Fault line section positioning method and device of power distribution network, equipment and storage medium

Abstract

The invention relates to the technical field of distribution networks, and discloses a fault line section positioning method, device and equipment of a power distribution network and a storage medium, and the method comprises the steps: receiving signal information sent by each fault indicator; detecting whether at least one fault indicator in the signal information sends out an alarm signal or not; if at least one fault indicator emits an alarm signal, constructing an alarm vector according to the signal information; and calculating a fault line section in each line section based on the alarm vector. The method has the beneficial effects that the time of non-planned power failure caused by faults is shortened, the real-time response capability of maintenance personnel to the faults is also improved, the faults can be eliminated more quickly, potential faults can be captured in time, the fault prevention capability is improved, the operation safety of the power distribution network is ensured by an effective monitoring mechanism, and the power distribution network safety is improved. And the long-time outage risk and the economic loss caused by the long-time outage risk are reduced.

Description

Technical Field

[0001] This invention relates to the field of power distribution network technology, and in particular to a method, apparatus, equipment and storage medium for locating faulty line sections in a power distribution network. Background Technology

[0002] As a crucial component of the power system, the distribution network plays a vital role in reliably and efficiently delivering electrical energy to users. With the continuous expansion of the distribution network and the increasing complexity of its operating environment, the probability of various faults is also gradually rising. Among these, hidden faults (such as intermittent grounding, transient discharges caused by insulator deterioration, and localized overheating) pose significant challenges to operation and maintenance work due to their inconspicuous fault characteristics and difficulty in direct detection. Traditional methods for locating distribution network faults mainly rely on relay protection, fault indicators (FI), and manual inspection. Relay protection can effectively identify obvious faults such as short circuits and permanent grounding, but its detection capability for hidden faults is limited, and it is difficult to accurately determine the fault section. While fault indicators can provide fault alarm information, in the early stages of hidden faults, the fault current is often small, making it difficult to trigger an alarm and resulting in delayed fault detection. Furthermore, manual inspection relies on the experience of maintenance personnel, which is not only inefficient but may also lead to misjudgments or missed diagnoses due to the uncertainty of fault characteristics. In recent years, with the development of intelligent technologies, waveform recording equipment has been widely used in distribution network operation monitoring. Waveform recording equipment can acquire electrical quantity information such as current and voltage with high time resolution and record transient waveforms at the time of fault occurrence, providing detailed data support for fault analysis. However, existing waveform data analysis methods are mainly used for identifying typical faults such as short circuits and grounding faults, and there is still a lack of effective algorithms and means for detecting hidden faults. In addition, existing fault location methods based on waveform recording usually rely on obvious waveform distortion or current abrupt changes, while the characteristics of hidden faults are relatively weak, making existing methods difficult to apply to the section location of hidden faults in distribution networks. Therefore, there is an urgent need for a fault section location method based on distribution networks. Summary of the Invention

[0003] Based on this, it is necessary to propose a method, device, equipment and storage medium for locating faulty line sections in existing distribution networks.

[0004] A method for locating faulty line sections in a distribution network, the distribution network comprising multiple line sections, each line section being equipped with a fault indicator, the method comprising: Receive signal information sent by each of the fault indicators; Detect whether the signal information contains at least one of the fault indicators issuing an alarm signal; If at least one of the fault indicators issues an alarm signal, an alarm vector is constructed based on the signal information; The faulty line segment in each of the line segments is calculated based on the alarm vector.

[0005] Furthermore, before the step of receiving the signal information sent by each of the fault indicators, the method further includes: Obtain the network topology of the power distribution network; A line segment fault relationship matrix is ​​constructed based on the network topology; wherein, the line segment fault relationship matrix is ​​used to calculate faulty line segments.

[0006] Further, the step of calculating the faulty line segment in each of the line segments based on the alarm vector includes: The fault relationship matrix of the line section is divided into blocks according to the columns to obtain multiple block vectors; Each of the segmented vectors is compared with the alarm vector to obtain the faulty line segment.

[0007] Further, the step of constructing an alarm vector based on the signal information if at least one of the fault indicators issues an alarm signal includes: If at least one of the fault indicators issues an alarm signal, then the network topology of the distribution network and the target fault indicator that issued the alarm signal in the signal information are obtained. Based on the target fault indicator and the network topology, the fault current flow is determined; Detect whether a fault has occurred in the line section downstream of the target fault indicator based on the direction of the fault current; If a fault occurs in a downstream line section, the fault indicator corresponding to the downstream line section will be marked as the target fault indicator that will issue an alarm signal. The signal information is regenerated based on the target fault indicator, and the alarm vector is constructed.

[0008] Further, the step of constructing an alarm vector based on the signal information if at least one of the fault indicators issues an alarm signal includes: If at least one of the fault indicators issues an alarm signal, then the network topology of the distribution network and the target fault indicator that issued the alarm signal in the signal information are obtained. Based on the target fault indicator and the network topology, the fault current flow is determined; Based on the direction of the fault current, determine whether all fault indicators upstream of the target fault indicator have issued alarm signals. If no alarm signal is issued, all fault indicators upstream of the target fault indicator will be marked as the target fault indicator that issued the alarm signal. The signal information is regenerated based on the target fault indicator, and the alarm vector is constructed.

[0009] Furthermore, before the step of receiving the signal information sent by each of the fault indicators, the method further includes: Obtain the circuit nodes of the power distribution network; A line segment is determined based on two adjacent circuit nodes; A fault indicator is set for each of the aforementioned line sections.

[0010] Furthermore, the fault indicator is one of a current-type fault indicator, a voltage-type fault indicator, and a combined fault indicator.

