Real-time fault detection and automatic repair system for power grid

Abstract

The invention relates to a real-time fault detection and automatic repair system for a power grid. The real-time fault detection and automatic repair system comprises a multi-level sensing module, a data processing module, an automatic repair module and a monitoring and logging module. The multi-level sensing module collects data such as voltage, current, frequency and temperature in operation of a power grid by deploying multiple types of sensors, and sends the data to the data processing module. And the data processing module analyzes the collected data through an embedded intelligent algorithm, identifies potential faults and generates fault diagnosis results. And the automatic repair module executes repair operations of isolating a fault area, reconstructing a power grid topological structure and recovering normal power supply according to a fault diagnosis result. The monitoring and log module records the operation state of the power grid and the fault diagnosis and repair process, and provides fault analysis and performance evaluation functions through a user interface. According to the system, real-time detection, accurate positioning and automatic repair of power grid faults and comprehensive monitoring of operation data are realized, and the safety and reliability of power grid operation are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a power grid real-time fault detection and automatic repair system. Background Art

[0002] In the prior art, a variety of faults may occur during the operation of the power grid, including short circuits, overloads, and equipment abnormalities. In order to improve the reliability of the power grid, existing systems collect power grid operation data and analyze its status through sensors. Some systems can locate faults and handle them manually or semi-automatically. In addition, some intelligent systems can provide basic monitoring functions for power grid operation, but they are often limited to data recording after a fault occurs and handling of a single fault.

[0003] However, the existing technology still has obvious problems, mainly reflected in the lack of real-time fault detection, inaccurate diagnostic results and low automation of the repair process. The existing system has limitations in identifying fault types and assessing the scope of impact. At the same time, the topology reconstruction and repair operations of the power grid often require manual intervention, which is difficult to meet the needs of modern power grids for rapid recovery and high reliability.

[0004] In order to solve the above problems, the present invention provides a new real-time fault detection and automatic repair system for power grid. Summary of the invention

[0005] The present application provides a real-time power grid fault detection and automatic repair system to improve the safety and reliability of power grid operation.

[0006] The present application provides a power grid real-time fault detection and automatic repair system, comprising:

[0007] A multi-level perception module, used to collect the operation data of the power grid through multiple types of sensors, and send the collected operation data to the data processing module; wherein the operation data includes voltage, current, frequency and temperature;

[0008] A data processing module, configured to receive the operation data provided by the multi-level perception module; analyze the operation data through an embedded intelligent algorithm to identify potential faults, and generate a fault diagnosis result when a fault is detected, wherein the fault diagnosis result includes the fault type, fault location, and impact range;

[0009] An automated repair module, configured to perform repair operations according to the fault diagnosis results generated by the data processing module, wherein the repair operations include isolating the fault area, reconstructing the grid topology, and restoring normal power supply;

[0010] The monitoring and logging module is used to record the grid operation status, fault diagnosis results and repair operation process, generate historical data reports, and provide fault analysis and operation performance evaluation through the user interface.

[0011] Furthermore, the multi-level perception module is specifically used for:

[0012] Deploy voltage sensors and current sensors at substations, transmission and distribution lines, and load ends to collect voltage and current data of each node in real time. The voltage sensor is used to detect the instantaneous value of the node voltage, and the current sensor is used to monitor the amplitude and direction of the current.

[0013] Install temperature sensors at high-load equipment and key line locations to regularly detect the temperature rise of the equipment casing and lines, and send temperature data to the data processing unit through the wireless communication module;

[0014] A frequency acquisition device is integrated in the main substation to continuously sample changes in system frequency, capture frequency deviations caused by load fluctuations or faults, and encapsulate all collected data and transmit them to the data processing module.

[0015] Furthermore, the automated repair module is specifically used for:

[0016] Based on the fault diagnosis result, a circuit breaker control unit is activated to isolate the identified fault area, wherein the isolation includes physically disconnecting the faulty line or equipment from the normal power supply part;

[0017] Calculate the grid topology of the non-fault area, generate a new power supply path by enabling backup power sources, backup lines or redistributing existing loads, and send instructions to related switchgear through the communication module to perform topology reconstruction;

[0018] After confirming that the topology adjustment is complete, adjust the voltage level and power supply through the transformer to gradually restore power supply to the normal load area.

[0019] Furthermore, the monitoring and logging module is specifically used for:

[0020] The status acquisition unit obtains real-time operation data, including voltage, current, frequency and temperature parameters, records abnormal data when a fault occurs, and generates a snapshot of the operation status before and after the fault;

[0021] During the fault repair process, the specific steps and execution time of isolation operations, topology adjustments, and power restoration are recorded in real time;

[0022] After the repair is completed, a complete log report including grid operation status data, fault cause analysis and repair process is generated and displayed to the operator and stored through a visual interface.

