Power distribution network fault fast positioning system

Abstract

The application relates to the technical field of power grid fault positioning, in particular to a power distribution network fault rapid positioning system which comprises an environment sensing module, a data fusion processing module, a fault detection and positioning module, a synchronous correlation module and a spatial information integration module; wherein: the environment sensing module is used for real-time monitoring of a power distribution network operation environment; the data fusion processing module is used for extracting effective information related to faults; the fault detection and positioning module is used for extracting fault characteristic signals and identifying and preliminarily positioning the fault characteristic signals; the synchronous correlation module is used for optimizing the output result of the fault detection and positioning module; and the spatial information integration module is used for generating a visual fault distribution map. Through integration of advanced signal processing technology, time synchronization, event correlation analysis and geographic information system visualization, the application significantly improves the fault detection speed and accuracy, optimizes the fault information processing flow, and improves the operation and maintenance efficiency and power grid management efficiency through intuitive fault display.

Description

Technical Field

[0001] This invention relates to the field of power grid fault location technology, and in particular to a rapid fault location system for distribution networks. Background Technology

[0002] In modern power systems, the stable operation of the distribution network is crucial. Rapid fault detection and accurate fault location are key to ensuring power supply and system security. Currently, the identification and location of distribution network faults mainly rely on traditional monitoring equipment and manual diagnosis. These methods often depend on a large amount of sensor data and complex manual analysis, which leads to prolonged fault handling time and makes it difficult to meet the needs of rapid response. In addition, common problems in existing technologies include difficulties in data synchronization, insufficient fault data analysis, and unintuitive fault information display, all of which seriously affect the efficiency and accuracy of fault handling.

[0003] To address the aforementioned issues, it is necessary to develop a new fault detection and location system. This system should be able to synchronize time data across all nodes of the power distribution network, analyze fault signals using advanced data processing techniques, and provide intuitive visualization of fault distribution by integrating geographic information system data, thereby improving the speed and accuracy of fault location. Summary of the Invention

[0004] To achieve the above objectives, the present invention provides a rapid fault location system for power distribution networks.

[0005] The power distribution network fault rapid location system includes an environmental sensing module, a data fusion and processing module, a fault detection and location module, a synchronization and correlation module, and a spatial information integration module; among which:

[0006] Environmental sensing module: used to monitor the operating environment of the power distribution network in real time, including temperature, humidity, meteorological conditions and electromagnetic interference parameters;

[0007] Data fusion processing module: Receives operating environment data transmitted by the environmental perception module, as well as electrical quantity data of each node in the distribution network. It processes the multi-source data through an algorithm combining improved Kalman filtering and Bayesian networks to extract effective information related to faults.

[0008] Fault detection and localization module: Based on the effective information provided by the data fusion processing module, the improved wavelet transform is first used to perform time-frequency analysis on the signal to extract fault feature signals; then, a convolutional neural network is used to identify the fault type and perform preliminary localization; finally, the detection results and localization information are transmitted to the synchronization association module.

[0009] Synchronization and Association Module: Receives the output results from the fault detection and location module, synchronizes the time data of each node in the distribution network, and uses event correlation technology to analyze the spatiotemporal relationship of fault events, thereby optimizing the output results of the fault detection and location module;

[0010] Spatial Information Integration Module: Receives the fault location information optimized by the Synchronization and Association Module, integrates it with the geographic information system data, and generates a visualized fault distribution map.

[0011] Furthermore, the environmental sensing module includes a temperature monitoring unit, a humidity monitoring unit, a meteorological condition monitoring unit, and an electromagnetic interference monitoring unit; wherein:

[0012] Temperature monitoring unit: includes multiple temperature sensors for real-time acquisition of temperature data at different nodes of the power distribution network. The temperature sensors are based on the thermocouple principle and use the electromotive force difference generated by the metal at different temperatures to measure the temperature. The analog signal is converted into a digital signal by a digital signal processor and transmitted to the data fusion processing module in real time.

[0013] Humidity monitoring unit: includes multiple humidity sensors for real-time collection of humidity data at different nodes of the power distribution network. The humidity sensors are based on the principle of capacitance humidity measurement, using the change in capacitance caused by humidity changes to measure humidity. The signal is amplified and filtered by the signal conditioning circuit before being transmitted to the data fusion processing module.

[0014] Meteorological Condition Monitoring Unit: Includes multiple meteorological sensors for real-time collection of meteorological data in the power distribution network area, including wind speed, wind direction, rainfall, and atmospheric pressure; the meteorological sensors are based on mechanical and electronic measurement principles, measuring meteorological parameters through mechanical motion and electronic signal conversion, and transmitting the collected data to the data fusion processing module;

[0015] Electromagnetic interference monitoring unit: includes multiple electromagnetic interference sensors for real-time detection of electromagnetic interference signals in the power distribution network. The electromagnetic interference sensors are based on the principle of electromagnetic induction, using the induced electromotive force generated by the induction coil when the electromagnetic field changes to detect electromagnetic interference signals. After processing by filtering and amplification circuits, the data is transmitted to the data fusion processing module.

[0016] Furthermore, the data fusion processing module includes a data receiving unit, a preprocessing unit, an improved Kalman filter unit, a Bayesian network processing unit, and a data output unit; wherein:

[0017] Data receiving unit: Used to receive operating environment data from the environmental sensing module and electrical quantity data from each node of the distribution network. This data receiving unit is connected to the sensor interfaces of the environmental sensing module and each node of the distribution network through a high-speed data bus to ensure real-time and accurate data transmission.

[0018] Preprocessing unit: performs preliminary processing on the received multi-source data, including data format conversion, noise filtering, and data alignment;

[0019] Improved Kalman Filter Unit: Performs dynamic filtering and state estimation on preprocessed data. Based on the extended Kalman filter algorithm and combined with the dynamic model of the distribution network, the improved Kalman filter unit performs state prediction and error correction on operating environment data and electrical quantity data to extract preliminary fault-related information.

[0020] Bayesian network processing unit: performs probabilistic inference and data fusion on the preliminary information output by the Kalman filter unit. Specifically, it uses the conditional probability distribution model of Bayesian network to fuse multi-source data and, combined with historical fault data and prior knowledge, deeply extracts effective information related to the fault.

[0021] Data output unit: Sends the fused data to downstream modules in real time through preset standard communication protocols and interfaces.