[0011] Further, the step of constructing an alarm vector based on the signal information if at least one of the fault indicators issues an alarm signal includes: If at least one of the fault indicators issues an alarm signal, then waveform data for each of the line sections is obtained based on the signal information. The hidden features in the recorded waveform data are extracted according to a preset neural network model; The alarm vector is constructed based on the concealment characteristics and the signal information.

[0012] Furthermore, after the step of constructing the line segment fault relationship matrix based on the network topology, the method further includes: Real-time monitoring of whether the network topology of the power distribution network is updated; If the network topology of the power distribution network is updated, the updated target network topology is obtained. Based on the target network topology, the fault relationship matrix of the line segments is reconstructed.

[0013] A fault line section location device for a power distribution network, the power distribution network including multiple line sections, each line section being equipped with a fault indicator, the device comprising: The receiving module is used to receive signal information sent by each of the fault indicators; The detection module is used to detect whether the signal information contains at least one of the fault indicators issuing an alarm signal; A construction module is configured to construct an alarm vector based on the signal information if at least one of the fault indicators issues an alarm signal. The calculation module is used to calculate the faulty line section in each of the line sections based on the alarm vector.

[0014] A computer device includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the following steps: Receive signal information sent by each of the fault indicators; Detect whether the signal information contains at least one of the fault indicators issuing an alarm signal; If at least one of the fault indicators issues an alarm signal, an alarm vector is constructed based on the signal information; The faulty line segment in each of the line segments is calculated based on the alarm vector.

[0015] A computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the following steps: Receive signal information sent by each of the fault indicators; Detect whether the signal information contains at least one of the fault indicators issuing an alarm signal; If at least one of the fault indicators issues an alarm signal, an alarm vector is constructed based on the signal information; The faulty line segment in each of the line segments is calculated based on the alarm vector.

[0016] The beneficial effects of this invention are as follows: By centrally processing and comprehensively analyzing all fault indicator signal data, the location of the fault can be accurately identified. This not only reduces the unplanned power outage time caused by the fault, but also improves the real-time response capability of maintenance personnel to the fault, making fault troubleshooting more rapid. It can also continuously monitor the operating status of the line segment, capture potential faults in a timely manner, thereby improving fault prevention capabilities. The effective monitoring mechanism ensures the safe operation of the distribution network and reduces the risk of long-term outages and the resulting economic losses. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] in: Figure 1 This is an application environment diagram of a fault line section location method in a distribution network in one embodiment; Figure 2 This is a flowchart of a method for locating faulty line sections in a distribution network, as shown in one embodiment. Figure 3 This is a schematic diagram of a simulation model with a fault in one embodiment; Figure 4 This is a schematic diagram of a simulation model of a power distribution network in one embodiment; Figure 5 This is a structural block diagram of a fault line section location device in a distribution network according to one embodiment; Figure 6 This is a structural block diagram of a computer device in one embodiment. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Figure 1 This is an application environment diagram for locating faulty line sections in a distribution network in one embodiment. (Refer to...) Figure 1 The fault line section location method for this distribution network is applied to a fault line section location system for the distribution network. This fault line section location system includes a terminal 110 and a server 120. The terminal 110 and server 120 are connected via a network. The terminal 110 can be a desktop terminal or a mobile terminal; the mobile terminal can be at least one of a mobile phone, tablet, or laptop. The server 120 can be a standalone server or a server cluster consisting of multiple servers. The terminal 110 is used to receive signal information, and the server 120 is used to analyze the fault line section.

[0021] like Figure 2 As shown, in one embodiment, a method for locating faulty line sections in a distribution network is provided. This method can be applied to both terminals and servers; this embodiment uses server application as an example. The distribution network includes multiple line sections, each equipped with a fault indicator. The method for locating faulty line sections in this distribution network specifically includes the following steps: S1: Receive signal information sent by each of the fault indicators; S2: Detect whether the signal information contains at least one of the fault indicators issuing an alarm signal; S3: If at least one of the fault indicators issues an alarm signal, then an alarm vector is constructed based on the signal information; S4: Calculate the faulty line segment in each of the line segments based on the alarm vector.

[0022] As described in step S1 above, signal information is received from each of the fault indicators. Signal information is received from multiple fault indicators in the power distribution network. A fault indicator is a device that monitors power lines in real time, collecting data on current, voltage, and power quality through sensors. When the device detects an abnormality, it issues an alarm signal and collects the status information of all fault indicators, providing a basis for subsequent fault location. This information can be digital signals, analog signals, or the status information of the fault indicator itself (such as the time, location, and severity of the fault). The collected information needs to be sent to the control center via a communication network. The control center typically processes and analyzes the data from each indicator centrally, laying the data foundation for accurately locating the fault point. The timely reception and accuracy of the information directly affect the efficiency and accuracy of subsequent fault determination.

[0023] As described in step S2 above, the system detects whether at least one fault indicator has issued an alarm signal in the signal information. Upon receiving a signal from a fault indicator, the system needs to perform information discrimination to check if at least one fault indicator has issued an alarm signal. If the signal information contains an alarm signal, this indicates a fault or abnormality in a section of the distribution network. Detecting whether at least one fault indicator has issued an alarm signal in the signal information is a prerequisite for further fault location. If no indicator issues an alarm signal, it indicates that the current distribution network is operating normally, and the fault location process can be suspended. Conversely, if an alarm signal exists, fault location needs to continue. If a certain number of alarms are detected, they may be classified according to their alarm level, and subsequent maintenance work may be prioritized based on their importance. This effectively filters out fault information that requires attention, thereby improving the efficiency of fault handling.