[0023] Furthermore, the intelligent algorithm adopted by the data processing module is implemented using the following steps:

[0024] The operation data collected by the multi-level perception module is decomposed by wavelet transform, and low-frequency components are extracted by removing high-frequency noise; sliding window time series analysis is performed on the low-frequency components to extract characteristic data reflecting the operation status of the power grid and generate power grid characteristic data; wherein the extracted characteristic data includes the current waveform change rate, voltage imbalance and frequency offset characteristics;

[0025] The feature data is input into a pre-trained support vector machine classifier, and the classification boundary is dynamically optimized based on historical samples and real-time load data to generate a diagnosis result of the fault type; abnormal operating parameters related to the fault type are marked according to the diagnosis result, and the fault type includes short circuit, overload, line break or equipment abnormality;

[0026] According to the diagnosis results of the fault type and the marked abnormal operating parameters, the source of the voltage or current change is analyzed based on the abnormal current propagation path by tracing back the physical structure of the power grid layer by layer; based on the analysis results of the source of the voltage or current change, the specific location of the fault is determined in combination with the operating characteristics of the equipment and lines, and the fault location results including the identification of the faulty equipment or line are generated;

[0027] Based on the fault location results, combined with the connection relationship and real-time load status of the equipment in the power grid, the fault impact range is analyzed by step-by-step propagation, and the operating status changes of substations, transmission lines and load equipment and their affected areas are gradually calculated; when the impact is weakened to a pre-set negligible range, complete detailed information on the affected area is generated, including equipment identification, operating parameter change values ​​and specific impact range.

[0028] Furthermore, the operation data collected by the multi-level perception module is decomposed by wavelet transform, and low-frequency components are extracted by removing high-frequency noise, including:

[0029] According to the following formula (1) and formula (2), define the wavelet basis function ψ j,k (t) and φ j,k (t):

[0030]

[0031] Where, t represents the sampling time; j represents the scale parameter; k represents the time shift parameter;

[0032] ψ(t) and φ(t) are basis functions of the wavelet function, as shown in the following formulas (3) and (4):

[0033] ψ(t)=exp(-αt 2)cos(2πβt) (3)

[0034] φ(t)=exp(-αt 2 ) (4)

[0035] Among them, α is the frequency offset adjustment parameter; β is the waveform adjustment parameter; t represents the sampling time;

[0036] According to the following formulas (5) and (6), the running data x(t) is decomposed into multiple scales to generate the high-frequency component D j (t) and low-frequency component A j (t):

[0037]

[0038] According to the following formula (7), calculate the high-frequency component threshold T:

[0039]

[0040] Wherein, η is the proportional factor set based on the statistical characteristics of power grid operation data; N is the number of sampling points;

[0041] D j The high-frequency component of (t)|>T is set to zero to remove noise, and the denoised high-frequency component is obtained;

[0042] By performing inverse wavelet transform on the denoised high-frequency and low-frequency components, the low-frequency components reflecting the operating status of the power grid are reconstructed and extracted as the key feature input to describe the power grid status.

[0043] This application has the following beneficial technical effects:

[0044] (1) This application can accurately identify potential faults in power grid operation through the intelligent algorithm embedded in the data processing module, combined with the multi-dimensional operation data collected by the multi-level perception module, and generate diagnostic results including fault type, fault location and impact range, providing a reliable basis for quickly taking repair measures. (2) The automated repair module can autonomously perform isolation operations in the fault area based on the diagnostic results, quickly reconstruct the power grid topology, and restore normal power supply, significantly reducing power outage time and the need for manual intervention, and improving the operation reliability and maintenance efficiency of the power grid. (3) Through the monitoring and logging module, the system can record the operation status of the power grid, fault diagnosis results and repair operation process in detail, generate historical data reports, and provide intuitive fault analysis and performance evaluation through the user interface to support power grid operation optimization and maintenance decision-making. (4) The system realizes real-time response to the entire process from fault detection to repair, and has the ability to quickly handle sudden faults. At the same time, the modular design makes each functional unit independent and collaborative, which is convenient for flexible configuration and expansion according to the scale of the power grid and application requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic diagram of a power grid real-time fault detection and automatic repair system provided in the first embodiment of the present application. DETAILED DESCRIPTION

[0046] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0047] The first embodiment of the present application provides a real-time fault detection and automatic repair system for a power grid. Figure 1 , which is a schematic diagram of the first embodiment of the present application. Figure 1 A first embodiment of the present application provides a power grid real-time fault detection and automatic repair system for detailed description.

[0048] The real-time fault detection and automatic repair system for power grid includes a multi-level perception module 101, a data processing module 102, an automatic repair module 103 and a monitoring and log module.

[0049] The multi-level sensing module 101 is used to collect the operation data of the power grid through multiple types of sensors, and send the collected operation data to the data processing module; wherein the operation data includes voltage, current, frequency and temperature.

[0050] The multi-level sensing module 101 is designed to efficiently and in real time collect key parameters of power grid operation through various types of sensors, including voltage, current, frequency and temperature. The module can be deployed at multiple key locations of the power grid, including substations, transmission and distribution line nodes, load centers and access points of important equipment, to achieve comprehensive monitoring of the power grid operation status.

[0051] First, voltage sensors and current sensors are installed at the high-voltage busbars of the substation, the intermediate nodes of the transmission and distribution lines, and the important load access points. The voltage sensor can collect the instantaneous value of the node voltage in real time to monitor the stability of the grid voltage; the current sensor is responsible for capturing the amplitude and direction information of the node current to evaluate the current distribution and load conditions. The sensor sends the collected data to the module's integrated data collection unit through a standard communication protocol (such as MODBUS or IEC 61850).

[0052] Secondly, temperature sensors are installed at key points of the line, on the casing of high-load equipment, and on transformers of the power grid to monitor temperature changes of the equipment. Temperature data is particularly important because temperature rise may indicate line overload or equipment abnormality. The sensor transmits data to the central processor of the multi-level perception module through a wireless communication module (such as ZigBee or LoRa).

