Instantaneous fault positioning method and system of power distribution network system

Abstract

The invention discloses a transient fault positioning method and system for a power distribution network system. The method comprises the following steps: acquiring original electrical parameter data from the power distribution network system in real time; performing data verification on the collected original electrical parameter data, performing data preprocessing on the verified data, and performing fault-related feature extraction on the preprocessed data to obtain feature parameters for describing fault features; determining a fault type according to the characteristic parameters, selecting a corresponding fault positioning algorithm according to the fault type, and calculating the specific position of a fault point based on the characteristic parameters and the structure of the power distribution network. The method can accurately calculate the specific position of the fault point, effectively improves the safety and reliability of a power distribution network, and reduces the influence of the fault on the operation of a power system.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power grids, and in particular to a method and system for locating instantaneous faults in an electric power distribution network system. Background Art

[0002] In power distribution systems, fault location and early warning have always been key links in ensuring the safe and stable operation of the power grid. Traditionally, fault location mainly relies on manual inspections and simple monitoring equipment. This method is not only time-consuming and labor-intensive, but also difficult to timely capture and accurately locate transient faults. At the same time, due to the lack of an effective early warning mechanism, operation and maintenance personnel often only learn about the fault after it occurs, which not only increases the difficulty of fault handling, but may also have a serious impact on the normal operation of the power system.

[0003] With the continuous development of power distribution network automation technology, intelligence and informatization have become important directions for the upgrade of power distribution network systems. However, most existing power distribution network automation systems have problems such as incomplete data collection, untimely processing, and inaccurate fault location. They are unable to meet the needs of efficient positioning and timely warning of transient faults. Especially in complex power distribution network structures, the rapid and accurate positioning of fault points faces many challenges.

[0004] Therefore, there is an urgent need to provide a method that can collect electrical parameter data in real time, perform precise processing and analysis, accurately calculate the fault location, and issue early warning information to operation and maintenance personnel in various ways when necessary, so as to improve the safety and reliability of the power distribution network. Summary of the Invention

[0005] The technical problem to be solved by the present invention is: In response to the above-mentioned problems in the prior art, a method and system for locating instantaneous faults in an electric power distribution network system with good safety, strong reliability and high efficiency is provided to accurately locate the fault point position of the electric power distribution network system and ensure the safe operation of the electric power distribution network.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is: A method for locating instantaneous faults in a power distribution network system, comprising: Step S1, data acquisition: real-time acquisition of raw electrical parameter data from the power distribution network system; Step S2, data processing: performing data verification on the collected raw electrical parameter data, performing data preprocessing on the verified data, and extracting fault-related features from the preprocessed data to obtain feature parameters for describing fault characteristics; Step S3, fault analysis and location: determining the fault type according to the characteristic parameters, selecting a corresponding fault location algorithm according to the fault type, and calculating the specific location of the fault point based on the characteristic parameters and the structure of the power distribution network.

[0007] Furthermore, in step S2, data verification is performed on the collected original electrical parameter data, including: The original electrical parameter data is subjected to data format verification, data range verification, consistency verification, outlier verification and data integrity verification, and data with incorrect data format, data exceeding a preset range in data range verification, data with large differences in consistency verification, data greater than a preset threshold in outlier verification, and data with incomplete data packets, data frame loss and obvious data fluctuations in data integrity verification are marked.

[0008] Furthermore, in step S2, the verified data is subjected to data preprocessing, including: The original electrical parameter data is filtered and denoised, and the filtered and denoised data is normalized to obtain pre-processed data.

[0009] Furthermore, in step S2, the pre-processed data is subjected to feature extraction related to the fault to obtain feature parameters for describing the fault characteristics, including: extracting one or more of a fault current waveform, a fault current frequency, and a fault current phase difference from the preprocessed data as characteristic parameters describing the fault characteristics; The peak value of the fault current, the average value of the fault current and the effective value of the fault current are calculated and obtained as specific values ​​of the characteristic parameters.

[0010] Furthermore, in step S3, determining the fault type according to the characteristic parameters includes: Select a machine learning algorithm based on the specific application scenario and data characteristics, where the machine learning algorithm includes one or more of a support vector machine-based fault judgment algorithm, a neural network-based fault judgment algorithm, and a decision tree-based fault judgment algorithm; Inputting the characteristic parameter data of the fault type to be determined into a machine learning algorithm model trained based on data of known fault types to determine the fault type; The machine learning algorithm model outputs the fault type and the corresponding confidence level, thereby determining the fault type corresponding to the characteristic parameters; wherein the fault type includes one or more of a short circuit fault, a ground fault, and an overload fault.