[0024] As described in step S3 above, if at least one of the fault indicators issues an alarm signal, an alarm vector is constructed based on the signal information. Once an alarm signal is confirmed, the system constructs an alarm vector based on the received signal information. This step converts the state information of each fault indicator into a multi-dimensional vector for subsequent analysis and processing. The state information includes various information, such as the fault indicator number, alarm type (e.g., short circuit, overload, ground fault, etc.), occurrence time, signal strength, etc. Then, an alarm vector is generated based on the state information of each fault indicator, enabling the system to effectively integrate the state information from different indicators during fault location, which helps to identify and assess the severity and nature of the fault. In another embodiment, the state information of each fault indicator may simply be that an alarm signal has been issued or that no alarm signal has been issued. That is, the alarm vector specifically represents the alarm status of each fault indicator. Specifically, the state information corresponding to a fault indicator that issues an alarm signal can be recorded as 1, and the state information corresponding to a fault indicator that does not issue an alarm signal can be recorded as 0. This process not only greatly simplifies subsequent data processing but also improves the accuracy and efficiency of location. By forming a standardized representation of signal information, the system can more easily perform algorithmic calculations and achieve accurate identification of fault areas.

[0025] As described in step S4 above, the faulty line segment in each of the line sections is calculated based on the alarm vector. After the alarm vector is constructed, related calculations and analyses can be performed based on the vector to determine the line segment where the fault occurs. Various algorithms can be used to analyze the alarm vector, common methods include fault location algorithms, fuzzy logic, and data mining techniques. These algorithms can process and analyze complex information from multiple lines, infer possible fault paths, and thus accurately identify the specific line segment where the fault occurs. During the analysis process, the system considers the strength, quantity distribution, and other parameters of the alarm signal to provide a scientific basis for fault location. This analysis process not only improves the speed and accuracy of fault location but also provides important information support for subsequent maintenance and recovery operations. In one embodiment, a line segment fault relationship matrix can be pre-constructed based on the set distribution network topology, and then the alarm vector is compared with each column in the line segment fault relationship matrix to obtain the faulty line segment. Ultimately, the faulty line segment will be clearly identified, helping maintenance personnel to quickly and safely locate the fault, improving the sensitivity and accuracy of fault identification.

[0026] In one embodiment, before step S1 of receiving signal information sent by each of the fault indicators, the method further includes: S001: Obtain the network topology of the power distribution network; S002: Construct a line segment fault relationship matrix based on the network topology; wherein, the line segment fault relationship matrix is ​​used to calculate faulty line segments.

[0027] As described in steps S001-S002 above, understanding the network topology of the distribution network is crucial before fault location. This step lays the foundation for subsequent fault analysis and handling. The network topology describes the connection relationships between various components (such as transformers, switches, lines, and fault indicators). This is achieved through database queries or system modeling tools. By accurately understanding the network topology, the system can draw an overall structural diagram of the distribution network, identifying the specific locations and connections of each line and device. Understanding the distribution network topology is essential for fault location because the impact of different line segments and devices on faults is interconnected. If a line fails, surrounding lines may be affected, and these effects may lead to faults in other areas. Therefore, obtaining the network topology before starting fault detection not only provides visual information but also provides important spatial and logical basis for subsequent data processing. This information will be used to construct a fault relationship matrix, thereby helping the system more effectively analyze the path and area of ​​fault occurrence. After obtaining the network topology, the next step is to construct a line segment fault relationship matrix. This matrix is ​​a mathematical tool that effectively describes the fault relationships between different line segments in the distribution network. The process of constructing a fault relationship matrix involves abstracting the relationship between each line segment and its adjacent line segments into a matrix form. For example, the construction of the relationship matrix... The fault indicator FI and line sections are numbered sequentially from upstream to downstream. Assume the distribution network has... One fault indicator, details are as follows: In the above formula, the first... The meaning represented by the line is: when the upstream line is the first When a fault indicator issues an alarm signal, the fault status of each line section is displayed, specifically: An alarm vector is established using FI alarm information and fault current flow direction, i.e. This is used to characterize the actual alarm status of each fault indicator (FI) after a fault occurs in the distribution network. The specific construction process is as follows: First, based on the alarm signals directly observed on-site, a preliminary alarm vector is constructed. During this process, if the fault indicator... Issue an alarm. If the i-th fault indicator is represented, then the corresponding If no police report is filed, then The second step, considering the possibility of missed alarm messages from fault indicators in actual situations, involves combining the relationship matrix with the alarm vector... Information corrections are performed to obtain alarm vectors, thereby improving the accuracy of the alarm vectors.

[0028] Specifically, when a fault occurs on a line, the matrix can be used to assess whether connected lines are also affected. This relationship matrix provides crucial information for subsequent fault location; by analyzing the fault relationship matrix, the system can quickly identify potentially affected areas. For example, if an alarm signal is issued for a specific line section, the system will consult the fault relationship matrix to examine other connected sections, thereby uncovering potential fault areas. This approach not only improves the efficiency of fault location but also reduces delays in fault handling caused by human error. Overall, the establishment of the fault relationship matrix makes fault analysis more systematic and scientific, playing a crucial role in ensuring the reliability and security of the distribution network.

[0029] In one embodiment, step S4, which calculates the faulty line segment in each of the line segments based on the alarm vector, includes: S401: Divide the fault relationship matrix of the line section into blocks according to the columns to obtain multiple block vectors; S402: Compare each of the block vectors with the alarm vector to obtain the faulty line section.