[0053] For frequency detection, the module integrates a high-precision frequency acquisition device, which is installed on the low-voltage side of the main substation. It can monitor the operating frequency of the power grid at a high sampling rate (for example, 100 times per second) and capture frequency deviations caused by load fluctuations or faults. In addition, the device has anti-interference function and can maintain high-precision measurement in a strong electromagnetic interference environment.

[0054] The multi-level perception module 101 also includes a data integration and packaging unit for aggregating, formatting and packaging data from different types of sensors to form standardized data packets. The unit ensures the consistency of timestamps of all collected data through a time synchronization mechanism (e.g., GPS-based clock synchronization), thereby improving the accuracy of data analysis.

[0055] Finally, the module is equipped with a reliable data transmission function. The integrated communication module supports multiple communication methods, including wired methods (such as Ethernet or optical fiber) and wireless methods (such as LTE or 5G), to ensure that the collected data can be quickly and stably transmitted to the data processing module 102. To improve the robustness of data transmission, the module also has a data buffering and retransmission mechanism, which can temporarily store data when communication is interrupted and resend it after recovery to avoid data loss.

[0056] Through the above design, the multi-level perception module 101 realizes multi-dimensional monitoring of the power grid operation status and efficient data transmission, providing reliable data support for subsequent data processing and fault diagnosis.

[0057] Furthermore, the multi-level perception module is specifically used for:

[0058] Deploy voltage sensors and current sensors at substations, transmission and distribution lines, and load ends to collect voltage and current data of each node in real time. The voltage sensor is used to detect the instantaneous value of the node voltage, and the current sensor is used to monitor the amplitude and direction of the current.

[0059] Install temperature sensors at high-load equipment and key line locations to regularly detect the temperature rise of the equipment casing and lines, and send temperature data to the data processing unit through the wireless communication module;

[0060] A frequency acquisition device is integrated in the main substation to continuously sample changes in system frequency, capture frequency deviations caused by load fluctuations or faults, and encapsulate all collected data and transmit them to the data processing module.

[0061] The multi-level perception module fully considers the operation monitoring needs of different locations in the power grid. By deploying multiple types of sensors in substations, transmission and distribution lines, load ends and other key areas, it realizes real-time collection and transmission of operation data such as voltage, current, temperature and frequency, providing comprehensive basic data support for monitoring the operation status of the power grid and fault diagnosis.

[0062] At substations, transmission and distribution lines, and load ends, voltage sensors and current sensors are deployed to cover the main nodes and paths of the power grid. Voltage sensors are specifically designed to detect the instantaneous value of voltage at nodes, and their design accuracy can meet the high sensitivity requirements for voltage fluctuations in power grid operation. These sensors are usually connected to key points of high-voltage busbars and transmission lines, and can capture rapid drops in voltage or other abnormal changes when a fault occurs. Current sensors are installed at the entrance of transmission and distribution lines and load equipment, and have the ability to monitor current amplitude and direction. These sensors provide key data support for fault location and load analysis by detecting the flow characteristics of current.

[0063] Temperature sensors are used to monitor the temperature rise of equipment housings or lines at high-load equipment and critical line locations. The main goal of temperature monitoring is to prevent overheating problems caused by overload or equipment failure, which may cause electrical fires or equipment damage. The installation point selection of temperature sensors focuses on the heat-generating parts of the equipment, such as transformer tanks, switch cabinet housings, and high-voltage line connection points. Temperature data is sampled at fixed time intervals and transmitted to the data processing unit through a wireless communication module. The wireless communication module supports multiple protocols (such as ZigBee, LoRa, or LTE) and can maintain stable data transmission in complex electromagnetic environments.

[0064] In the main substation, frequency acquisition devices are integrated into the system to continuously sample the system frequency in grid operation. These devices have high sampling rate and high precision, and can capture frequency deviations caused by load fluctuations or faults. For example, when a short circuit or large-scale load switching occurs, the frequency acquisition device can instantly detect the change in system frequency and pass it as an abnormal initial signal to the subsequent data processing module. In order to ensure the synchronization of the collected frequency data, the frequency acquisition device usually has a built-in high-precision clock source to support time alignment with the data of other sensors.

[0065] After being collected, all sensor data will be initially packaged by the integrated processing unit of the multi-level perception module to form data packets with standardized structures. These data packets include information such as voltage, current, temperature and frequency measurements, timestamps and device identification. The integrated processing unit also has a data integrity check function, which can perform error checking on the collected data and request retransmission when necessary to ensure the accuracy of the data. After data packaging is completed, the data is sent to the data processing module via wired or wireless communication for further analysis and diagnosis.

[0066] Through the above implementation steps, the multi-level perception module can meet the diverse needs of power grid operation status monitoring. Its efficient and reliable monitoring and data transmission functions provide a solid foundation for the operation of the real-time fault detection and automatic repair system of the entire power grid.

[0067] The data processing module 102 is used to receive the operating data provided by the multi-level perception module; analyze the operating data through an embedded intelligent algorithm to identify potential faults, and generate a fault diagnosis result when a fault is detected, wherein the fault diagnosis result includes the fault type, fault location and impact range.

[0068] The data processing module 102 is one of the core components of the real-time fault detection and automatic repair system for the power grid. Its function is to receive the operation data from the multi-level perception module 101, analyze it using the embedded intelligent algorithm, thereby identifying potential faults, and generating diagnostic results of fault type, fault location and impact range. The design of the module covers the entire process of data reception, preprocessing, analysis, diagnosis and output, and all operations are aimed at high efficiency and automation.