[0022] Furthermore, the improved Kalman filter unit includes:

[0023] State initialization: Define the initial state variable x0 and the initial covariance matrix P0 of the system to describe the initial state and initial uncertainties of the system;

[0024] Prediction steps: Based on the dynamic model of the distribution network, the system state is predicted using the state transition equation, and the prediction results are corrected using the process noise covariance Q1; the specific calculation formula is as follows:

[0025] x k|k-1 =f(x) k-1 ,u k-1 );

[0026] Where, x k|k-1 The predicted state from time k-1 to time k; u k-1 is the control input at time k-1; F1 is the Jacobian matrix of the state transition matrix; Q1 is the process noise covariance;

[0027] Measurement update steps: Correct the predicted state according to the measurement equation, and perform state correction by measuring the predicted value and Kalman gain. The specific correction formula is as follows:

[0028] z k|k-1 =h(x k|k-1 );

[0029]

[0030] Among them, z k|k-1H1 is the measurement prediction vector, representing the measured value calculated based on the predicted state; H2 is the Jacobian matrix of the measurement matrix, representing the linear approximation of the measurement model; S1 is the measurement prediction error covariance matrix, representing the covariance of the measurement error; R1 is the measurement noise covariance matrix, representing the measurement noise; K1 is the Kalman gain matrix, representing the weights for prediction error correction.

[0031] State Update: The predicted state is corrected using Kalman gain to obtain the updated state estimate and covariance matrix, as expressed by the following formula:

[0032] x k =x k|k-1 +K1(z k -z k|k-1 );

[0033] Where, x k P is the updated state estimate vector, representing the corrected system state. k Let z be the updated covariance matrix, representing the corrected state uncertainty; k This is a vector of actual measured values, representing the actual data obtained from the environmental sensing module and the distribution network nodes;

[0034] Fault information extraction: Based on the updated state estimate x k The covariance matrix P k Extract preliminary fault-related information.

[0035] Furthermore, the Bayesian network processing unit includes:

[0036] Node definition: Define the nodes in a Bayesian network, where each node represents a random variable, specifically including the state estimate x output by the Kalman filter unit. k Historical fault data h k and prior knowledge p k ;

[0037] Edge definition: Define the edges in a Bayesian network to represent the dependencies between nodes, using a conditional probability distribution model to describe the dependencies;

[0038] Conditional probability table construction: Based on historical data and expert knowledge, a conditional probability table is constructed to describe the probability distribution of each node given its parent node. Specifically, when the state estimate x... k Given historical fault data h k and prior knowledge p k The conditional probability under the given condition can be expressed as: P(x) k =x|h k =h,p k =p);

[0039] Probabilistic inference: Preliminary information x from the output of the Kalman filter unit k Probabilistic inference is performed by combining historical fault data and prior knowledge to calculate the posterior probability of a fault occurring. The Bayesian inference formula is as follows:

[0040] Among them, z k The actual measured values ​​obtained from the environmental sensing module and the distribution network nodes; P(z) k |x k P(x) is the likelihood function; k P(z) represents the prior probability; k ) as evidence;

[0041] Data fusion: Preliminary information is fused using a Bayesian network, combining a conditional probability distribution model and historical data to extract more in-depth fault-related information. The fused information includes an updated fault probability distribution and fault location estimation. The fusion formula is as follows: Among them, F k The merged fault information; Estimate the i-th state; Let be the posterior probability estimated for the i-th state.

[0042] Furthermore, the fault detection and location module includes a signal preprocessing unit, a time-frequency analysis unit, a fault identification unit, a location unit, and a result transmission unit; wherein:

[0043] Signal preprocessing unit: Used to receive valid information provided by the data fusion processing module and preprocess the signal, including noise reduction and normalization, to improve signal quality and analysis accuracy;

[0044] Time-frequency analysis unit: The improved wavelet transform is used to perform time-frequency analysis on the preprocessed signal. By using the preset mother wavelet function of the distribution network signal characteristics, the time domain signal is transformed into the time-frequency domain, making the fault characteristics more obvious at different frequencies and time scales, thereby improving the resolution and recognition ability of the fault signal to capture the transient characteristics of the fault signal.

[0045] Fault identification unit: Combines convolutional neural network to identify fault type by extracting fault feature signals. Specifically, the fault feature signals are input into the trained convolutional neural network model, and high-level features are extracted and classified through multi-layer convolution and pooling operations to identify fault type.

[0046] Location Unit: Based on the fault type information output by the fault identification unit, it performs preliminary fault location, determines the specific location of the fault by analyzing the time-frequency characteristics and spatial distribution information of the fault signal, and integrates the location information and fault type information to generate fault detection results;

[0047] Result Transmission Unit: Transmits fault detection results and location information to the synchronization association module.

[0048] Furthermore, the time-frequency analysis unit includes:

[0049] Selecting the mother wavelet function: Based on the characteristics of the distribution network fault signal, select a suitable mother wavelet function ψ(t). The mother wavelet functions include Daubechies wavelet, Haar wavelet and Symlet wavelet.

[0050] Signal decomposition: The preprocessed time-domain signal x(t) is decomposed into different frequencies and time scales using wavelet transform. The formula for continuous wavelet transform is: Among them, W x (a,b) are wavelet coefficients, representing the signal components at scale a and position b; ψ is the mother wavelet function; a is the scale parameter; b is the translation parameter; ψ * The complex conjugate of the mother wavelet function;

[0051] Multi-scale analysis: By adjusting the scale parameter a and the translation parameter b, the signal is analyzed at multiple scales. Small scales correspond to high-frequency details and are used to capture the transient characteristics of the signal; large scales correspond to low-frequency information and are used to reflect the overall trend of the signal; the distribution of fault features at different scales and times can be observed through wavelet coefficient plots.

[0052] Feature extraction: By analyzing the wavelet coefficient diagram, fault feature signals are extracted. For transient fault signals, the features will be manifested as abrupt changes in high-frequency components. The fault features are quantified by calculating the energy or amplitude of the wavelet coefficients.

[0053] Feature signal reconstruction: Based on the extracted feature signal, the wavelet coefficients are inversely transformed to reconstruct the fault feature signal. The reconstruction formula of discrete wavelet transform is: x(t)=∑ a,b W x (a,b)ψ a,b (t), where ψ a,b (t) represents the mother wavelet function at scale a and position b.

[0054] Furthermore, the positioning unit includes:

[0055] Receiving fault type information: The positioning unit first receives fault type information from the fault identification unit, including the fault type and its corresponding signal characteristic description;

[0056] Feature signal reconstruction: Reconstructing fault feature signals to obtain specific time-frequency characteristics and spatial distribution information;

[0057] Time-frequency analysis of fault signals: Analyze the time-frequency characteristics of the reconstructed signal, especially transient characteristics, including spikes and breaks. These characteristics are more pronounced in the high-frequency components of wavelet transform. By quantitatively analyzing the intensity and distribution of transient characteristics, the time point of fault occurrence can be determined.