[0030] As described in steps S401-S402 above, the constructed line segment fault relationship matrix is ​​processed. Specifically, the first step of this processing is to divide the fault relationship matrix into blocks according to columns, forming multiple block vectors. The fault relationship matrix essentially describes the fault connections between various line segments in the distribution network. Each column corresponds to a specific line segment, while each row represents the reliability and potential fault impact of other line segments on this line segment. Therefore, each column of the matrix provides fault impact information for each line segment relative to other lines. By dividing the matrix columns into blocks, the system extracts the fault impact information of each line segment into block vectors. The purpose of this operation is to prepare for subsequent comparative analysis, ensuring that each line segment corresponds one-to-one with an alarm vector. After dividing the matrix into blocks, the complexity of the analysis can be effectively simplified, allowing the system to focus on the fault nature and state of each specific line segment. This block-based approach is very helpful in ensuring the organization of data and the logic of analysis when applied to complex system analysis, thus providing a clear basis for the next step of comparison. After completing the column block division, the obtained block vectors are compared with the previously constructed alarm vectors. The alarm vector contains all alarm information issued by the fault indicator, reflecting the overall current fault status. Each block vector represents the fault relationship and status of its corresponding line segment. By comparing the block vectors with the alarm vectors one by one, the system can identify which line segments have fault relationships that highly match the current alarm information. This matching can be achieved through various methods, such as using matching functions, correlation coefficient calculations, and logical judgments, with the optimal choice made based on the specific algorithm design. If a block vector and an alarm vector show significant similarity or consistency in a certain feature, it indicates that the line segment may be faulty. Ultimately, through comparative analysis, the system can accurately identify which line segments are faulty. This not only helps to quickly and accurately locate faults, improves response time, and reduces the impact on power supply, but also provides clear objectives for subsequent maintenance and repair work, optimizing the allocation and scheduling of maintenance resources.

[0031] In one embodiment, step S3, which involves constructing an alarm vector based on the signal information if at least one of the fault indicators issues an alarm signal, includes: S301: If at least one of the fault indicators issues an alarm signal, then obtain the network topology of the power distribution network and the target fault indicator that issued the alarm signal in the signal information. S302: Determine the fault current flow based on the target fault indicator and the network topology; S303: Detect whether a fault has occurred in the line section downstream of the target fault indicator based on the fault current direction; S304: If a fault occurs in a downstream line section, the fault indicator corresponding to the downstream line section will be marked as the target fault indicator that will issue an alarm signal. S305: Regenerate signal information based on the target fault indicator and construct the alarm vector.

[0032] As described in steps S301-S305 above, when it is confirmed that at least one fault indicator has issued an alarm signal, the network topology of the distribution network is obtained. The network topology helps to understand the spatial and logical relationships between various line sections. It provides a framework for subsequent fault analysis. Furthermore, it is necessary to determine which fault indicators are the target fault indicators issuing alarm signals. These target fault indicators play a crucial role in the power system; they are the sources of fault signals, indicating potential power anomalies. By recording the fault indicators that have issued alarm signals, the system can focus its attention and conduct more in-depth analysis. After identifying the target fault indicators and the network topology, the system begins to analyze the flow of fault current. This process is key to understanding the fault occurrence mechanism; the flow of fault current is usually related to the fault location and its impact on the distribution network. By applying the network topology, the system can deduce the flow path of fault current using circuit analysis methods. For example, when a short circuit or overload occurs, current will flow through the line according to a certain electrical path; past current flow directions and equipment characteristics are used as the basis for analysis. Identifying the line segments where the fault current might flow is crucial, as these segments are likely the source or affected area of ​​the fault. Understanding the fault current's trajectory allows the system to more accurately pinpoint the fault area, providing a basis for subsequent location analysis. Without a clear current trajectory, subsequent analysis and fault identification become significantly more complex. After determining the fault current's trajectory, the system monitors the line segments downstream of the target fault indicator. The goal of this monitoring is to determine which downstream line segments might also be affected by the fault. Since current typically flows along a specific path during a fault, the state of downstream line segments is directly related to the fault current characteristics. By monitoring fault indicators on downstream lines and through real-time signal acquisition and historical data analysis, the system can determine whether these lines have experienced a fault. This process can be conducted in various ways, such as using electrical parameter (voltage, current) monitoring and sensor data collection. Once a fault is detected in a downstream line segment, the system must be able to quickly locate these lines for subsequent analysis and processing. If no fault is found in the downstream line segment, the system may trace upstream to further investigate the cause of the fault. Therefore, this step helps the system gain a comprehensive understanding of the fault, supporting the subsequent construction of fault labeling and alarm vectors. After detecting a fault in a line segment downstream of a target fault indicator, the corresponding fault indicators for these downstream line segments are marked as new alarm signal sources. This labeling process is a crucial step in continuously expanding the fault correlation. In the distribution network, fault indicators can not only monitor their own line segments but also interact and provide feedback to equipment in adjacent line segments. By associating fault indicators with the upstream and downstream lines where the fault occurred, the system can comprehensively depict the fault chain.This process not only involves timely fault labeling and continuous alarm signal updates, but also helps maintenance personnel understand the scope of the fault during subsequent maintenance. This labeling strategy ensures that the system can "go deep layer by layer," accurately identifying the root cause of the fault and its direct impact, enabling maintenance personnel to effectively take measures for handling and repair. This not only improves the speed of fault response but also optimizes the allocation of maintenance resources to ensure the safety and stability of power supply. After labeling the downstream line faults, the next step is to regenerate the signal information based on the information from the target fault indicator and construct the final alarm vector. This process integrates and standardizes the information collected and analyzed in the previous steps, forming an easily processed vector format. The alarm vector typically includes the latest status information of different fault indicators, including the time of alarm issuance, fault type, scope of impact, and level. After integration, this information provides a unified data format for subsequent fault analysis and location.

[0033] When constructing new alarm vectors, the system needs to consider the state changes of all target fault indicators and the alarm responses under different fault conditions. This process not only focuses on the accuracy and completeness of the data but also ensures that it can be easily transmitted and analyzed within the system. This also guarantees that fault diagnosis and corresponding decisions in subsequent steps can be carried out smoothly with accurate data transmission. By generating structured alarm vectors, the system can achieve intelligent response and dynamic adjustment, significantly improving fault response capabilities and operational efficiency.