[0069] When receiving operating data, the data processing module is connected to the multi-level perception module through standardized communication interfaces that support multiple communication protocols, such as MODBUS, IEC 61850 or TCP / IP-based communication protocols. The module is equipped with a receiving unit that can simultaneously process data streams from multiple sensors, including parameters such as voltage, current, frequency and temperature. To ensure the integrity of the received data, the receiving unit has an error correction mechanism that can detect and repair bit errors during data transmission, and supports temporary data caching to cope with short communication interruptions.

[0070] After the operating data enters the data processing module, it will be standardized and denoised by the preprocessing unit. First, the module normalizes each data stream according to its physical unit to eliminate the analysis deviation caused by dimensional differences. For example, for voltage and current data, the preprocessing unit converts them into percentage form based on the rated parameters of the equipment. Secondly, the module uses sliding window filtering technology and threshold rejection algorithm to clean up high-frequency noise and outliers in the data to ensure the accuracy of subsequent analysis. At the same time, the preprocessing unit assigns a unified timestamp to data from different sensors through a time synchronization mechanism to ensure the correctness of time association in multidimensional data analysis.

[0071] After preprocessing, the module will extract features from the cleaned data, which is the basis for fault diagnosis. The feature extraction unit combines the characteristics of the power grid operation data and designs a multi-level feature analysis logic. For example, for current data, the module calculates the waveform change rate and the current difference between adjacent nodes. These features can effectively reflect the unbalanced condition of the power grid load; for voltage data, the module extracts the imbalance and fluctuation amplitude to identify abnormal voltage areas. In addition, the module also analyzes the dynamic change pattern of frequency data, and provides support for subsequent diagnosis by capturing changes in the main frequency offset and harmonic components.

[0072] Fault diagnosis is the core function of the data processing module. The module embeds a pre-trained intelligent algorithm based on the support vector machine (SVM) model and dynamically optimizes it in combination with real-time updated load data. The algorithm receives the extracted feature data as input and generates fault diagnosis results through classification and regression analysis. Specifically, the classification part is used to identify the type of fault, such as short circuit, overload, or equipment abnormality, while the regression analysis calculates the location of the fault based on the feature data, such as a specific line or node. To improve the accuracy of the diagnosis, the algorithm dynamically adjusts the boundaries of the classification model based on historical sample data and current load distribution to adapt to changes in the real-time operating environment.

[0073] After generating the fault diagnosis results, the data processing module will package and output the results, including key information such as fault type, fault location and impact range. The module is equipped with a standardized output unit that supports data encapsulation in multiple formats, such as JSON, XML or binary data streams. The output unit can send the diagnosis results to the automated repair module 103 through a high-speed communication interface to trigger the repair operation, and pass the results to the monitoring and logging module 104 for recording and display.

[0074] The data processing module 102 can not only efficiently process the massive data in the operation of the power grid, but also accurately identify and locate faults, providing strong technical support for the stable operation of the power grid.

[0075] Furthermore, the intelligent algorithm adopted by the data processing module is implemented using the following steps:

[0076] The operation data collected by the multi-level perception module is decomposed by wavelet transform, and low-frequency components are extracted by removing high-frequency noise; sliding window time series analysis is performed on the low-frequency components to extract characteristic data reflecting the operation status of the power grid and generate power grid characteristic data; wherein the extracted characteristic data includes the current waveform change rate, voltage imbalance and frequency offset characteristics;

[0077] The feature data is input into a pre-trained support vector machine classifier, and the classification boundary is dynamically optimized based on historical samples and real-time load data to generate a diagnosis result of the fault type; abnormal operating parameters related to the fault type are marked according to the diagnosis result, and the fault type includes short circuit, overload, line break or equipment abnormality;

[0078] According to the diagnosis results of the fault type and the marked abnormal operating parameters, the source of the voltage or current change is analyzed based on the abnormal current propagation path by tracing back the physical structure of the power grid layer by layer; based on the analysis results of the source of the voltage or current change, the specific location of the fault is determined in combination with the operating characteristics of the equipment and lines, and the fault location results including the identification of the faulty equipment or line are generated;

[0079] Based on the fault location results, combined with the connection relationship and real-time load status of the equipment in the power grid, the fault impact range is analyzed by step-by-step propagation, and the operating status changes of substations, transmission lines and load equipment and their affected areas are gradually calculated; when the impact is weakened to a pre-set negligible range, complete detailed information on the affected area is generated, including equipment identification, operating parameter change values ​​and specific impact range.

[0080] The intelligent algorithm used in the data processing module achieves comprehensive analysis of the power grid operation status, fault diagnosis and location, and accurate assessment of the fault impact range through a multi-step coordinated analysis and calculation process. The implementation of the algorithm covers multiple stages including data preprocessing, feature extraction, fault diagnosis, physical structure backtracking, and impact range analysis. The design of each stage ensures its logic and technical feasibility.

[0081] In the first stage, the algorithm receives raw operating data from the multi-level perception module, including signals such as voltage, current, frequency and temperature. These signals are usually interfered by high-frequency noise, so the algorithm first decomposes the data through wavelet transform. Wavelet transform can divide the operating data into different frequency bands, where the high-frequency components contain noise information, while the low-frequency components retain the main grid operation characteristics. By removing the high-frequency components and retaining the low-frequency components, the algorithm generates a set of time series data that reflects the dynamic characteristics of the grid. These data are then processed in segments, and each time series is analyzed using a sliding window technique to capture local changes in the operating status.

