identifiers, and event types to divide the data into real-time data and historical data, and then archived according to the station area or equipment number.

[0058] Implementing the embodiments of the present invention has the following beneficial effects: This invention generates observation data by collecting operating parameters of key nodes and determining anomalies. It then generates state chains based on the node connection relationships in the structured topology and the observation data. State chains that fail consistency checks are used as candidate events for distribution network fault detection. This method does not rely on fixed thresholds or the operating parameters of individual nodes. Instead, it detects faults by combining the topology and node connection relationships of the entire distribution network after screening out abnormal operating parameters. This effectively reduces the impact of noise and interference, thereby significantly improving the accuracy of distribution network fault detection.

[0059] Furthermore, in this embodiment of the invention, when the operating status or network structure of the distribution network changes, the node and branch information in the knowledge graph is updated to ensure that the knowledge graph always remains consistent with the actual power grid structure and to avoid analysis deviations caused by the lag in topology data.

[0060] like Figure 2 As shown, based on the above method embodiments, corresponding apparatus embodiments are provided; One embodiment of the present invention provides a fault detection device for a low-voltage distribution network, comprising: The observation data determination module 10 is used to collect the operating parameters of key nodes in the target distribution network, and to determine anomalies based on the operating parameters, using the abnormal operating parameters as observation data. The topology construction module 20 is used to construct a structured topology based on the node and branch connection relationships of the target distribution network. The state chain generation module 30 is used to generate state chains based on the node connection relationships in the structured topology and the observation data, and to take the state chains that fail the consistency check as candidate events. The fault detection module 40 is used to perform fault detection based on candidate events to obtain the fault type and fault location of the target distribution network.

[0061] In one embodiment, anomaly detection is performed based on operating parameters, and abnormal operating parameters are used as observation data, including: The operating parameters are filtered, noise is suppressed, and features are extracted to obtain preprocessed data. Anomalies are determined based on each operating parameter and its corresponding preset threshold range, and the abnormal operating parameters are used as observation data.

[0062] In one embodiment, before generating the state chain based on the node connectivity relationships in the structured topology and the observation data, the following steps are included: Establish communication links between multiple key nodes, and synchronize and interact observation data among the key nodes based on the communication links.

[0063] In one embodiment, after constructing the structured topology based on the node and branch connection relationships of the target distribution network, the method further includes: When the operating status or network structure of the distribution network changes, the node and branch information in the structured topology is updated.

[0064] In one embodiment, generating a state chain based on node connectivity in a structured topology and observation data includes: Within a preset time window, timestamps of multiple observation data are compared and synchronized to obtain synchronized observation data. Based on the node connection relationships in the structured topology, the synchronized observation data are associated according to the propagation path to generate a state chain.

[0065] In one embodiment, fault detection based on candidate events yields the fault type and location of the target distribution network, including: A pre-built machine learning model is used to perform feature analysis and fault detection on candidate events to determine the fault type of the distribution network; The fault node is determined based on the structured topology, and the fault location corresponding to the current fault type is obtained.

[0066] In one embodiment, after obtaining the fault type and fault location of the target distribution network based on candidate events for fault detection, the method further includes: Based on the fault type and fault location, visualized information on operating status and fault distribution is generated respectively.

[0067] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention, and can implement the fault detection method for low-voltage distribution networks provided by any of the above-described method embodiments of the present invention.

[0068] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0069] Based on the above embodiments of the fault detection method for low-voltage distribution networks, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the fault detection method for low-voltage distribution networks of any embodiment of the present invention.

[0070] For example, in this embodiment, the computer program can be divided into one or more modules, one or more modules are stored in memory and executed by a processor to complete the present invention. One or more module elements can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in a terminal device.

[0071] Terminal devices can be computing devices such as desktop computers, laptops, handheld computers, and cloud servers. Terminal devices may include, but are not limited to, processors and memory.

[0072] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device through various interfaces and lines.

[0073] Based on the above-described method embodiments, another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute the fault detection method for low-voltage distribution networks according to any of the above-described method embodiments of the present invention.

[0074] The modules / units integrated into the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0075] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A fault detection method for a low-voltage distribution network, characterized in that, include: Collect operating parameters of key nodes in the target distribution network, and determine anomalies based on the operating parameters, using the abnormal operating parameters as observation data; Based on the node and branch connection relationships of the target distribution network, a structured topology is constructed; A state chain is generated based on the node connection relationships in the structured topology and the observation data, and the state chain that fails the consistency check is taken as a candidate event. Fault detection is performed based on the candidate events to obtain the fault type and fault location of the target distribution network.

2. The fault detection method for low-voltage distribution networks as described in claim 1, characterized in that, The step of determining anomalies based on the operating parameters, and using the abnormal operating parameters as observation data, includes: The operating parameters are filtered, noise suppressed, and feature extracted to obtain preprocessed data; Anomalies are determined based on each operating parameter and its corresponding preset threshold range, and the abnormal operating parameters are used as observation data.

3. The fault detection method for low-voltage distribution networks as described in claim 1, characterized in that, Before generating the state chain based on the node connection relationships in the structured topology and the observation data, the process includes: Establish communication links between multiple key nodes, and synchronize and interact observation data among the multiple key nodes based on the communication links.

4. The fault detection method for low-voltage distribution networks as described in claim 1, characterized in that, After constructing the structured topology based on the node and branch connection relationships of the target distribution network, the process also includes: When the operating status or network structure of the distribution network changes, the node and branch information in the structured topology is updated.

5. The fault detection method for low-voltage distribution networks as described in claim 1, characterized in that, The step of generating a state chain based on the node connection relationships in the structured topology and the observation data includes: Within a preset time window, timestamp comparison and synchronization processing are performed on multiple observation data to obtain synchronized observation data; Based on the node connection relationships in the structured topology, the synchronized observation data are associated according to the propagation path to generate a state chain.

6. The fault detection method for low-voltage distribution networks as described in claim 1, characterized in that, The step of fault detection based on the candidate events to obtain the fault type and fault location of the target distribution network includes: A pre-built machine learning model is used to perform feature analysis and fault detection on the candidate events to determine the fault type of the distribution network. Based on the structured topology, the fault node is determined, and the fault location corresponding to the current fault type is obtained.

7. The fault detection method for low-voltage distribution networks as described in claim 1, characterized in that, After performing fault detection based on the candidate events to obtain the fault type and fault location of the target distribution network, the process further includes: Based on the fault type and the fault location, visualized information on operating status and fault distribution is generated respectively.

8. A fault detection device for a low-voltage distribution network, characterized in that, include: The observation data determination module is used to collect the operating parameters of key nodes in the target distribution network, and to determine anomalies based on the operating parameters, using the abnormal operating parameters as observation data. The topology construction module is used to construct a structured topology based on the node and branch connection relationships of the target distribution network. The state chain generation module is used to generate a state chain based on the node connection relationship in the structured topology and the observation data, and to take the state chain that fails the consistency check as a candidate event. The fault detection module is used to perform fault detection based on the candidate events to obtain the fault type and fault location of the target distribution network.

9. A terminal device, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the fault detection method for a low-voltage distribution network as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, include: A stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform the fault detection method for a low-voltage distribution network as described in any one of claims 1-7.

Images