[0058] Spatial distribution analysis: Combining the topology of the distribution network and the known sensor locations, the propagation and attenuation of fault characteristic signals at different locations are analyzed. The potential location of the fault source is calculated by using the speed and direction of signal propagation and the signal strength received from different sensors.

[0059] Precise fault location: Based on the combined results of time-frequency feature analysis and spatial distribution analysis, the specific location of the fault is accurately calculated using least squares estimation or triangulation algorithms.

[0060] Integrate fault information and output: Integrate location information and fault type information to generate fault detection results, including fault type, specific time and location of fault occurrence, and cause of fault.

[0061] Furthermore, the synchronization and association module includes a time synchronization unit, an event extraction unit, a spatiotemporal correlation analysis unit, and a result optimization unit; wherein:

[0062] Time synchronization unit: Used to receive the output results from the fault detection and location module, as well as the time data of each node in the distribution network. It achieves time synchronization through a preset network time protocol, ensuring that the timestamps of all nodes are consistent, eliminating clock drift and time errors, and providing an accurate time reference.

[0063] Event Extraction Unit: Extracts relevant event information from the output of the fault detection and localization module, including the time, type, and preliminary location information of the fault. By analyzing the fault signal, the event extraction unit identifies transient events related to the fault, providing basic data for subsequent spatiotemporal correlation analysis.

[0064] Spatiotemporal correlation analysis unit: Based on the synchronization time data provided by the time synchronization unit and the event information extracted by the event extraction unit, the spatiotemporal relationship of fault events is analyzed using event correlation technology. The specific analysis includes time series analysis.

[0065] The time-series analysis utilizes synchronized time data to perform time-series analysis on fault events, determining the sequence and time intervals of events. By comparing timestamps from different nodes, the fault propagation path and speed are identified. The time-series analysis formula is as follows: Where Δt is the time difference between node i and node j. and For the timestamp of the corresponding node;

[0066] The spatial correlation analysis, by combining geographic information system data of the power distribution network, analyzes the spatial distribution and correlation of fault events. Using the geographical location of the events and sensor layout, it determines the source and scope of the fault. The spatial correlation analysis formula is as follows: Where d is the distance between the two nodes, and (x1,y1) and (x2,y2) are the position coordinates of the nodes;

[0067] Result Optimization Unit: Based on the analysis results of the spatiotemporal correlation analysis unit, the preliminary location information of the fault detection and location module is optimized. Specifically, by comprehensively analyzing the temporal and spatial distribution of fault events, the preliminary location results are corrected to improve location accuracy. The optimized location information and fault type information are integrated to generate the final fault detection result. The optimized location formula is as follows: Among them, L optimized For the optimized positioning results, L initial For the initial localization result, L i Here is the location information for the i-th node, and α and β are weighting coefficients.

[0068] Furthermore, the spatial information integration module includes a data receiving unit, a data conversion unit, a spatial data processing unit, and a visualization generation unit; wherein:

[0069] Data receiving unit: used to receive optimized fault location information from the synchronization association module, as well as geographic data obtained from the geographic information system;

[0070] Data conversion unit: Converts the received optimized fault location information into a format that can be recognized by the geographic information system, and uses a spatial reference system and projection conversion method to match the location information with geographic coordinates to ensure accurate mapping of fault location information in geographic space;

[0071] Spatial data processing unit: The spatial data processing unit integrates the converted fault location information with geographic information system data. The spatial data processing unit uses spatial analysis technology to process and analyze the fault information, including spatial overlay, buffer analysis and spatial interpolation operations, to generate accurate fault distribution information.

[0072] Visualization generation unit: Based on the integrated and processed fault location information, it generates a visualized fault distribution map. The visualization generation unit uses the graphic rendering function of GIS software to display the fault information in a graphical way, including information on the fault point, the scope of impact, and the fault type.

[0073] The beneficial effects of this invention are:

[0074] This invention integrates improved wavelet transform and convolutional neural network (CNN) to effectively extract key fault features from large amounts of complex sensor data. This method uses the multi-scale analytical capability of wavelet transform to capture transient fault signals, while CNN performs in-depth learning and classification of these features, greatly improving the accuracy and speed of fault detection. Through this efficient signal processing and fault analysis technology, the system can respond quickly to faults, shorten power outage time, and improve the reliability of the power system.

[0075] This invention introduces a time synchronization unit and spatiotemporal correlation analysis technology to ensure that the data of each node in the distribution network is highly synchronized in time, thereby making the event correlation analysis more accurate. Through this synchronization and analysis, the system can clearly identify the propagation path and speed of the fault, as well as the specific location of the fault. This not only helps to quickly locate the fault source, but also provides important information for subsequent maintenance work, thereby optimizing the fault handling process and improving the repair efficiency.

[0076] This invention utilizes Geographic Information System (GIS) technology, combined with fault location information, to generate an intuitive fault distribution map. This visualization not only allows maintenance personnel to directly observe the geographical location and impact range of the fault, but also enables comparative analysis with historical data and the geographical environment, further assisting in decision-making. By providing this intuitive fault display method, this system greatly improves the efficiency of fault response and handling, while also strengthening the management and monitoring capabilities of the power distribution network. Attached Figure Description

[0077] To more clearly illustrate the technical solutions in this 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 for this invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0078] Figure 1 This is a schematic diagram of a power distribution network fault rapid location system according to an embodiment of the present invention;

[0079] Figure 2 This is a schematic diagram of the fault detection and location module according to an embodiment of the present invention. Detailed Implementation

[0080] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0081] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects.

[0082] like Figures 1-2 As shown, the rapid fault location system for power distribution networks includes an environmental sensing module, a data fusion and processing module, a fault detection and location module, a synchronization and correlation module, and a spatial information integration module; wherein:

[0083] Environmental sensing module: used to monitor the operating environment of the power distribution network in real time, including temperature, humidity, meteorological conditions and electromagnetic interference parameters, and transmit these data to the data fusion processing module;

[0084] Data fusion processing module: Receives operating environment data transmitted by the environmental perception module, as well as electrical quantity data of each node in the distribution network. It processes the multi-source data through an algorithm combining improved Kalman filtering and Bayesian networks, extracts effective information related to faults, and transmits it to the fault detection and location module.

[0085] Fault detection and localization module: Based on the effective information provided by the data fusion processing module, the improved wavelet transform is first used to perform time-frequency analysis on the signal to extract fault feature signals; then, a convolutional neural network is used to identify the fault type and perform preliminary localization; finally, the detection results and localization information are transmitted to the synchronization association module.