[0034] In one embodiment, step S3, which involves constructing an alarm vector based on the signal information if at least one of the fault indicators issues an alarm signal, includes: S311: If at least one of the fault indicators issues an alarm signal, then obtain the network topology of the power distribution network and the target fault indicator that issued the alarm signal in the signal information. S312: Determine the fault current flow based on the target fault indicator and the network topology; S313: Determine whether all fault indicators upstream of the target fault indicator have issued alarm signals based on the fault current flow. S314: If no alarm signal is issued, all fault indicators upstream of the target fault indicator will be marked as target fault indicators that have issued alarm signals. S315: Regenerate signal information based on the target fault indicator and construct the alarm vector.

[0035] As described in steps S311-S315 above, after confirming that at least one fault indicator has issued an alarm signal, it is necessary to obtain the network topology of the distribution network. This topology includes the connection relationships of all devices and lines, as well as their locations within the distribution network. Mastering this information is crucial for subsequent fault analysis. Furthermore, the system needs to identify which fault indicators are the "target fault indicators" for this analysis, i.e., those devices that first issued alarm signals. Obtaining the status of the target fault indicators and their locations within the network will lay the foundation for subsequent analysis of the fault current flow. The effectiveness of this step directly affects the accuracy of subsequent fault location and handling, ensuring that the system can comprehensively understand the possible causes and extent of the fault based on a clear network layout. By analyzing the network topology, the system next needs to determine the flow of the fault current, i.e., the path the current may follow along the lines when a fault occurs. Determining the fault current flow is a core aspect of fault analysis because it affects how the fault propagates and other lines or devices that may be affected. Typically, when a device fails, the fault current flows within the network along the path of least resistance according to electrical theory; therefore, understanding this path helps identify potential fault areas. After clarifying the fault current flow, the next step of the system is to check all relevant fault indicators upstream of the target fault indicator to determine if they have all issued alarm signals. If some fault indicators upstream of the target fault indicator were not detected in the previous step, the system needs to mark these upstream fault indicators as new target fault indicators. New signal information is generated based on the current target fault indicators and integrated to construct an alarm vector. The construction of the alarm vector is not only a process of organizing and marking the acquired data, but also the formation of a standard data structure that can be effectively used for fault location and analysis. This alarm vector should comprehensively consider the status information of all target fault indicators, including their alarm time, fault type, possible impact range, and relationships. The generated alarm vector will become the basis for subsequent fault analysis and judgment; its accuracy and completeness will directly affect the efficiency and accuracy of subsequent fault location. Therefore, special attention to information organization and standardization is crucial in this process. Through the integrated information, the system can achieve a deeper understanding of the fault cause and provide a faster and more scientific response strategy. This step not only ensures the rapid recovery of power system operation but also helps to improve the intelligence level of fault management tools, thereby enhancing the overall stability of the distribution network.

[0036] In one specific embodiment, reference is made to Figure 3If the downstream fault indicator F3 issues an alarm signal, but its upstream associated fault indicator F2 does not, based on the previously established logic, it can be inferred that the upstream fault indicator F2 is experiencing a missed alarm. In this case, correction needs to be made in the signal information, or alternatively, in the alarm vector. In order to make up for the omissions and corrections, that is... The value of the element at the corresponding position in the vector is changed to 1.

[0037] In one specific embodiment, reference is made to Figure 4 Establish a simulation model of a 10kV distribution network, and install fault indicators in each section as follows: Figure 4 As shown, the fault indicator FI number is consistent with the segment number. The distances between segments are set as follows: segments 1, 3, and 5 are 5km apart; segments 2, 6, 7, and 8 are 2km apart; and segment 4 is 4km apart. Assuming the fault occurs in segment L7, fault indicator F3 does not issue an alarm signal. Based on the constructed simulation model topology, a relationship matrix is ​​built according to the numbering order. The specific results are as follows: ; Based on the alarm signals directly observed on-site, the preliminary alarm vector is constructed as follows: ; Based on the location of the fault indicator in the topology, the alarm vector is configured according to the alarm status of each fault indicator. The correction involves determining, based on the fault current flow, whether all fault indicators upstream of the target fault indicator have issued alarm signals. If no alarm signal has been issued, then all fault indicators upstream of the target fault indicator are marked as target fault indicators that have issued alarm signals. The corrected actual alarm vector is: ; According to the formula Calculations show that: .

[0038] Therefore, the fault segment can be identified as L7, consistent with the assumption. Here, "&" represents a vector comparison operation, and its output is a logical value. Only if the relation matrix... The elements in a column vector after segmentation and the alarm vector The result of the operation is 1 only when the corresponding elements are completely identical; otherwise, the result is 0. If any one of the operation results in 1, then the corresponding segment... This is the section where the fault occurred, thus completing the location of the faulty section, where L is the section detection vector.

[0039] In one embodiment, before step S1 of receiving signal information sent by each of the fault indicators, the method further includes: S011: Obtain the circuit nodes of the power distribution network; S012: Determine a line segment based on two adjacent circuit nodes; S013: Set a fault indicator for each of the aforementioned line sections.

[0040] As described in steps S011-S013 above, before performing the specific operation of receiving fault indicator signals, it is first necessary to obtain the circuit nodes of the distribution network. Circuit nodes are the basic building blocks of a power distribution system, typically referring to intersections or connection points in the power system. They include substations, switches, loads, and various equipment connecting lines. Understanding and obtaining information about these circuit nodes is crucial for subsequent line segmentation and fault analysis.

[0041] By utilizing Geographic Information System (GIS) technology or distribution network databases, the system can acquire detailed information about the circuit nodes of the distribution network, including their geographical coordinates, connectivity, and load data. These circuit nodes not only constitute the topology of the power network but also play a crucial role in fault detection and analysis. Understanding the connections between nodes allows for a better understanding of current flow paths and fault propagation patterns. Therefore, accurately acquiring information about the circuit nodes provides a data foundation and spatial information for subsequent distribution network fault location and handling, thereby improving the accuracy and efficiency of fault response.