[0082] The results of the sliding window analysis are used for feature extraction, which is the basis for fault diagnosis. The feature extraction stage focuses on three core indicators: the rate of change of the current waveform, the voltage imbalance, and the frequency offset characteristics. The rate of change of the current waveform is obtained by calculating the current change amplitude at adjacent time points, which is used to identify abnormal current fluctuations; the voltage imbalance is calculated by comparing the voltage difference between different phases of the power grid, reflecting the stability of the voltage distribution; the frequency offset characteristics capture the deviation of the power grid operating frequency and its changing trend, which can effectively indicate the impact of load fluctuations or faults.

[0083] The extracted feature data is input into a pre-trained support vector machine classifier for fault diagnosis. The support vector machine is initially trained using historical sample data, including various fault types and their corresponding feature distributions, and combined with real-time load data to optimize the classification boundaries, thereby improving the accuracy and real-time performance of the diagnosis. The output of the classifier is the diagnosis result of the fault type, such as short circuit, overload, line break, or equipment abnormality. In addition, the diagnosis result will mark abnormal operating parameters related to the fault type, such as current peak or frequency abnormality at a specific time point, to provide a basis for subsequent analysis.

[0084] Based on the diagnosis results, the algorithm traces back the physical structure of the power grid layer by layer to determine the source of the voltage or current change. The process uses the grid topology information and the propagation path of the abnormal current to trace back step by step, from the affected load equipment to the transmission and distribution lines, until the starting node of the abnormal change is found. By combining operating parameters and historical data, the algorithm further analyzes the abnormal behavior of the source node, such as a sudden increase in current or a sudden drop in voltage, and finally determines the location of the faulty device or line. The result of this stage is a precise fault location report that includes the identification of the faulty device or line.

[0085] After determining the fault location, the algorithm further evaluates the overall impact of the fault on the grid operation status. Through step-by-step propagation analysis, the algorithm simulates the diffusion process of abnormal current or voltage, and dynamically calculates its impact range in combination with the operating characteristics of the equipment and lines. The result of each propagation will update the operating status changes of the relevant equipment, including increased current load, larger voltage drop, or frequency offset diffusion. When the impact of the propagation is weakened to a pre-set negligible range, the algorithm stops the propagation calculation and generates a detailed impact report. The report lists the identification of all affected equipment, the specific change values ​​of the operating parameters, and the geographical or topological distribution of the impact range.

[0086] Through the collaborative work of the above stages, the intelligent algorithm in the data processing module can realize the full process automation from preliminary analysis of operating data to fault location and impact assessment, providing technical support for the rapid repair and comprehensive assessment of power grid faults.

[0087] Furthermore, the operation data collected by the multi-level perception module is decomposed by wavelet transform, and low-frequency components are extracted by removing high-frequency noise, including:

[0088] According to the following formula (1) and formula (2), define the wavelet basis function ψ j,k (t) and φ j,k (t):

[0089]

[0090] Among them, t represents the sampling time, which is the time coordinate of the power grid operation data;

[0091] j represents the scale parameter, which controls the balance between the time resolution and frequency resolution of the wavelet basis function;

[0092] k represents the time shift parameter, which determines the position of the wavelet on the time axis.

[0093] ψ(t) and φ(t) are basis functions of the wavelet function, as shown in the following formulas (3) and (4):

[0094] ψ(t)=exp(-αt 2 )cos(2πβt) (3)

[0095] φ(t)=exp(-αt 2 ) (4)

[0096] Among them, α is the frequency offset adjustment parameter, which is used to control the time domain expansion degree of the wavelet function. Usually, a smaller value is selected according to the frequency characteristics of the power grid signal to enhance the time resolution;

[0097] β is the waveform adjustment parameter, which defines the center frequency of the wavelet function and is usually selected to be consistent with the main frequency characteristics of the power grid signal;

[0098] t represents the sampling time;

[0099] According to the following formulas (5) and (6), the running data x(t) is decomposed into multiple scales to generate the high-frequency component D j (t) and low-frequency component A j (t):

[0100]

[0101] D j (t) represents the running data x(t) and the wavelet basis function ψ j,k The convolution operation of (t) is used to capture the high-frequency changes of the signal.

[0102]

[0103] A j (t) is used to calculate the running data x(t) and the scaling function φ j,k Convolution of (t) extracts the low-frequency characteristics of the signal. Extracts the low-frequency characteristics of the signal.

[0104] According to the following formula (7), calculate the high-frequency component threshold T:

[0105]

[0106] Wherein, η is a proportional factor set based on the statistical characteristics of the power grid operation data. Usually, by statistically analyzing the historical operation data, a value that can effectively distinguish between noise and signal is selected, for example, η can be in the range of 1 to 3.

[0107] N is the number of sampling points;

[0108] D j The high-frequency component of (t)|>T is set to zero to remove noise, and the denoised high-frequency component is obtained;

[0109] By performing inverse wavelet transform on the denoised high-frequency and low-frequency components, the low-frequency components reflecting the operating status of the power grid are reconstructed and extracted as the key feature input to describe the power grid status.

[0110] Furthermore, performing sliding window time series analysis on the low-frequency component to extract characteristic data reflecting the operation status of the power grid and generate power grid characteristic data includes:

[0111] Perform wavelet decomposition on the operating data of current, voltage and frequency respectively to generate the corresponding low-frequency component Acurrent (t), A voltage (t) and A frequency (t), and use the sliding window technology to perform time series analysis on each low-frequency component, define the sliding window length W and step size S, and extract the following various features from different windows.