[0086] Synchronization and Association Module: Receives the output results of the fault detection and location module, synchronizes the time data of each node in the distribution network, and uses event correlation technology to analyze the spatiotemporal relationship of fault events, thereby optimizing the output results of the fault detection and location module. The processed data is then transmitted to the spatial information integration module.

[0087] Spatial Information Integration Module: Receives the fault location information optimized by the synchronization and association module, integrates it with Geographic Information System (GIS) data, and generates a visualized fault distribution map.

[0088] The environmental sensing module includes a temperature monitoring unit, a humidity monitoring unit, a meteorological condition monitoring unit, and an electromagnetic interference monitoring unit; among which:

[0089] Temperature monitoring unit: includes multiple temperature sensors for real-time acquisition of temperature data at different nodes of the power distribution network. The temperature sensors are based on the thermocouple principle and use the electromotive force difference generated by the metal at different temperatures to measure the temperature. The analog signal is converted into a digital signal by a digital signal processor and transmitted to the data fusion processing module in real time.

[0090] Humidity monitoring unit: includes multiple humidity sensors for real-time collection of humidity data at different nodes of the power distribution network. The humidity sensors are based on the principle of capacitance humidity measurement, using the change in capacitance caused by humidity changes to measure humidity. The signal is amplified and filtered by the signal conditioning circuit and then transmitted to the data fusion processing module.

[0091] Meteorological Condition Monitoring Unit: Includes multiple meteorological sensors for real-time collection of meteorological data in the power distribution network area, including wind speed, wind direction, rainfall, and atmospheric pressure; the meteorological sensors are based on mechanical and electronic measurement principles, measuring meteorological parameters through mechanical motion and electronic signal conversion, and transmitting the collected data to the data fusion processing module;

[0092] Electromagnetic Interference Monitoring Unit: This unit includes multiple electromagnetic interference sensors for real-time detection of electromagnetic interference signals in the power distribution network. Based on the principle of electromagnetic induction, these sensors utilize the induced electromotive force generated by an induction coil when the electromagnetic field changes to detect electromagnetic interference signals. After processing through filtering and amplification circuits, the data is transmitted to the data fusion processing module. The combination of these units enables more accurate real-time monitoring of the power distribution network's operating environment, including temperature, humidity, meteorological conditions, and electromagnetic interference parameters, ensuring high data accuracy and real-time performance. This provides a reliable foundation for subsequent data fusion processing and fault detection.

[0093] The data fusion processing module includes a data receiving unit, a preprocessing unit, an improved Kalman filter unit, a Bayesian network processing unit, and a data output unit; wherein:

[0094] Data receiving unit: Used to receive operating environment data from the environmental sensing module and electrical quantity data from each node of the distribution network. This data receiving unit is connected to the sensor interfaces of the environmental sensing module and each node of the distribution network through a high-speed data bus to ensure real-time and accurate data transmission.

[0095] Preprocessing unit: performs preliminary processing on the received multi-source data, including data format conversion, noise filtering, and data alignment;

[0096] Improved Kalman Filter Unit: Performs dynamic filtering and state estimation on preprocessed data. Based on the extended Kalman filter algorithm and combined with the dynamic model of the distribution network, the improved Kalman filter unit performs state prediction and error correction on operating environment data and electrical quantity data to extract preliminary fault-related information.

[0097] Bayesian network processing unit: performs probabilistic inference and data fusion on the preliminary information output by the Kalman filter unit. Specifically, it uses the conditional probability distribution model of Bayesian network to fuse multi-source data and, combined with historical fault data and prior knowledge, deeply extracts effective information related to the fault.

[0098] Data output unit: Through preset standard communication protocols and interfaces, the fused data is sent to downstream modules in real time to ensure the integrity and accuracy of the information. Through the combination of the above units, multi-source data can be processed and fused efficiently and accurately. The improved Kalman filter and Bayesian network combined algorithm improves the dynamic response and probabilistic inference capabilities of data processing, ensuring the accuracy and reliability of fault detection in complex environments. This multi-source data fusion processing technology provides a high-quality data foundation for the fault detection and location module, significantly improving the speed and accuracy of fault location in the distribution network and ensuring the safe and stable operation of the power grid.

[0099] The improved Kalman filter unit includes:

[0100] State initialization: Define the initial state variable x0 and the initial covariance matrix P0 of the system to describe the initial state and initial uncertainties of the system;

[0101] Prediction steps: Based on the dynamic model of the distribution network, the system state is predicted using the state transition equation, and the prediction results are corrected using the process noise covariance Q1; the specific calculation formula is as follows:

[0102] x k|k-1 =f(x) k-1 ,u k-1 );

[0103] Where, x k|k-1 The predicted state from time k-1 to time k; u k-1 is the control input at time k-1; F1 is the Jacobian matrix of the state transition matrix; Q1 is the process noise covariance;

[0104] Measurement update steps: Correct the predicted state according to the measurement equation, and perform state correction by measuring the predicted value and Kalman gain. The specific correction formula is as follows:

[0105] z k|k-1 =h(x k|k-1 );

[0106]

[0107] Among them, z k|k-1H1 is the measurement prediction vector, representing the measured value calculated based on the predicted state; H2 is the Jacobian matrix of the measurement matrix, representing the linear approximation of the measurement model; S1 is the measurement prediction error covariance matrix, representing the covariance of the measurement error; R1 is the measurement noise covariance matrix, representing the measurement noise; K1 is the Kalman gain matrix, representing the weights for prediction error correction.

[0108] State Update: The predicted state is corrected using Kalman gain to obtain the updated state estimate and covariance matrix, as expressed by the following formula:

[0109] x k =x k|k-1 +K1(z k -z k|k-1 );

[0110] Where, x k P is the updated state estimate vector, representing the corrected system state. k Let z be the updated covariance matrix, representing the corrected state uncertainty; k This is a vector of actual measured values, representing the actual data obtained from the environmental sensing module and the distribution network nodes;

[0111] Fault information extraction: Based on the updated state estimate x k The covariance matrix P k The above steps utilize the extended Kalman filter algorithm, combined with the dynamic model of the distribution network, to extract preliminary fault-related information, significantly improving the accuracy and response speed of fault detection. This provides a high-quality data foundation for the fault detection and location module, ensuring the safe and stable operation of the distribution network.