[0011] Furthermore, in step S3, a corresponding fault location algorithm is selected according to the fault type, and the specific location of the fault point is calculated based on the characteristic parameters and the structure of the power distribution network, including: Obtaining power distribution network topology information; wherein the power distribution network topology information includes one or more of line length, branching conditions, and monitoring point locations; Constructing a mathematical model of the power distribution network based on the acquired power distribution network topology information, wherein the mathematical model of the power distribution network includes a network structure composed of nodes and branches; Select a fault location algorithm based on the fault type and the characteristics of the power distribution network; the fault location algorithm includes a fault location algorithm based on traveling wave location technology and a fault location algorithm based on impedance location technology; The preprocessed data and the mathematical model of the power distribution network are input into the selected fault location algorithm. The equivalent impedance between the fault point and the measurement point is calculated based on the current and voltage data in the measured electrical parameter data, the impedance relationship between each node pair in the mathematical model of the power distribution network, and the admittance relationship between each node pair. The specific location of the fault point is obtained based on the calculated equivalent impedance and the actual impedance distribution of the network.

[0012] Furthermore, the power distribution network mathematical model includes the impedance relationship and admittance relationship between each node pair and the voltage of each node; The impedance relationship between each node pair is expressed as: ; In the above formula, represents the impedance between node i and node j, represents the impedance of the line connecting node i and node j, represents the impedance of the transformer connecting node i and node j, is the resistance of the line between node i and node j, is the reactance between node i and node j; The expression of the admittance relationship between each node pair is: ; The voltage expression of node i is: ; In the above formula, is the vector of the current injected into node i, is the vector of node i voltage, is the admittance matrix of node i.

[0013] Furthermore, after step S3, the method further includes: step S4, verifying the calculated specific location of the fault point to determine whether it is accurate, specifically including: Compare the expected voltage and current waveforms at the specific location of the fault point obtained by calculation with the actual monitored waveforms; Calculate using different fault location algorithms and compare the specific locations of the fault points obtained by each algorithm; A simulation model is established based on the actual structure and parameters of the power distribution network. The fault process is simulated in the simulation model, and the specific location of the fault point is calculated. The simulation results are compared with the calculated results. Compare the calculated fault location with historical fault records to analyze whether the fault characteristic parameters of the current fault situation are consistent with the historical data; If the above comparison results are all within the preset position range, the calculated specific position of the fault point is accurate.

[0014] Furthermore, after step S4, the following steps are further included: The calculated specific location of the fault point is output in a visual manner, and the need to issue an early warning information is determined based on the specific location of the fault point, the severity and urgency of the fault, and an early warning information is issued to the operation and maintenance personnel when it is necessary.

[0015] The present invention also provides a system for locating instantaneous faults in a power distribution network system, comprising: Data acquisition module, used to collect raw electrical parameter data from the power distribution network system in real time; A data processing module is used to perform data verification on the collected raw electrical parameter data, perform data preprocessing on the verified data, and extract fault-related features from the preprocessed data to obtain feature parameters for describing fault characteristics; The fault analysis and location module is used to determine the fault type according to the characteristic parameters and select the corresponding fault location algorithm according to the fault type to calculate the specific location of the fault point.

[0016] Compared with the prior art, the advantages of the present invention are: By collecting electrical parameter data in real time and performing data processing and fault analysis and location, the present invention can accurately calculate the specific location of the fault point, effectively improving the safety and reliability of the power distribution network and reducing the impact of faults on the operation of the power system. Through data verification, the impact of data errors and anomalies on subsequent processing can be effectively reduced, providing a high-quality data foundation for the power distribution network's automated instantaneous fault location and early warning system, thereby improving the system's overall performance and accuracy. By selecting the appropriate location algorithm based on the fault type, the fault point's location in the power distribution network can be accurately calculated, providing a strong guarantee for the safe and stable operation of the power distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of a method for locating instantaneous faults in a power distribution network system according to embodiment 1 of the present invention.