[0112] Here the low frequency component A current (t), A voltage (t) and A frequency (t) can be obtained by using the above formulas (1)-(7). The sliding window technology effectively captures local change characteristics by processing the signal in segments. The length W of the sliding window determines the time span of each analysis segment, which is usually set according to the characteristic period of the power grid signal. For example, when the power grid frequency is 50Hz, W can be selected in the range of 0.1 seconds to 1 second. The step size S defines the number of steps of the window sliding. A smaller step size can improve the resolution, while a larger step size can reduce the computational burden. The typical value is 10% to 20% of W.

[0113] According to the following formula (8), calculate the current waveform change rate R current :

[0114]

[0115] Where N is the number of data segments in the window, N = W / S; m i is the fitting slope of the i-th data segment in the window; m i-1 is the fitting slope of the i-1th data segment in the window; m i The following formula (9) is used for calculation:

[0116]

[0117] Among them, W i is the i-th sliding window, whose time range is [t i , t i +W], where W is the window length; t i is the starting time of the i-th sliding window; t is the sampling time point; is the mean of the time points within the window and is calculated using the following formula (10):

[0118]

[0119] Where n is the number of sampling points in the window; is the mean value of the low-frequency component in the window, calculated using the following formula (11):

[0120]

[0121] Where n is the number of sampling points in the window;

[0122] According to the following formula (12), calculate the voltage unbalance U unbalance :

[0123]

[0124] Among them, t k It represents the starting time of the kth sliding window; W is the sliding window length; S is the step size; the numerator calculates the voltage difference between adjacent sampling points, and the denominator uses the maximum and minimum values ​​of the signal to normalize the result, so as to facilitate the comparison of signals with different amplitude ranges.

[0125] According to the following formula (13), the frequency offset characteristic F is calculated offset :

[0126]

[0127] Among them, ω normal is the normal frequency of the power grid (usually 50Hz or 60Hz); inst (t) is the instantaneous frequency at time t, calculated using the following formula (14):

[0128]

[0129] Wherein, H represents the Hilbert transform symbol; arg is the phase angle calculation function;

[0130] The calculated current waveform change rate R current , voltage unbalance U unbalance And the frequency offset characteristic F offet Integrate and generate grid characteristic data.

[0131] Furthermore, the feature data is input into a pre-trained support vector machine classifier, and the classification boundary is dynamically optimized based on historical samples and real-time load data to generate a diagnosis result of the fault type, including:

[0132] receiving characteristic data of the operation status of the power grid, the characteristic data including the current waveform change rate, voltage imbalance and frequency offset characteristics; performing normalization processing on the input characteristic data to ensure that the dimensions of different characteristics are consistent;

[0133] The support vector machine classifier is trained using a historical sample data set, wherein the historical sample data set includes a fault type label and corresponding feature data; the fault type includes short circuit, overload, line break and equipment abnormality;

[0134] The decision boundary of the classifier is dynamically adjusted in combination with real-time load data. The classification model is optimized by updating the weighted distance formula between support vectors. The optimization target is the following formula (15):

[0135]

[0136] Where w is the weight vector of the classifier; ξ i is the slack variable of the i-th sample; n is the number of samples; β is the load-sensitive weight coefficient; load i is the load data of the i-th sample; load represents the load data of all samples.

[0137] The power grid real-time fault detection and automatic repair system uses a support vector machine classifier to diagnose the fault type, combines historical sample data and real-time load data, and generates accurate diagnosis results by dynamically optimizing classification boundaries.

[0138] The input of the support vector machine classifier is the characteristic data of the power grid operation status, which includes the current waveform change rate, voltage imbalance and frequency offset characteristics. Since these characteristic data have different dimensions, for example, the current waveform change rate is expressed as amplitude change, and the frequency offset characteristics are expressed in Hertz, all characteristic data need to be normalized before entering the classifier. Normalization ensures that all features have the same range by scaling the value of each feature by its maximum value or standard deviation, usually normalized to the range of [0,1] or [-1,1], thereby avoiding the impact of dimensional differences on classifier performance.

[0139] The training process of the support vector machine classifier is based on a pre-prepared historical sample data set. The historical sample data set includes multiple samples of known fault types, each of which contains corresponding feature data and labels. The label describes the fault type, such as short circuit, overload, line break, or equipment abnormality. Through these sample data, the classifier can learn the feature patterns corresponding to each type of fault. During the training process, the classifier separates different types of fault data by optimizing the classification boundaries so that unknown faults can be accurately classified at runtime.

[0140] The optimization objective of the classifier is based on the following formula:

[0141]

[0142] Where w represents the weight vector of the classifier, which determines the location and direction of the classification boundary. The classification boundary is a hyperplane in a high-dimensional space that can effectively separate the fault types. The first term of the optimization objective The complexity of the classification boundary is controlled, and a smaller weight value w can prevent the classifier from overfitting.

[0143] The slack variable ξ in the second term i is the tolerance for classification errors. For samples that are difficult to classify, ξ i The value of will be larger, thus allowing the classifier to have a certain error on these samples. The weight C determines the weight of the error term. A larger C value tends to strictly reduce the classification error, but may lead to overfitting; a smaller C value allows a larger classification error, but can improve the generalization ability of the model.