[0112] The Bayesian network processing unit includes:

[0113] Node definition: Define the nodes in a Bayesian network, where each node represents a random variable, specifically including the state estimate x output by the Kalman filter unit. k Historical fault data h k and prior knowledge p k ;

[0114] Edge definition: An edge in a Bayesian network is defined to represent the dependency between nodes. This dependency is described using a conditional probability distribution model, such as the state estimate x. k It relies on historical failure data and prior knowledge;

[0115] Conditional Probability Table Construction: Based on historical data and expert knowledge, a conditional probability table (CPT) is constructed to describe the probability distribution of each node given its parent node. Specifically, when the state estimate x...k Given historical fault data h k and prior knowledge p k The conditional probability under the given condition can be expressed as: P(x) k =x|h k =h,p k =p);

[0116] Probabilistic inference: Preliminary information x from the output of the Kalman filter unit k Probabilistic inference is performed by combining historical fault data and prior knowledge to calculate the posterior probability of a fault occurring. The Bayesian inference formula is as follows:

[0117] Among them, z k The actual measured values ​​obtained from the environmental sensing module and the distribution network nodes; P(z) k |x k P(x) is the likelihood function; k P(z) represents the prior probability; k ) as evidence;

[0118] Data fusion: Preliminary information is fused using a Bayesian network, combining a conditional probability distribution model and historical data to extract more in-depth fault-related information. The fused information includes an updated fault probability distribution and fault location estimation. The fusion formula is as follows: Among them, F k The merged fault information; Estimate the i-th state; The posterior probability of the i-th state is estimated. Through the working principle of the above steps, this system can effectively perform probabilistic inference and data fusion on the preliminary information output by the Kalman filter unit. By utilizing the conditional probability distribution model of the Bayesian network, combined with historical fault data and prior knowledge, it can deeply extract effective information related to the fault, improve the accuracy and reliability of fault location, provide solid data support for subsequent fault handling, and ensure the stable operation of the distribution network.

[0119] The fault detection and location module includes a signal preprocessing unit, a time-frequency analysis unit, a fault identification unit, a location unit, and a result transmission unit; wherein:

[0120] Signal preprocessing unit: Used to receive valid information provided by the data fusion processing module and preprocess the signal, including noise reduction and normalization, to improve signal quality and analysis accuracy. The preprocessed signal is then transmitted to the time-frequency analysis unit.

[0121] Time-frequency analysis unit: The preprocessed signal is analyzed using an improved wavelet transform. The time-domain signal is converted to the time-frequency domain by a preset mother wavelet function of the distribution network signal characteristics, making the fault characteristics more obvious at different frequencies and time scales, thereby improving the resolution and recognition capability of the fault signal to capture the transient characteristics of the fault signal. The extracted fault characteristic signal is then transmitted to the fault identification unit.

[0122] Fault identification unit: Combines convolutional neural network to identify the fault type by extracting fault feature signals. CNN is a deep learning algorithm with the ability to automatically extract and learn signal features. Specifically, the fault feature signals are input into the trained convolutional neural network model. Through multi-layer convolution and pooling operations, high-level features are extracted and classified to identify the fault type. The identification results are transmitted to the localization unit.

[0123] Location Unit: Based on the fault type information output by the fault identification unit, it performs preliminary fault location, determines the specific location of the fault by analyzing the time-frequency characteristics and spatial distribution information of the fault signal, and integrates the location information and fault type information to generate fault detection results;

[0124] The result transmission unit transmits fault detection results and location information to the synchronization and association module. This is achieved through standard communication protocols and data interfaces, ensuring information integrity and real-time performance, and supporting further analysis and optimization by the synchronization and association module. By detailing the working principles and unit composition of the fault detection and location module, this system can efficiently and accurately detect and locate faults in the distribution network. It utilizes improved wavelet transform for time-frequency analysis to extract precise fault feature signals, and combines this with convolutional neural networks for fault type identification and location, improving the accuracy and response speed of fault detection. This provides high-quality data support for subsequent fault handling, ensuring the stable operation of the distribution network.

[0125] The time-frequency analysis unit includes:

[0126] Selection of mother wavelet function: Based on the characteristics of the fault signal in the distribution network, a suitable mother wavelet function ψ(t) is selected. Mother wavelet functions include Daubechies wavelet, Haar wavelet and Symlet wavelet. The selected mother wavelet function needs to have good time-frequency localization characteristics in order to effectively capture the transient characteristics of the fault signal.

[0127] Signal decomposition: The preprocessed time-domain signal x(t) is decomposed into different frequencies and time scales using wavelet transform. The formula for continuous wavelet transform (CWT) is: Among them, W x (a,b) are wavelet coefficients, representing the signal components at scale a and position b; ψ is the mother wavelet function; a is the scale parameter; b is the translation parameter; ψ* The complex conjugate of the mother wavelet function;

[0128] Multi-scale analysis: By adjusting the scale parameter a and the translation parameter b, the signal is analyzed at multiple scales. Small scales correspond to high-frequency details and are used to capture the transient characteristics of the signal; large scales correspond to low-frequency information and are used to reflect the overall trend of the signal; the distribution of fault features at different scales and times can be observed through wavelet coefficient plots.

[0129] Feature extraction: Fault feature signals are extracted by analyzing wavelet coefficient diagrams. For transient fault signals, the features will manifest as abrupt changes in high-frequency components. The fault features are quantified by calculating the energy or amplitude of the wavelet coefficients. Specifically, the wavelet energy E(a,b) at scale a and time b is calculated, with the formula: E(a,b)=|W x (a,b)| 2 The change of wavelet energy at different scales can reveal the transient characteristics of fault signals;

[0130] Feature signal reconstruction: Based on the extracted feature signal, the wavelet coefficients are inversely transformed to reconstruct the fault feature signal. The reconstruction formula of Discrete Wavelet Transform (DWT) is: x(t)=∑ a,b W x (a,b)ψ a,b (t), where ψ a,b (t) represents the mother wavelet function at scale a and location b. The reconstructed fault feature signal is used for subsequent fault identification and location. Through the above steps, this system can efficiently and accurately perform time-frequency analysis on the preprocessed time-domain signal. By using the preset mother wavelet function of the distribution network signal characteristics, the signal is converted to the time-frequency domain, making the fault features more obvious at different frequencies and time scales, thereby improving the resolution and identification capability of the fault signal. This method effectively captures the transient features of the fault signal, providing high-quality feature signals for subsequent fault identification and location, and significantly improving the accuracy and response speed of fault detection.

[0131] The positioning unit includes:

[0132] Receiving fault type information: The positioning unit first receives fault type information from the fault identification unit, including the fault type and its corresponding signal characteristic description;

[0133] Feature signal reconstruction: Reconstructing fault feature signals to obtain specific time-frequency characteristics and spatial distribution information;

[0134] Time-frequency analysis of fault signals: Analyze the time-frequency characteristics of the reconstructed signal, especially transient characteristics, including spikes and breaks. These characteristics are more pronounced in the high-frequency components of wavelet transform. By quantitatively analyzing the intensity and distribution of transient characteristics, the time point of fault occurrence can be determined.