[0018] Figure 2 This is a schematic block diagram of the specific structure of the instantaneous fault location system of the power distribution network system according to embodiment 2 of the present invention. DETAILED DESCRIPTION

[0019] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0020] Example 1 like Figure 1 As shown, an embodiment of the present invention provides a method for locating instantaneous faults in a power distribution network system, comprising: Step S1, data acquisition: real-time acquisition of raw electrical parameter data from the power distribution network system; Step S2, data processing: performing data verification on the collected raw electrical parameter data, performing data preprocessing on the verified data, and extracting fault-related features from the preprocessed data to obtain feature parameters for describing the fault characteristics; Step S3, fault analysis and location: determine the fault type according to the characteristic parameters, select the corresponding fault location algorithm according to the fault type, and calculate the specific location of the fault point based on the characteristic parameters and the structure of the power distribution network.

[0021] In a specific application embodiment, electrical parameter data can be collected in real time from sensors and monitoring terminal devices in the power distribution network through a data acquisition module. The data acquisition module can be connected to the sensors and monitoring terminal devices through a variety of methods including wired connection, network connection, and Bluetooth connection. The collected electrical parameter data includes current parameter data and voltage parameter data. Since transient faults often occur very quickly and briefly, it is necessary to be able to capture these fault data in real time and accurately. Conventional data acquisition methods may not be able to accurately capture fault characteristics due to processing delays or data loss. By adopting multiple connection methods, including wired connection, network connection, and Bluetooth connection, as well as connection with sensors and monitoring terminal devices, real-time data transmission can be ensured.

[0022] In step S2 of this embodiment, data verification is performed on the collected original electrical parameter data, including: The original electrical parameter data is subjected to data format verification, data range verification, consistency verification, outlier verification and data integrity verification, and data with incorrect data format, data exceeding the preset range in data range verification, data with large differences in consistency verification, data greater than the preset threshold in outlier verification, and data with incomplete data packets, data frame loss and obvious data fluctuations in data integrity verification are marked.

[0023] In a specific application embodiment, the data acquisition module has a data verification and error detection mechanism, so the data acquisition module can be used to perform data verification, which specifically includes the following steps: Step A21, receiving the original electrical parameter data and checking its data format, including the data type, length and encoding; Step A22: Check the data range. If the data exceeds the expected range, further error detection is performed. Step A23: Perform consistency check. If there are large differences between the data, mark the data with large differences as errors. Step A24: Use a statistical method to detect outliers on the received data, where the statistical method is expressed as: ; (1) In the above formula, X is the data point, μ is the mean, and σ is the standard deviation. When identifying outliers, if the value of Z calculated from the data point X is greater than the set threshold, the data point X is marked as an outlier. Step A25, data integrity check and historical data comparison, including checking whether the data packet is complete, whether the data frame is lost, and marking obvious data fluctuations.

[0024] It can be understood that through data verification and error detection, a comprehensive review and verification of the original data is achieved. Not only the format, scope and consistency of the data are checked, but also statistical methods are used to detect outliers. Combined with data integrity checks and historical data comparisons, the accuracy and reliability of the data are ensured. This series of verification steps effectively reduces the impact of data errors and anomalies on subsequent processing, and provides a high-quality data foundation for the power distribution network automation instantaneous fault location and early warning system, thereby improving the overall performance and accuracy of the system.

[0025] In step S2 of this embodiment, the verified data is subjected to data preprocessing, including: The original electrical parameter data is filtered and denoised, and the filtered and denoised data are normalized to obtain preprocessed data.

[0026] In step S2 of this embodiment, the preprocessed data is subjected to fault-related feature extraction to obtain feature parameters for describing the fault characteristics, including: extracting one or more of a fault current waveform, a fault current frequency, and a fault current phase difference from the preprocessed data as characteristic parameters describing the fault characteristics; The peak value of the fault current, the average value of the fault current and the effective value of the fault current are calculated and used as the specific values ​​of the characteristic parameters.

[0027] In a specific application embodiment, when the verified data is preprocessed, the following steps are specifically included: Step B21, data filtering: filtering the collected data to remove high-frequency noise and interference signals. The expression for filtering is: ; (2) In the above formula, It is a frequency representation, x(n) represents the time domain signal, N represents the signal length, and k represents the frequency domain index; Step B22, data denoising: denoising the filtered data to further reduce the noise component in the data. The denoising expression is: ; (3) In the above formula, is the smoothed signal, x(n) is the original signal, and M is the window size of the moving average; Step B23, data standardization: This includes converting the data into a dimensionless form to ensure the accuracy and consistency of subsequent analysis. The expression for standardization is: ; (4) In the above formula, Represents the normalized value of data point X.