[0042] S012: Determine a line segment based on two adjacent circuit nodes. After acquiring the circuit nodes, the system next needs to determine a line segment based on two adjacent circuit nodes. A line segment can be viewed as a section of power line connecting two nodes in a distribution network. By analyzing the relationships between adjacent nodes, the system can effectively divide multiple line segments to facilitate subsequent fault detection and indicator configuration. The process of determining line segments involves analyzing the connection relationships between various nodes in the distribution network. For each pair of adjacent circuit nodes, the system can use linear or graph theory methods to divide the segments. For example, if there is a connecting line between node A and node B, it can be defined as a line segment, labeled "segment AB". The division of areas not only provides a clear framework for fault location but also helps the system identify the nodes and corresponding equipment that may be affected by the fault. Accurate line segment definition is an important foundation for subsequent fault indicator installation and signal monitoring, effectively improving the accuracy of fault location. After determining the line segments, the final step is to connect a fault indicator to each line segment. A fault indicator is a device with real-time monitoring capabilities, typically used to detect abnormal conditions such as fault current, overload, and short circuit in power lines. Installing fault indicators in each line section not only facilitates centralized monitoring of the power system's health but also enables timely alarm signals in the event of a fault. It's important to note that these fault indicators can be existing devices in the distribution network; only data acquisition is required. The data from these indicators can be transmitted to the centralized management system via wireless signals or wired networks, facilitating information sharing and effective monitoring. Alternatively, additional fault indicators can be installed. This also lays a solid technical foundation for subsequent signal reception and processing. By equipping each line section with fault indicators, the overall security of the distribution network can be improved, enabling an efficient fault detection and response mechanism, ultimately ensuring the stable and reliable operation of the power system.

[0043] In one embodiment, the fault indicator is one of a current-type fault indicator, a voltage-type fault indicator, and a combined fault indicator. The current-type fault indicator is primarily used to monitor changes in current. When a fault occurs in the power system (such as a short circuit or overload), the current will exhibit significant abnormal fluctuations. The current-type fault indicator can capture these changes in real time and determine the presence of a fault based on set parameters. Once an abnormal current is detected, it immediately issues an alarm signal. The current-type fault indicator is highly sensitive and can respond quickly to fault conditions, making it suitable for power monitoring environments requiring high real-time performance. Furthermore, the advantages of the current-type fault indicator include: rapid response: Because it directly monitors current changes, it can quickly react and identify faults. High sensitivity: It can detect small-amplitude abnormal fluctuations, allowing for timely location of potential problems. Easy integration: Current-type fault indicators are typically designed for simple integration with existing equipment, facilitating installation and maintenance. Economic efficiency: Compared to combined fault indicators, current-type fault indicators generally have lower costs and are suitable for large-scale deployment. Therefore, a current-type fault indicator is preferred.

[0044] In one embodiment, step S3, which involves constructing an alarm vector based on the signal information if at least one of the fault indicators issues an alarm signal, includes: S321: If at least one of the fault indicators issues an alarm signal, then the waveform data of each of the line sections is obtained based on the signal information; S322: Extract hidden features from the recorded waveform data according to a preset neural network model; S323: Construct the alarm vector based on the concealment characteristics and the signal information.

[0045] As described in steps S321-S323 above, when at least one fault indicator issues an alarm signal, it means that the system has detected a potential fault or abnormality. Therefore, it is necessary to collect waveform data from the relevant lines. Waveform data includes transient waveforms of electrical parameters such as current, voltage, and frequency during the fault occurrence period, typically acquired by monitoring equipment or sensors in the distribution network. For example, by capturing signals through real-time monitoring equipment and storing them in digital form, the waveform data for each line segment will include changes in electrical parameters before and after the fault, thus providing important information for fault analysis. A pre-trained neural network model is used to perform deep learning and feature extraction on the acquired waveform data. These hidden features refer to important information hidden in the data that helps identify and locate the fault. For example, it could be a partial discharge pulse. Through the neural network, the system can adaptively identify fault modes, abnormal waveforms, noise distribution, etc. The hierarchical structure of the neural network can transform the original input data into a higher-dimensional feature representation through multiple iterations of learning, thereby capturing abnormal features that are difficult to identify using traditional methods. Based on the hidden features extracted from the waveform data and the previously obtained signal information, an alarm vector is constructed. Alarm vectors are important tools for quantifying the current fault state and its characteristics. They comprehensively consider multiple factors, such as fault type, degree of power parameter variation, fault occurrence time, and duration. Constructing an alarm vector typically involves performing appropriate mathematical calculations on extracted hidden features to form a vector representation. Each element can represent a specific fault characteristic or the strength of an alarm signal. In this way, alarm vectors not only indicate the presence of a fault but also help to quickly identify the nature and severity of the fault.

[0046] The neural network model is trained using supervised learning. First, a large amount of historical waveform data is collected, including samples of various fault types (such as short circuits, overvoltages, and partial discharges) and samples of normal operation. This data is then labeled to form a training dataset. Next, the waveform data undergoes preprocessing, including data cleaning, normalization, and segmentation, to ensure data quality. Then, an appropriate neural network architecture, such as a deep convolutional neural network (CNN) or a long short-term memory network (LSTM), is selected to capture the temporal and spatial features of the waveform data. During training, the cross-entropy loss function and the Adam optimizer are used, and the network parameters are iteratively adjusted using the backpropagation algorithm until the model achieves satisfactory accuracy on the validation set. Finally, the trained model is able to extract effective hidden features from new waveform data.