[0135] Spatial distribution analysis: Combining the topology of the distribution network and the known sensor locations, the propagation and attenuation of fault characteristic signals at different locations are analyzed. The potential location of the fault source is calculated by using the speed and direction of signal propagation and the signal strength received from different sensors.

[0136] Precise fault location: Based on the results of comprehensive time-frequency feature analysis and spatial distribution analysis, the specific location of the fault is accurately calculated using least squares estimation or triangulation algorithms. In this process, multiple data sources and fault indicators can be considered to improve the accuracy and reliability of the location.

[0137] Integrating fault information and output: The system integrates location information and fault type information to generate fault detection results, including the fault type, the specific time and location of the fault, and the cause of the fault. Through the steps of the above-mentioned public location unit, the system can effectively utilize the fault type information provided by the fault identification unit, combined with time-frequency characteristics and spatial distribution information, to perform preliminary fault location. By utilizing feature signal reconstruction and advanced signal analysis techniques, the system significantly improves the accuracy and efficiency of fault location. The ability to integrate fault information and output ensures the stability and security of the distribution network operation and provides reliable data support for rapid response and fault repair.

[0138] The synchronization and correlation module includes a time synchronization unit, an event extraction unit, a spatiotemporal correlation analysis unit, and a result optimization unit; among which:

[0139] Time synchronization unit: Receives output from the fault detection and location module, as well as time data from each node in the distribution network. It achieves time synchronization through a preset Network Time Protocol (NTP), ensuring consistent timestamps across all nodes, eliminating clock drift and time errors, and providing an accurate time reference. The time synchronization formula is as follows: Among them, T corrected For the corrected time, T received To receive the timestamp, T sent For sending timestamps, T reply To reply with a timestamp, T transmit For transmission timestamp;

[0140] Event Extraction Unit: Extracts relevant event information from the output of the fault detection and localization module, including the time, type, and preliminary location information of the fault. By analyzing the fault signal, the event extraction unit identifies transient events related to the fault, providing basic data for subsequent spatiotemporal correlation analysis.

[0141] Spatiotemporal correlation analysis unit: Based on the synchronization time data provided by the time synchronization unit and the event information extracted by the event extraction unit, the spatiotemporal relationship of fault events is analyzed using event correlation technology. The specific analysis includes time series analysis.

[0142] Time series analysis utilizes synchronized time data to perform time series analysis on fault events, determining the sequence and time intervals of events. By comparing timestamps from different nodes, it identifies the fault propagation path and speed. The time series analysis formula is as follows: Where Δt is the time difference between node i and node j. and For the timestamp of the corresponding node;

[0143] Spatial correlation analysis combines geographic information system (GIS) data from the power distribution network to analyze the spatial distribution and correlation of fault events. By utilizing the geographical location of the events and sensor layout, it determines the fault source and its impact range. The formula for spatial correlation analysis is: Where d is the distance between the two nodes, and (x1,y1) and (x2,y2) are the position coordinates of the nodes;

[0144] Result Optimization Unit: Based on the analysis results of the spatiotemporal correlation analysis unit, the preliminary location information of the fault detection and location module is optimized. Specifically, by comprehensively analyzing the temporal and spatial distribution of fault events, the preliminary location results are corrected to improve location accuracy. The optimized location information and fault type information are integrated to generate the final fault detection result. The optimized location formula is as follows: Among them, L optimized For the optimized positioning results, L initial For the initial localization result, L i The location information of the i-th node is represented by α and β, which are weighting coefficients. By combining the above units, the time data of each node in the distribution network can be effectively synchronized. Event correlation technology is used to analyze the spatiotemporal relationship of fault events, thereby optimizing the output results of the fault detection and location module. By utilizing precise time synchronization and event correlation analysis technology, this system significantly improves the accuracy and reliability of fault location, provides strong data support for the rapid response and handling of distribution network faults, and ensures the stable operation of the power grid.

[0145] The spatial information integration module includes a data receiving unit, a data conversion unit, a spatial data processing unit, and a visualization generation unit; among which:

[0146] Data receiving unit: Used to receive optimized fault location information from the synchronization association module, as well as geographic data obtained from the Geographic Information System (GIS). The data receiving unit exchanges data with other modules through standard data interfaces and communication protocols to ensure the real-time performance and accuracy of the data.

[0147] Data conversion unit: Converts the received optimized fault location information into a format that can be recognized by the geographic information system, and uses a spatial reference system (SRS) and projection conversion method to match the location information with geographic coordinates to ensure accurate mapping of fault location information in geographic space;

[0148] Spatial data processing unit: The spatial data processing unit integrates the converted fault location information with geographic information system data. The spatial data processing unit uses spatial analysis technology to process and analyze the fault information, including spatial overlay, buffer analysis and spatial interpolation operations, to generate accurate fault distribution information.

[0149] The visualization generation unit generates a visualized fault distribution map based on the integrated fault location information. Utilizing the graphics rendering capabilities of GIS software, this unit displays fault information graphically, including fault location, impact range, and fault type. This ensures the generated distribution map has high resolution and a clear hierarchical structure, facilitating intuitive monitoring and analysis by maintenance personnel. Through the combination of these units, the system efficiently integrates the optimized fault location information from the synchronous association module with geographic information system data to generate a visualized fault distribution map. By leveraging spatial data processing and visualization technologies, this system significantly improves the display effect and operability of fault information, providing strong support for the rapid location and handling of distribution network faults. The generated visualized fault distribution map helps maintenance personnel intuitively understand the location and impact range of faults, ensuring the stable operation of the power grid.