[0028] It can be understood that the characteristic parameters of transient faults, including fault current waveform, frequency and phase difference, are often complex and changeable, and are easily affected by noise, which makes feature extraction difficult. This embodiment significantly improves the quality of the original data through data filtering, denoising and standardization. First, data filtering effectively removes high-frequency noise and interference signals, then denoising further reduces the noise component, and finally the data is converted into a dimensionless form through standardization, ensuring the accuracy and consistency of subsequent analysis. This series of preprocessing steps greatly optimizes the algorithm performance, improves data quality, enhances consistency, reduces noise and redundancy, and optimizes algorithm performance. It lays a solid foundation for subsequent data processing and analysis, thereby improving the overall efficiency and reliability of the power distribution network automation system.

[0029] In step S3 of this embodiment, determining the fault type according to the characteristic parameters includes: Select a machine learning algorithm based on the specific application scenario and data characteristics, where the machine learning algorithm includes one or more of a support vector machine-based fault judgment algorithm, a neural network-based fault judgment algorithm, and a decision tree-based fault judgment algorithm; Inputting characteristic parameter data of the fault type to be determined into a trained machine learning algorithm model to determine the fault type; wherein the selected machine learning algorithm is trained using data of known fault types to learn the mapping relationship between different fault types and characteristic parameters, thereby obtaining a trained machine learning algorithm model; The machine learning algorithm model outputs the fault type and the corresponding confidence level, thereby determining the fault type corresponding to the characteristic parameters; wherein the fault type includes one or more of a short circuit fault, a ground fault, and an overload fault.

[0030] It can be understood that through the above-mentioned algorithm selection and training process, combined with the precise extraction of characteristic parameters, intelligent judgment of the power distribution network fault type is achieved. By using machine learning algorithms to learn the complex mapping relationship between fault characteristics and types, the data to be judged can be accurately classified into the corresponding fault type, and high-confidence judgment results can be output. This can significantly improve the accuracy and efficiency of fault analysis and provide strong guarantees for the safe and stable operation of the power distribution network.

[0031] In step S3 of this embodiment, a corresponding fault location algorithm is selected according to the fault type, and the specific location of the fault point is calculated based on the characteristic parameters and the structure of the power distribution network, including: Obtaining power distribution network topology information; wherein the power distribution network topology information includes one or more of line length, branching conditions, and monitoring point locations; Building a mathematical model of the power distribution network based on the acquired power distribution network topology information, the mathematical model of the power distribution network including a network structure composed of nodes and branches; Select a fault location algorithm based on the fault type and the characteristics of the power distribution network; the fault location algorithm includes a fault location algorithm based on traveling wave location technology and a fault location algorithm based on impedance location technology; The preprocessed data and the mathematical model of the power distribution network are input into the selected fault location algorithm. The equivalent impedance between the fault point and the measurement point is calculated based on the current and voltage data in the measured electrical parameter data, the impedance relationship between each node pair in the mathematical model of the power distribution network, and the admittance relationship between each node pair. The specific location of the fault point is obtained based on the calculated equivalent impedance and the actual impedance distribution of the network.

[0032] In this embodiment, the mathematical model of the power distribution network includes the impedance relationship and admittance relationship between each node pair and the voltage of each node; The impedance relationship between each node pair is expressed as: ; (5) In the above formula, represents the impedance between node i and node j, represents the impedance of the line connecting node i and node j, represents the impedance of the transformer connecting node i and node j, is the resistance of the line between node i and node j, is the reactance between node i and node j; The expression of the admittance relationship between each node pair is: ; (6) The voltage expression of node i is: ; (7) In the above formula, is the vector of the current injected into node i, is the vector of node i voltage, is the admittance matrix of node i.

[0033] In a specific application embodiment, the methods for obtaining the structural information of the power distribution network include: obtaining through existing data: using existing data such as design drawings, technical documents, GIS databases or power enterprise management systems of the power distribution network, detailed topological structure information can be quickly obtained, including line length, branching conditions and monitoring point locations, to provide basic data for fault location; on-site investigation and measurement: through field measurement and investigation, the actual structural information of the power distribution network is accurately obtained, including the actual length of the line, the exact location of the branch point and the actual layout of the monitoring point. These on-site data are crucial to improving the accuracy of fault location; application of advanced technology: with the help of QR code technology, the QR code containing the topological structure information is quickly read on the power distribution network equipment to realize the rapid acquisition and update of information; at the same time, using remote communication technology and intelligent perception and recognition technology, the status and changes of the power distribution network can be monitored and identified in real time, providing real-time and accurate data support for fault location.