[0047] The specific process for constructing an alarm vector is as follows: First, the preprocessed waveform data is input into a trained neural network model, which outputs feature representations through forward propagation. These feature representations come from the last hidden layer of the network or a specifically designed output layer, containing key fault-related information. Then, based on application requirements, the dimensions of the alarm vector are designed, with each dimension corresponding to a fault feature. For example, the alarm vector may include the following elements: Element 1 represents the probability distribution of the fault type, obtained through the softmax function; Element 2 represents the intensity of the abnormal waveform, obtained by calculating the error between the input data and the model-reconstructed data; Element 3 represents the quantized value of the noise level, based on the statistical variance in the features; Element 4 represents the duration of the fault, extracted from the time series of the waveform data. In addition, previously obtained signal information, such as historical changes in power parameters, can be combined and integrated into the alarm vector through weighted fusion. Finally, the alarm vector is formed through mathematical calculations (such as normalization or threshold comparison).

[0048] In one embodiment, a temperature sensor can be set to acquire temperature data, and then the alarm vector can be constructed by combining the fault indicator signal, the recorded waveform, and the temperature sensor data.

[0049] In one embodiment, after step S002 of constructing the line segment fault relationship matrix based on the network topology, the method further includes: S0031: Real-time monitoring of whether the network topology of the power distribution network is updated; S0032: If the network topology of the distribution network is updated, then obtain the updated target network topology. S0033: Reconstruct the line segment fault relationship matrix based on the target network topology.

[0050] As described in steps S0031-S0033 above, the topology of the distribution network may change due to various reasons, such as equipment upgrades, line maintenance, or new connections. The monitoring process typically involves continuously collecting operational and status information of the distribution network using system monitoring tools or sensors. The monitoring system may set thresholds or conditions, triggering an update check when real-time data deviates from these conditions. Once a topology update is identified, the updated target network topology is obtained. This can be done through database queries, GIS systems, equipment management systems, or manual input by operation and maintenance personnel. After obtaining the updated target network topology, the line segment fault relationship matrix needs to be reconstructed. This is because the original fault relationship matrix may no longer be applicable to the updated topology; failure to update it will lead to inaccurate fault analysis results. Specifically, the target network topology information needs to be input into the fault relationship matrix construction algorithm. Based on the new line connections and equipment status, the system will reassess the fault relationships between each line segment.

[0051] Reference Figure 5 The present invention also provides a fault line section location device for a distribution network, the distribution network including multiple line sections, each line section being equipped with a fault indicator, the device comprising: The receiving module 902 is used to receive signal information sent by each of the fault indicators; The detection module 904 is used to detect whether the signal information contains at least one of the fault indicators issuing an alarm signal; The construction module 906 is used to construct an alarm vector based on the signal information if at least one of the fault indicators issues an alarm signal. The calculation module 908 is used to calculate the faulty line section in each of the line sections based on the alarm vector.

[0052] In one embodiment, the fault line section location device for the distribution network further includes: A network topology acquisition module is used to acquire the network topology of the power distribution network; The line segment fault relationship matrix construction module is used to construct a line segment fault relationship matrix based on the network topology; wherein, the line segment fault relationship matrix is ​​used to calculate faulty line segments.

[0053] In one embodiment, the computing module 908 includes: The segmentation submodule is used to divide the line section fault relationship matrix into blocks according to columns to obtain multiple segmentation vectors. The comparison submodule is used to compare each of the block vectors with the alarm vector to obtain the faulty line segment.

[0054] In one embodiment, building module 906 includes: The first submodule for obtaining network topology is used to obtain the network topology of the distribution network and the target fault indicator that issued the alarm signal in the signal information if at least one of the fault indicators issues an alarm signal. The first fault current direction determination submodule is used to determine the fault current direction based on the target fault indicator and the network topology. The fault detection submodule is used to detect whether a fault has occurred in the line section downstream of the target fault indicator based on the direction of the fault current. The first marking submodule of the target fault indicator is used to mark the fault indicator corresponding to the downstream line section as the target fault indicator that issues an alarm signal if a fault occurs in the downstream line section. The first signal information regeneration submodule is used to regenerate signal information based on the target fault indicator and construct the alarm vector.

[0055] In one embodiment, building module 906 includes: The second submodule for obtaining network topology is used to obtain the network topology of the distribution network and the target fault indicator that issued the alarm signal in the signal information if at least one of the fault indicators issues an alarm signal. The second fault current direction determination submodule is used to determine the fault current direction based on the target fault indicator and the network topology. The alarm signal judgment submodule is used to determine whether all the fault indicators upstream of the target fault indicator have issued alarm signals based on the direction of the fault current. The second marking submodule of the target fault indicator is used to mark all fault indicators upstream of the target fault indicator as the target fault indicator that has issued an alarm signal if no alarm signal is issued. The second signal information regeneration submodule is used to regenerate signal information based on the target fault indicator and construct the alarm vector.

[0056] In one embodiment, the fault line section location device for the distribution network further includes: A circuit node acquisition module is used to acquire the circuit nodes of the power distribution network; The line segment determination module is used to determine a line segment based on two adjacent circuit nodes; The fault indicator setting module is used to set a fault indicator for each of the line sections.

[0057] In one embodiment, the fault indicator is one of a current-type fault indicator, a voltage-type fault indicator, and a combined fault indicator.

[0058] Figure 6 An internal structural diagram of a computer device in one embodiment is shown. This computer device can specifically be a terminal or a server. Figure 6 As shown, the computer device includes a processor, memory, and network interface connected via a system bus. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and may also store a computer program. When executed by the processor, this computer program enables the processor to implement a method for locating faulty line sections in a distribution network. The internal memory may also store a computer program, which, when executed by the processor, enables the processor to implement a method for locating faulty line sections in a distribution network. Those skilled in the art will understand that... Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0059] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the following steps: Receive signal information sent by each of the fault indicators; Detect whether the signal information contains at least one of the fault indicators issuing an alarm signal; If at least one of the fault indicators issues an alarm signal, an alarm vector is constructed based on the signal information; The faulty line segment in each of the line segments is calculated based on the alarm vector.