[0150] This invention is intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A rapid fault location system for power distribution networks, characterized in that, It includes an environmental perception module, a data fusion and processing module, a fault detection and location module, a synchronization and association module, and a spatial information integration module; among which: Environmental sensing module: used to monitor the operating environment of the power distribution network in real time, including temperature, humidity, meteorological conditions and electromagnetic interference parameters; The data fusion processing module receives operating environment data transmitted by the environmental sensing module, as well as electrical quantity data from various nodes of the distribution network. It processes the multi-source data using an algorithm combining an improved Kalman filter and a Bayesian network to extract effective information related to faults. The data fusion processing module includes a data receiving unit, a preprocessing unit, an improved Kalman filter unit, a Bayesian network processing unit, and a data output unit. The improved Kalman filter unit includes: State initialization: Define the initial state variables of the system. and the initial covariance matrix , used to describe the initial state and initial uncertainties of the system; Prediction steps: Based on the dynamic model of the distribution network, the system state is predicted using the state transition equation, and the process noise covariance is used. The prediction results are corrected; the specific calculation formula is as follows: ； ,in, For a moment At the time The predicted state; For a moment Control input; The Jacobian matrix of the state transition matrix; For process noise covariance; Measurement update steps: Correct the predicted state according to the measurement equation, and perform state correction by measuring the predicted value and Kalman gain. The specific correction formula is as follows: ； ； ;in, This is a vector of measured predicted values, representing the measured values ​​calculated based on the predicted state. Let be the Jacobian matrix of the measurement matrix, representing a linear approximation of the measurement model; The measurement prediction error covariance matrix represents the covariance of the measurement error; The measurement noise covariance matrix represents the measurement noise; Here, is the Kalman gain matrix, representing the weights for prediction error correction; State Update: The predicted state is corrected using Kalman gain to obtain the updated state estimate and covariance matrix, as expressed by the following formula: ； ,in, The updated state estimation vector represents the corrected system state; Let be the updated covariance matrix, representing the corrected state uncertainty; This is a vector of actual measured values, representing the actual data obtained from the environmental sensing module and the distribution network nodes; Fault information extraction: based on the updated state estimation Covariance Matrix Extract preliminary fault-related information; Fault detection and localization module: Based on the effective information provided by the data fusion processing module, the improved wavelet transform is first used to perform time-frequency analysis on the signal to extract fault feature signals; then, a convolutional neural network is used to identify the fault type and perform preliminary localization; finally, the detection results and localization information are transmitted to the synchronization association module. Synchronization and Association Module: Receives the output results from the fault detection and location module, synchronizes the time data of each node in the distribution network, and uses event correlation technology to analyze the spatiotemporal relationship of fault events, thereby optimizing the output results of the fault detection and location module; Spatial Information Integration Module: Receives the fault location information optimized by the Synchronization and Association Module, integrates it with the geographic information system data, and generates a visualized fault distribution map.

2. The rapid fault location system for power distribution networks according to claim 1, characterized in that, The environmental sensing module includes a temperature monitoring unit, a humidity monitoring unit, a meteorological condition monitoring unit, and an electromagnetic interference monitoring unit; wherein: Temperature monitoring unit: includes multiple temperature sensors for real-time acquisition of temperature data at different nodes of the power distribution network. The temperature sensors are based on the thermocouple principle and use the electromotive force difference generated by the metal at different temperatures to measure the temperature. The analog signal is converted into a digital signal by a digital signal processor and transmitted to the data fusion processing module in real time. Humidity monitoring unit: includes multiple humidity sensors for real-time collection of humidity data at different nodes of the power distribution network. The humidity sensors are based on the principle of capacitance humidity measurement, using the change in capacitance caused by humidity changes to measure humidity. The signal is amplified and filtered by the signal conditioning circuit before being transmitted to the data fusion processing module. Meteorological Condition Monitoring Unit: Includes multiple meteorological sensors for real-time collection of meteorological data in the power distribution network area, including wind speed, wind direction, rainfall, and atmospheric pressure; the meteorological sensors are based on mechanical and electronic measurement principles, measuring meteorological parameters through mechanical motion and electronic signal conversion, and transmitting the collected data to the data fusion processing module; Electromagnetic interference monitoring unit: includes multiple electromagnetic interference sensors for real-time detection of electromagnetic interference signals in the power distribution network. The electromagnetic interference sensors are based on the principle of electromagnetic induction, using the induced electromotive force generated by the induction coil when the electromagnetic field changes to detect electromagnetic interference signals. After processing by filtering and amplification circuits, the data is transmitted to the data fusion processing module.

3. The rapid fault location system for power distribution networks according to claim 1, characterized in that, The data receiving unit is used to receive operating environment data from the environmental sensing module and electrical quantity data from each node of the distribution network. The data receiving unit is connected to the sensor interfaces of the environmental sensing module and each node of the distribution network through a high-speed data bus to ensure real-time and accurate data transmission. The preprocessing unit performs preliminary processing on the received multi-source data, including data format conversion, noise filtering and data alignment. The improved Kalman filter unit performs dynamic filtering and state estimation on the preprocessed data. Based on the extended Kalman filter algorithm and combined with the dynamic model of the distribution network, the improved Kalman filter unit performs state prediction and error correction on the operating environment data and electrical quantity data to extract preliminary fault-related information. The Bayesian network processing unit performs probabilistic inference and data fusion on the preliminary information output by the Kalman filter unit. Specifically, it uses the conditional probability distribution model of Bayesian network to fuse multi-source data and combines historical fault data and prior knowledge to deeply extract effective information related to faults. The data output unit sends the fused data to the downstream module in real time through a preset standard communication protocol and interface.

4. The rapid fault location system for power distribution networks according to claim 3, characterized in that, The Bayesian network processing unit includes: Node Definition: Define the nodes in a Bayesian network, where each node represents a random variable, specifically including the state estimate output by the Kalman filter unit. Historical fault data and prior knowledge ; Edge definition: Define the edges in a Bayesian network to represent the dependencies between nodes, using a conditional probability distribution model to describe the dependencies; Conditional probability table construction: Based on historical data and expert knowledge, a conditional probability table is constructed to describe the probability distribution of each node given its parent node. Specifically, this table is used when state estimation... Given historical fault data and prior knowledge The conditional probability under the given condition is expressed as: ; Probabilistic Inference: Preliminary Information from the Kalman Filter Unit Output Probabilistic inference is performed by combining historical fault data and prior knowledge to calculate the posterior probability of a fault occurring. The Bayesian inference formula is as follows: ,in, These are the actual measurement values ​​obtained from the environmental sensing module and the distribution network nodes; It is the likelihood function; This is the prior probability; As evidence; Data fusion: Preliminary information is fused using a Bayesian network, combining a conditional probability distribution model and historical data to extract more in-depth fault-related information. The fused information includes an updated fault probability distribution and fault location estimation. The fusion formula is as follows: , among which, among which, The merged fault information; For the first One state estimate; For the first The posterior probability of each state estimate.