[0144] The formula also includes a load-sensitive weight adjustment Where β is a sensitivity coefficient that controls the degree of influence of real-time load on the adjustment of classification boundaries. This coefficient is usually selected through experimental data optimization, and the value range is usually between 0.1 and 1. i is the load information of a specific sample in operation, and max(load) is the maximum value of all sample loads, which is used for normalization. By introducing this item, the classifier can give higher weights to samples with larger loads, thereby dynamically adjusting the classification boundary to make it more adaptable to the load characteristics in the real-time operation environment.

[0145] In the actual optimization process, the support vector machine uses gradient descent or other optimization algorithms to minimize the above objective function. As the optimization proceeds, the classification boundaries are gradually adjusted, and ultimately the effect of maximizing the distinction between different fault types is achieved. After the optimization is completed, the classifier outputs the diagnosis results of the fault type, including the fault type label and confidence score.

[0146] Through the above design, the classifier can be dynamically adjusted in real time in combination with the operation data of the power grid, achieving accurate classification and efficient diagnosis of complex power grid fault types. According to the load characteristics of the actual power grid, the distribution of historical sample data, and the real-time operation requirements, the parameters C, β, and the normalization range can be flexibly adjusted to optimize the performance of the classifier and adapt to different application scenarios.

[0147] Furthermore, the diagnosis result of the fault type and the marked abnormal operating parameters are traced back to the physical structure of the power grid layer by layer, and the source of the voltage or current change is analyzed based on the abnormal current propagation path, including:

[0148] Based on the fault type diagnosis results and abnormal operation parameters, identify the initial node associated with the abnormal data in the physical structure of the power grid; and record the real-time operation status of the initial node and the connected upstream and downstream nodes;

[0149] The physical structure of the power grid is traced back layer by layer, and the upstream and downstream nodes or lines connected to it are checked in sequence along the abnormal current propagation path from the initial node. The propagation direction of the current or voltage anomaly is determined by comparing the voltage change difference and current imbalance characteristics of adjacent nodes.

[0150] In each layer of backtracking, historical operation data, topology and real-time load status are combined to identify the main path of abnormal propagation, and ultimately determine the initial source of the current or voltage change, and mark the initial source as a suspected fault point for subsequent analysis.

[0151] This embodiment traces back the physical structure of the power grid layer by layer, analyzes the source of voltage or current changes based on the abnormal current propagation path, combines the diagnosis results of the fault type and the marked abnormal operating parameters, and gradually determines the initial source of the abnormality, providing a key basis for fault location. The specific implementation process is described in detail below.

[0152] First, the system identifies the initial nodes in the physical structure of the power grid that are related to the abnormal data based on the fault diagnosis results and the marked abnormal operating parameters. The initial node refers to the grid node or equipment that is directly associated with the abnormal operating state in the fault type analysis, such as a specific load end, substation, or access point to the transmission and distribution line. When identifying the initial node, the system combines real-time monitoring data (such as current fluctuations, voltage anomalies) with the power grid topology structure, and locks the relevant nodes through parameter matching and logical deduction. For each initial node, the system not only records its abnormal parameter values, but also synchronously extracts the connection relationship between its upstream and downstream nodes. This information will be used as the basis for judging the abnormal propagation path in subsequent retrospective analysis.

[0153] After determining the initial node, the system starts the process of tracing back the physical structure of the power grid layer by layer. The tracing back process is based on the topological information of the power grid. Starting from the initial node, it gradually traces back to the source of the power grid along the propagation path of the abnormal current. In each layer of tracing back, the system analyzes the voltage changes and current characteristics of the upstream and downstream nodes or lines directly connected to the current node. Specifically, by comparing the voltage change difference between adjacent nodes, the system can determine the propagation direction of the voltage anomaly. At the same time, by analyzing the current imbalance characteristics of adjacent lines (such as sudden changes in current amplitude or phase deviation), it is further verified whether the current anomaly continues to the node.

[0154] During the retrospective process, the system also combines historical operation data, real-time load status and topological structure characteristics to optimize the judgment of abnormal propagation paths. Historical operation data provides the behavior patterns of nodes or lines under normal and abnormal conditions, such as load fluctuation range, line impedance characteristics, etc. Real-time load status provides a dynamic reference for the current load distribution and operating conditions, such as whether a node is overloaded or there is a power imbalance. By combining this information, the system can more accurately judge the direction and main path of abnormal propagation, avoiding misjudgment due to fluctuations in a single parameter.

[0155] Finally, the system locks the initial source of the current or voltage change based on the abnormal propagation path. The source node is the main location that causes the abnormality, which may be an abnormal point caused by equipment failure, short circuit or other physical problems. When identifying the source node, the system marks it as a suspected fault point and attaches information including its physical location (such as substation or line number), main abnormal parameter values ​​(such as current peak or voltage drop value) and related upstream and downstream nodes. This information provides key support for subsequent further analysis and repair operations.

[0156] Through the above implementation steps, this method can not only accurately trace the propagation path of current or voltage anomalies, but also accurately identify the source fault point from the complex power grid structure, providing technical guarantee for the rapid repair and reliable operation of the power grid.

[0157] Furthermore, the analysis result of the source of the voltage or current change and the determination of the specific location of the fault in combination with the operating characteristics of the equipment and the line include:

[0158] Analyze the operating parameters of the marked suspected fault point and its surrounding equipment, check the load current change rate of the equipment, the voltage drop amplitude of the line, and the timing characteristics of the current imbalance;

[0159] Combined with the operating characteristics of the equipment and lines, including the rated load capacity of the equipment, the impedance characteristics of the line and the historical failure mode, comprehensively evaluate whether the suspected fault point meets the actual fault characteristics, and screen out the most likely fault point or fault line;

[0160] The final fault point location is confirmed by matching with the power grid topology information.