[0034] In fault location calculations, the equivalent impedance between the fault point and the measurement point is calculated using the measured current and voltage data, the impedance relationship between each node pair in the power distribution network mathematical model, and the admittance relationship between each node pair. Then, based on the calculated equivalent impedance and the actual impedance distribution of the network, the position of the fault point in the network can be inferred.

[0035] When selecting a fault location algorithm based on the fault type and the characteristics of the power distribution network, the following steps are included: First, clarify the type of fault being handled and the structural characteristics of the power distribution network, including line parameters and branch conditions. Next, evaluate the accuracy, completeness, and real-time nature of the available data, and determine which data can be used as input for the algorithm. Then, based on the fault type, distribution network characteristics, and data availability factors, compare the performance of the optional algorithms, taking into account the accuracy, computational efficiency, real-time nature, robustness, and adaptability of the algorithms. Finally, select the algorithm that best suits the current application scenario, verify and test it in the actual distribution network environment, and adjust and optimize the algorithm based on the verification results.

[0036] It can be understood that by accurately obtaining the structural information of the power distribution network, constructing a mathematical model, and selecting an appropriate positioning algorithm based on the fault type and characteristics, the position of the fault point in the power distribution network can be accurately calculated and verified, providing a strong guarantee for the safe and stable operation of the power distribution network.

[0037] When selecting a fault location algorithm based on the fault type and the characteristics of the power distribution network, the available fault location algorithms include: Algorithm 1, fault location algorithm based on traveling wave location technology, its expression is: ; (8) In the above formula, D represents the distance from the fault point to the measurement point, v represents the propagation speed of the traveling wave in the power line, and t represents the time it takes for the traveling wave to propagate from the fault point to the measurement point and reflect back; Algorithm 2 is a fault location algorithm based on impedance location technology. Its principle formula is: ; (9) In the above formula, represents impedance, U represents the voltage at the measuring point, and I represents the current at the measuring point.

[0038] It can be understood that by simulating the power distribution network structure in the form of a mathematical model, compared with the existing technology of fault location through simulation, due to the complexity of the actual circuit structure, the simulation method is more complicated to calculate, and thus it is impossible to perform work positioning in a timely manner. This embodiment uses a simplified mathematical model of the power distribution network structure, without considering complex irrelevant factors, and by integrating and analyzing the actual parameters with the circuit principle structure, dividing and representing the circuit structure in the form of nodes, thereby achieving rapid real-time positioning of the fault point, providing a strong guarantee for the safe and stable operation of the power distribution network.

[0039] In addition, this embodiment provides two fault location algorithm options: traveling wave location technology and impedance location technology. The traveling wave location algorithm accurately measures the propagation time of traveling waves and uses the relationship between speed and time to accurately calculate the fault distance; the impedance location algorithm analyzes the voltage and current at the measurement point and calculates the impedance value to infer the fault location. The selection of these two algorithms depends on the fault type and the characteristics of the power distribution network. They can flexibly respond to different scenarios, improve the accuracy and adaptability of fault location, and provide effective support for the safe operation of the power distribution network.

[0040] In this embodiment, after step S3, the following step is further included: step S4, verifying the calculated specific location of the fault point to determine whether it is accurate, specifically including: Compare the expected voltage and current waveforms at the specific location of the fault point obtained by calculation with the actual monitored waveforms; Calculate using different fault location algorithms and compare the specific locations of the fault points obtained by each algorithm; A simulation model is established based on the actual structure and parameters of the power distribution network. The fault process is simulated in the simulation model, and the specific location of the fault point is calculated. The simulation results are compared with the calculated results. Compare the calculated fault location with historical fault records to analyze whether the fault characteristic parameters of the current fault situation are consistent with the historical data; If the above comparison results are all within the preset position range, the calculated specific location of the fault point is accurate. Otherwise, the specific location of the fault point needs to be recalculated and verified again until the calculated location is determined to be accurate.