5. The rapid fault location system for power distribution networks according to claim 1, characterized in that, The fault detection and location module includes a signal preprocessing unit, a time-frequency analysis unit, a fault identification unit, a location unit, and a result transmission unit; wherein: Signal preprocessing unit: Used to receive valid information provided by the data fusion processing module and preprocess the signal, including noise reduction and normalization, to improve signal quality and analysis accuracy; Time-frequency analysis unit: The improved wavelet transform is used to perform time-frequency analysis on the preprocessed signal. By using the preset mother wavelet function of the distribution network signal characteristics, the time domain signal is transformed into the time-frequency domain, making the fault characteristics more obvious at different frequencies and time scales, thereby improving the resolution and recognition ability of the fault signal to capture the transient characteristics of the fault signal. Fault identification unit: Combines convolutional neural network to identify fault type by extracting fault feature signals. Specifically, the fault feature signals are input into the trained convolutional neural network model, and high-level features are extracted and classified through multi-layer convolution and pooling operations to identify fault type. Location Unit: Based on the fault type information output by the fault identification unit, it performs preliminary fault location, determines the specific location of the fault by analyzing the time-frequency characteristics and spatial distribution information of the fault signal, and integrates the location information and fault type information to generate fault detection results; Result Transmission Unit: Transmits fault detection results and location information to the synchronization association module.

6. The rapid fault location system for power distribution networks according to claim 5, characterized in that, The time-frequency analysis unit includes: Selection of the mother wavelet function: Based on the characteristics of the distribution network fault signal, a suitable mother wavelet function is selected. The mother wavelet functions include the Daubechies wavelet, Haar wavelet, and Symlet wavelet; Signal decomposition: This involves converting the preprocessed time-domain signal... By decomposing the wavelet transform into different frequencies and time scales, the formula for the continuous wavelet transform is: ,in, The wavelet coefficients represent the scale. and location The signal components on; For the mother wavelet function; For scale parameters; These are translation parameters; The complex conjugate of the mother wavelet function; Multiscale analysis: By adjusting the scale parameters Translation parameters Multi-scale analysis of the signal is performed. Small scale corresponds to high-frequency details and is used to capture the transient characteristics of the signal; large scale corresponds to low-frequency information and is used to reflect the overall trend of the signal; the distribution of fault features at different scales and times is observed through wavelet coefficient plots. Feature extraction: By analyzing the wavelet coefficient diagram, fault feature signals are extracted. For transient fault signals, the features will be manifested as abrupt changes in high-frequency components. The fault features are quantified by calculating the energy or amplitude of the wavelet coefficients. Feature signal reconstruction: Based on the extracted feature signal, the wavelet coefficients are inversely transformed to reconstruct the fault feature signal. The reconstruction formula of discrete wavelet transform is: ,in, For scale and location The mother wavelet function on.

7. The rapid fault location system for power distribution networks according to claim 6, characterized in that, The positioning unit includes: Receiving fault type information: The positioning unit first receives fault type information from the fault identification unit, including the fault type and its corresponding signal characteristic description; Feature signal reconstruction: Reconstructing fault feature signals to obtain specific time-frequency characteristics and spatial distribution information; Time-frequency analysis of fault signals: Analyze the time-frequency characteristics of the reconstructed signal, including transient characteristics, such as spikes and breaks. These characteristics are more pronounced in the high-frequency components of wavelet transform. By quantitatively analyzing the intensity and distribution of transient characteristics, the time point of fault occurrence can be determined. Spatial distribution analysis: Combining the topology of the distribution network and the known sensor locations, the propagation and attenuation of fault characteristic signals at different locations are analyzed. The potential location of the fault source is calculated by using the speed and direction of signal propagation and the signal strength received from different sensors. Precise fault location: Based on the combined results of time-frequency feature analysis and spatial distribution analysis, the specific location of the fault is accurately calculated using least squares estimation or triangulation algorithms. Integrate fault information and output: Integrate location information and fault type information to generate fault detection results, including fault type, specific time and location of fault occurrence, and cause of fault.

8. The rapid fault location system for power distribution networks according to claim 1, characterized in that, The synchronization and association module includes a time synchronization unit, an event extraction unit, a spatiotemporal correlation analysis unit, and a result optimization unit; wherein: Time synchronization unit: Used to receive the output results from the fault detection and location module, as well as the time data of each node in the distribution network. It achieves time synchronization through a preset network time protocol, ensuring that the timestamps of all nodes are consistent, eliminating clock drift and time errors, and providing an accurate time reference. Event Extraction Unit: Extracts relevant event information from the output of the fault detection and localization module, including the time, type, and preliminary location information of the fault. By analyzing the fault signal, the event extraction unit identifies transient events related to the fault, providing basic data for subsequent spatiotemporal correlation analysis. Spatiotemporal correlation analysis unit: Based on the synchronization time data provided by the time synchronization unit and the event information extracted by the event extraction unit, the spatiotemporal relationship of fault events is analyzed using event correlation technology. The specific analysis includes time series analysis. The time-series analysis utilizes synchronized time data to perform time-series analysis on fault events, determining the sequence and time intervals of events. By comparing timestamps from different nodes, the fault propagation path and speed are identified. The time-series analysis formula is as follows: ,in, For nodes and nodes The time difference between them and For the timestamp of the corresponding node; The spatial correlation analysis, by combining geographic information system data of the power distribution network, analyzes the spatial distribution and correlation of fault events. Using the geographical location of the events and sensor layout, it determines the source and scope of the fault. The spatial correlation analysis formula is as follows: ,in, The distance between the two nodes. and These are the position coordinates of the node; Result Optimization Unit: Based on the analysis results of the spatiotemporal correlation analysis unit, the preliminary location information of the fault detection and location module is optimized. Specifically, by comprehensively analyzing the temporal and spatial distribution of fault events, the preliminary location results are corrected to improve location accuracy. The optimized location information and fault type information are integrated to generate the final fault detection result. The optimized location formula is as follows: ,in, The optimized positioning results This is the initial localization result. For the first Location information of each node, and These are the weighting coefficients.

9. The rapid fault location system for power distribution networks according to claim 1, characterized in that, The spatial information integration module includes a data receiving unit, a data conversion unit, a spatial data processing unit, and a visualization generation unit; wherein: Data receiving unit: used to receive optimized fault location information from the synchronization association module, as well as geographic data obtained from the geographic information system; Data conversion unit: Converts the received optimized fault location information into a format that can be recognized by the geographic information system, and uses a spatial reference system and projection conversion method to match the location information with geographic coordinates to ensure accurate mapping of fault location information in geographic space; Spatial data processing unit: The spatial data processing unit integrates the converted fault location information with geographic information system data. The spatial data processing unit uses spatial analysis technology to process and analyze the fault information, including spatial overlay, buffer analysis and spatial interpolation operations, to generate accurate fault distribution information. Visualization generation unit: Based on the integrated and processed fault location information, it generates a visualized fault distribution map. The visualization generation unit uses the graphic rendering function of GIS software to display the fault information in a graphical way, including information on the fault point, the scope of impact, and the fault type.

Images