[0060] By centrally processing and comprehensively analyzing all fault indicator signal data, the location of the fault can be accurately identified. This not only reduces the unplanned power outage time caused by the fault, but also improves the real-time response capability of maintenance personnel to the fault, making fault troubleshooting faster. It can also continuously monitor the operating status of the line segment, capture potential faults in a timely manner, and thus improve fault prevention capabilities. The effective monitoring mechanism ensures the safe operation of the distribution network and reduces the risk of long-term outages and the resulting economic losses.

[0061] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, causes the processor to perform the following steps: Receive signal information sent by each of the fault indicators; Detect whether the signal information contains at least one of the fault indicators issuing an alarm signal; If at least one of the fault indicators issues an alarm signal, an alarm vector is constructed based on the signal information; The faulty line segment in each of the line segments is calculated based on the alarm vector.

[0062] By centrally processing and comprehensively analyzing all fault indicator signal data, the location of the fault can be accurately identified. This not only reduces the unplanned power outage time caused by the fault, but also improves the real-time response capability of maintenance personnel to the fault, making fault troubleshooting faster. It can also continuously monitor the operating status of the line segment, capture potential faults in a timely manner, and thus improve fault prevention capabilities. The effective monitoring mechanism ensures the safe operation of the distribution network and reduces the risk of long-term outages and the resulting economic losses.

[0063] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0064] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0065] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for locating faulty line sections in a distribution network, characterized in that, The distribution network includes multiple line sections, each line section is equipped with a fault indicator, and the method includes: Receive signal information sent by each of the fault indicators; Detect whether the signal information contains at least one of the fault indicators issuing an alarm signal; If at least one of the fault indicators issues an alarm signal, an alarm vector is constructed based on the signal information; The faulty line segment in each of the line segments is calculated based on the alarm vector.

2. The method for locating faulty line sections in a distribution network according to claim 1, characterized in that, Before the step of receiving signal information sent by each of the fault indicators, the method further includes: Obtain the network topology of the power distribution network; A line segment fault relationship matrix is ​​constructed based on the network topology; wherein, the line segment fault relationship matrix is ​​used to calculate faulty line segments.

3. The method for locating faulty line sections in a distribution network according to claim 2, characterized in that, The step of calculating the faulty line segment in each of the line segments based on the alarm vector includes: The fault relationship matrix of the line section is divided into blocks according to the columns to obtain multiple block vectors; Each of the segmented vectors is compared with the alarm vector to obtain the faulty line segment.

4. The method for locating faulty line sections in a distribution network according to claim 1, characterized in that, The step of constructing an alarm vector based on the signal information if at least one of the fault indicators issues an alarm signal includes: If at least one of the fault indicators issues an alarm signal, then the network topology of the distribution network and the target fault indicator that issued the alarm signal in the signal information are obtained. Based on the target fault indicator and the network topology, the fault current flow is determined; Detect whether a fault has occurred in the line section downstream of the target fault indicator based on the direction of the fault current; If a fault occurs in a downstream line section, the fault indicator corresponding to the downstream line section will be marked as the target fault indicator that will issue an alarm signal. The signal information is regenerated based on the target fault indicator, and the alarm vector is constructed.

5. The method for locating faulty line sections in a distribution network according to claim 1 or 4, characterized in that, The step of constructing an alarm vector based on the signal information if at least one of the fault indicators issues an alarm signal includes: If at least one of the fault indicators issues an alarm signal, then the network topology of the distribution network and the target fault indicator that issued the alarm signal in the signal information are obtained. Based on the target fault indicator and the network topology, the fault current flow is determined; Based on the direction of the fault current, determine whether all fault indicators upstream of the target fault indicator have issued alarm signals. If no alarm signal is issued, all fault indicators upstream of the target fault indicator will be marked as the target fault indicator that issued the alarm signal. The signal information is regenerated based on the target fault indicator, and the alarm vector is constructed.

6. The method for locating faulty line sections in a distribution network according to claim 1, characterized in that, The step of constructing an alarm vector based on the signal information if at least one of the fault indicators issues an alarm signal includes: If at least one of the fault indicators issues an alarm signal, then waveform data for each of the line sections is obtained based on the signal information. The hidden features in the recorded waveform data are extracted according to a preset neural network model; The alarm vector is constructed based on the concealment characteristics and the signal information.

7. The method for locating faulty line sections in a distribution network according to claim 2, characterized in that, Following the step of constructing the line segment fault relationship matrix based on the network topology, the method further includes: Real-time monitoring of whether the network topology of the power distribution network is updated; If the network topology of the power distribution network is updated, the updated target network topology is obtained. Based on the target network topology, the fault relationship matrix of the line segments is reconstructed.

8. A fault line section location device for a power distribution network, characterized in that, The distribution network includes multiple line sections, each line section is equipped with a fault indicator, and the device includes: The receiving module is used to receive signal information sent by each of the fault indicators; The detection module is used to detect whether the signal information contains at least one of the fault indicators issuing an alarm signal; A construction module is configured to construct an alarm vector based on the signal information if at least one of the fault indicators issues an alarm signal. The calculation module is used to calculate the faulty line section in each of the line sections based on the alarm vector.

9. A computer-readable storage medium, characterized in that, The system contains a computer program that, when executed by a processor, causes the processor to perform the steps of the fault line section location method for the distribution network as described in any one of claims 1 to 7.

10. A computer device, characterized in that, The device includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the fault line section location method for the distribution network as described in any one of claims 1 to 7.

Images