[0041] It can be understood that verifying the calculated fault location through multiple methods not only enhances the accuracy and reliability of fault location, but also ensures the accuracy of the fault location through multi-angle verification, provides solid technical support for the safe operation of the power distribution network, and effectively reduces the risk of false alarms and missed alarms. Existing methods usually use a single verification method, such as relying only on actual monitoring data or using only one positioning algorithm to verify the fault location, which may have the disadvantages of incomplete verification, susceptibility to interference from external factors, and insufficient positioning accuracy. This embodiment adopts a comprehensive verification scheme, which specifically includes comparison with actual monitoring data, comparison with other positioning methods, verification using simulation software, and statistical analysis methods. It can verify the calculated fault location more comprehensively and accurately, improve the reliability and accuracy of fault location, reduce misjudgments and missed judgments caused by incomplete verification or inaccurate positioning, and provide strong support for quickly locating and repairing faults, thereby ensuring the safe and stable operation of the power distribution network.

[0042] In this embodiment, after step S4, the following steps are further included: The calculated fault location is output in a visual format, and based on the fault location, severity, and urgency, a decision is made as to whether an early warning message should be issued. If an early warning message is required, an early warning message is sent to the operation and maintenance personnel. The fault type and severity information can be stored in a database.

[0043] It can be understood that according to the severity and urgency of the fault, the corresponding alarm mechanism is triggered when it exceeds the warning threshold, so that early warning information can be issued to operation and maintenance personnel in various ways when necessary, effectively improving the safety and reliability of the power distribution network, effectively shortening the fault recovery time, reducing the impact of the fault on the operation of the power system, and providing strong decision-making support for operation and maintenance personnel.

[0044] Example 2 This embodiment provides a system for locating instantaneous faults in a power distribution network system, including: Data acquisition module, used to collect raw electrical parameter data from the power distribution network system in real time; The data processing module is used to verify the collected raw electrical parameter data, preprocess the verified data, and extract fault-related features from the preprocessed data to obtain characteristic parameters for describing the fault characteristics; The fault analysis and location module is used to determine the fault type based on the characteristic parameters and select the corresponding fault location algorithm according to the fault type to calculate the specific location of the fault point.

[0045] In a specific application embodiment, Figure 2 As shown in FIG, the instantaneous fault location system of the power distribution network system specifically includes: The data acquisition module is responsible for collecting electrical parameter data from sensors and monitoring terminal devices in the power distribution network in real time, and transmitting the collected data to the data processing and analysis module. The data acquisition module is connected to the sensors and monitoring terminal devices through various methods such as wired connection, network connection and Bluetooth connection. The collected electrical parameter data includes current parameter data and voltage parameter data; The data processing and analysis module is used to pre-process, feature-process and analyze the collected data, including filtering and denoising the collected data, extracting the current waveform and extracting the current frequency; The fault location module is used to accurately calculate the location of the fault in the power distribution network based on the processed data and transmit the fault location information to the early warning and alarm module, wherein the fault distance is calculated based on the fault characteristic parameters and the structure of the power distribution network; The early warning and alarm module is used to comprehensively analyze the data results of the data processing and analysis module and the fault location module, and judge whether it is necessary to issue an early warning information based on the fault location results and preset threshold conditions. When an early warning information is required, it will send the early warning information to the operation and maintenance personnel through various means; The communication module is used to realize data transmission between modules within the system and communication between the system and external devices. The communication technologies used include Ethernet, wireless local area network and mobile communication network communication technologies.

[0046] It can be understood that by integrating data acquisition, data processing and analysis, fault location, early warning and alarm, and communication modules, efficient positioning and timely early warning of instantaneous faults in power distribution network automation are achieved. By collecting electrical parameter data in real time and performing precise processing and analysis, the fault location is accurately calculated. At the same time, when necessary, early warning information is issued to operation and maintenance personnel in various ways, which can effectively improve the safety and reliability of the power distribution network, reduce the impact of faults on the operation of the power system, and provide strong decision-making support for operation and maintenance personnel.

[0047] The following is a specific application example to illustrate the overall process of the method and system of the present invention.

[0048] In the power distribution network, when a transient grounding fault occurs on a 10 kV busbar, the grid's operating status will immediately become abnormal. In order to quickly respond to this fault and accurately locate the fault point, it is first necessary to activate the power distribution network's automated transient fault location and early warning system.

[0049] After the system is started, data collection is performed first. The data acquisition module collects electrical parameter data from the 10 kV bus and its surrounding sensors and monitoring terminal devices in real time through various connection methods, such as wired connection, network connection, and Bluetooth connection. This data includes current parameter data and voltage parameter data, which is crucial for subsequent fault analysis.

[0050] The collected data needs to undergo a strict verification process to ensure its accuracy and reliability. The data verification module will perform format checks, range checks, consistency checks, outlier detection and data integrity checks on the data. Only data that has been verified and confirmed to be correct will be used for subsequent data processing and analysis.

[0051] Next, the data processing and analysis module will pre-process the raw data, including data cleaning, conversion, organization and standardization, to reduce noise and redundancy and improve data quality. Then, the module will extract characteristic parameters related to the fault, such as fault current waveform, fault current frequency and fault current phase difference, etc., providing important basis for subsequent fault judgment.

[0052] Based on the extracted characteristic parameters, the fault analysis module will use the fault judgment algorithm based on support vector machines to judge the fault type. In this step, the system will determine whether the fault is a transient ground fault. Once the fault type is determined, the system will output the fault type and fault severity information to the fault location module and store the processed and analyzed data in the database.

[0053] The fault location module is the core part of the system. It first obtains the topological structure information of the 10 kV bus through existing data, including the line length, branching situation and the location of monitoring points. Then, based on the obtained structural information, it constructs a mathematical model of the 10 kV bus. Next, according to the characteristics of instantaneous grounding faults and the structural characteristics of the 10 kV bus, it selects a suitable fault location algorithm, such as a fault location algorithm based on traveling wave location technology. The preprocessed data and the 10 kV bus structural model are input into the selected fault location algorithm, and the system can calculate the specific location of the fault point.

[0054] To ensure the accuracy of the fault location, the system will also verify the fault location. The verification process includes comparison with actual monitoring data and other positioning methods. By comparing with the actually monitored voltage and current waveforms, and using multiple fault location algorithms to calculate and compare the fault locations obtained by each algorithm, the system can further confirm the location of the fault point.

[0055] Once the fault location is confirmed, the early warning and alarm module comprehensively analyzes the data output from the data processing and analysis module and the fault location module to determine whether a warning is necessary. If so, the system will notify the operation and maintenance personnel through various means, prompting them to take timely action. Finally, based on the warning information, the operation and maintenance personnel will quickly arrive at the fault site to inspect and fix the problem, restoring normal grid operation.

[0056] Through the above process, the instantaneous fault location system of the power distribution network system can realize the rapid location and early warning of the instantaneous grounding fault of the 10 kV busbar, providing a strong guarantee for the safe and stable operation of the power distribution network.

[0057] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiment. All technical solutions based on the concept of the present invention are within the scope of protection of the present invention. It should be noted that for those skilled in the art, various improvements and modifications that do not depart from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A method for locating instantaneous faults in a power distribution network system, characterized in that: include: Step S1, data collection: real-time collection of raw electrical parameter data from the power distribution network system; Step S2, data processing: performing data verification on the collected original electrical parameter data, performing data preprocessing on the verified data, and extracting features related to the fault from the preprocessed data to obtain feature parameters for describing the fault features; Step S3, fault analysis and location: determine the fault type according to the characteristic parameters, select a corresponding fault location algorithm according to the fault type, and calculate the specific location of the fault point based on the characteristic parameters and the structure of the power distribution network.

2. The instantaneous fault location method of the power distribution network system according to claim 1, characterized in that: In the step S2, data verification is performed on the collected original electrical parameter data, including: The original electrical parameter data is subjected to data format check, data range check, consistency check, outlier check and data integrity check, and data with incorrect data format, data exceeding a preset range in the data range check, data with large differences in the consistency check, data greater than a preset threshold in the outlier check, and data with incomplete data packets, data frame loss and obvious data fluctuations in the data integrity check are marked.

3. The instantaneous fault location method of the power distribution network system according to claim 1, characterized in that: In step S2, the verified data is preprocessed, including: The original electrical parameter data is filtered and denoised, and the filtered and denoised data is subjected to data standardization to obtain pre-processed data.

4. The instantaneous fault location method of the power distribution network system according to claim 1, characterized in that: In step S2, the preprocessed data is subjected to feature extraction related to the fault to obtain feature parameters for describing the fault characteristics, including: Extracting one or more of a fault current waveform, a fault current frequency and a fault current phase difference from the preprocessed data as characteristic parameters describing the fault characteristics; The peak value of the fault current, the average value of the fault current and the effective value of the fault current are calculated and obtained as specific values ​​of the characteristic parameters.

5. The instantaneous fault location method of the power distribution network system according to claim 1, characterized in that: In the step S3, determining the fault type according to the characteristic parameter includes: Select a machine learning algorithm according to the specific application scenario and data characteristics, where the machine learning algorithm includes one or more of a fault judgment algorithm based on a support vector machine, a fault judgment algorithm based on a neural network, and a fault judgment algorithm based on a decision tree; Inputting the characteristic parameter data of the fault type to be determined into a machine learning algorithm model trained based on data of known fault types to determine the fault type; The machine learning algorithm model outputs the fault type and the corresponding confidence level, thereby determining the fault type corresponding to the characteristic parameters; wherein the fault type includes one or more of a short circuit fault, a ground fault, and an overload fault.

6. The instantaneous fault location method of the power distribution network system according to claim 1, characterized in that: In the step S3, a corresponding fault location algorithm is selected according to the fault type, and the specific location of the fault point is calculated based on the characteristic parameters and the structure of the power distribution network, including: Acquire the topological structure information of the power distribution network; wherein the topological structure information of the power distribution network includes one or more of the length of the line, the branching situation and the location of the monitoring point; Constructing a mathematical model of the power distribution network based on the acquired power distribution network topology information, wherein the mathematical model of the power distribution network includes a network structure composed of nodes and branches; According to the fault type and the characteristics of the power distribution network, a fault location algorithm is selected; wherein the fault location algorithm includes a fault location algorithm based on traveling wave location technology and a fault location algorithm based on impedance location technology; The preprocessed data and the mathematical model of the power distribution network are input into the selected fault location algorithm. The equivalent impedance between the fault point and the measurement point is calculated based on the current and voltage data in the measured electrical parameter data, the impedance relationship between each node pair in the mathematical model of the power distribution network, and the admittance relationship between each node pair. The specific location of the fault point is obtained based on the calculated equivalent impedance and the actual impedance distribution of the network.

7. The instantaneous fault location method of the power distribution network system according to claim 6, characterized in that: The mathematical model of the power distribution network includes the impedance relationship and admittance relationship between each node pair and the voltage of each node; The expression of the impedance relationship between each node pair is: ； In the above formula, represents the impedance between node i and node j, represents the impedance of the line connecting node i and node j, represents the impedance of the transformer connecting node i and node j, is the resistance of the line between node i and node j, is the reactance between node i and node j; The expression of the admittance relationship between each node pair is: ； The voltage expression of node i is: ； In the above formula, is the vector of the current injected into node i, is the vector of node i voltage, is the admittance matrix of node i.

8. The instantaneous fault location method of the power distribution network system according to claim 1, characterized in that: The step S3 further includes: step S4, verifying the calculated specific location of the fault point to determine whether it is accurate, specifically including: Compare the expected voltage and current waveforms at the specific location of the calculated fault point with the actual monitored waveforms; Calculate using different fault location algorithms and compare the specific locations of the fault points obtained by each algorithm; A simulation model is established based on the actual structure and parameters of the power distribution network. The process of fault occurrence is simulated in the simulation model, and the specific location of the fault point is calculated. The simulation results are compared with the calculation results. Compare the calculated specific location of the fault point with the historical fault records to analyze whether the fault characteristic parameters of the current fault situation are consistent with the historical data; If the above comparison results are all within the preset position range, the calculated specific position of the fault point is accurate.

9. The instantaneous fault location method of the power distribution network system according to claim 8, characterized in that: After step S4, the following steps are also included: The calculated specific location of the fault point is output in a visual manner, and the need to issue an early warning message is determined based on the specific location of the fault point, the severity and urgency of the fault, and an early warning message is issued to the operation and maintenance personnel when it is necessary.

10. An instantaneous fault location system for a power distribution network system, characterized in that: include: Data acquisition module, used to collect raw electrical parameter data from the power distribution network system in real time; A data processing module, used to perform data verification on the collected original electrical parameter data, perform data preprocessing on the verified data, and perform feature extraction related to the preprocessed data to obtain feature parameters for describing the fault characteristics; The fault analysis and location module is used to determine the fault type according to the characteristic parameters, and select the corresponding fault location algorithm according to the fault type to calculate the specific location of the fault point.

Images