[0161] Based on the analysis results of the source of voltage or current changes, and combined with the operating characteristics of equipment and lines, the specific location of the fault is determined, providing a precise method for locating power grid faults. This process gradually confirms the specific location of the fault through comprehensive analysis of the suspected fault point and its surrounding equipment, combined with the power grid operating characteristics and topology information, providing an accurate basis for subsequent repair operations.

[0162] In the first stage of fault location, the system conducts an in-depth analysis of the operating parameters of the marked suspected fault point and its surrounding equipment. These operating parameters include the load current change rate of the equipment, the voltage drop amplitude of the line, and the timing characteristics of the current imbalance. The load current change rate can reflect the stability of the equipment operation. For example, a sharp change in current in a short period of time may indicate that the equipment is affected by an abnormality. The voltage drop amplitude of the line is a key indicator of the health of the transmission line. A significant voltage drop may be caused by an increase in line impedance or a short circuit. In addition, the timing characteristics of the current imbalance can reveal whether there are problems such as asymmetric loads or phase failures in the three-phase system, which are usually accompanied by faults.

[0163] In the second stage, the system conducts a comprehensive evaluation of suspected fault points based on the operating characteristics of the equipment and lines. The operating characteristics include the rated load capacity of the equipment, the impedance characteristics of the line, and historical failure modes. For example, the rated load capacity is used to determine whether the current load of the equipment exceeds the design range, while the line impedance characteristics can help evaluate whether the voltage drop is consistent with normal operation. By introducing historical failure mode data, the system can identify whether the current situation is consistent with past known failure modes, thereby further verifying the reliability of the suspected fault point. Based on these analysis results, the system prioritizes all suspected fault points and screens out the most likely fault points or faulty lines.

[0164] Finally, the system confirms the final fault point location by matching it with the topological information of the power grid. Topological information includes the connection relationship between equipment and lines in the power grid, as well as the geographical or physical location of each node. The system uses topological information to verify whether the screened fault point conforms to the actual current or voltage propagation path, and checks whether the operating status of its upstream and downstream equipment or lines is consistent with the fault characteristics. In this way, erroneous markings caused by abnormal data or accidental fluctuations can be effectively eliminated to ensure the accuracy of the final positioning results.

[0165] The entire fault location process has technically achieved multi-level optimization from data analysis to comprehensive judgment and final confirmation. The system design ensures that the location of the fault point does not rely solely on a single parameter, but provides highly accurate fault diagnosis results through multi-dimensional data verification and logical deduction.

[0166] The automated repair module 103 is used to perform repair operations according to the fault diagnosis results generated by the data processing module, wherein the repair operations include isolating the fault area, reconstructing the grid topology, and restoring normal power supply.

[0167] The core of the automatic repair module 103 is to handle power grid faults efficiently and automatically, and its operation includes three main stages: fault area isolation, topology reconstruction and power supply restoration.

[0168] First, in the fault area isolation stage, the module uses the fault diagnosis results received from the data processing module 102 to start the isolation control operation. A dynamically updated power grid topology database is maintained inside the system to record all lines, nodes and their connection relationships. After receiving the specific fault location, the isolation control unit extracts a list of switchgear directly connected to the faulty node or line from the database, and establishes a control channel with these devices based on a real-time communication protocol (such as IEC 61850). The isolation instruction is sent to the target device in a standard format through the channel. The instruction content includes the unique identification of the switch, the execution action (such as disconnection), the trigger condition and the confirmation mechanism. To ensure the reliability of the isolation operation, the module monitors the status feedback signal of the switchgear in real time. If the confirmation signal of successful execution is not received within the set time, the module will automatically send a repeated instruction or alarm information to the backup control path.

[0169] During the topology reconstruction phase, the module relies on a built-in topology optimization engine that calculates the optimal power supply path based on a deep search algorithm and load balancing rules. First, the module extracts all node and line information in the non-fault area from the power grid topology database, and calculates the remaining transmission capacity of each line in combination with real-time load data. Secondly, the engine treats the power grid as a directed graph, in which nodes represent substations or load devices and edges represent transmission lines. Through a dynamic weighting method, edge weights are assigned with the remaining capacity of the line as the main parameter, and a depth-first search or Dijkstra algorithm is used to find the shortest or optimal path from the power source to the load. The resulting path plan is sent to the control unit in the form of instructions, which include the switchgear that needs to be connected to each line, load scheduling information, and safety verification parameters of the line.

[0170] The power restoration stage is completed by the power restoration unit, and its operation process is refined into a step-by-step power restoration mechanism. First, the module determines the priority of power restoration based on the topology optimization results, usually giving priority to restoring the lines connected to critical load equipment (such as hospitals or communication base stations). The specific implementation method of the recovery operation is to activate the lines section by section, and monitor the overall operation status of the power grid after each activation, including the voltage fluctuation range, frequency stability, and whether the current distribution exceeds the set threshold. If an abnormality is detected in any section of the recovery process, the module will immediately suspend subsequent operations and notify the monitoring module to re-evaluate the repair plan. In order to prevent a sudden increase in load from causing instability in the power grid, a load segmentation activation strategy is introduced in the power restoration process, such as gradually increasing the load at preset time intervals.

[0171] The automated repair module 103 can not only quickly isolate the fault area and dynamically reconstruct the grid topology, but also gradually restore power supply in a stable and safe manner, significantly improving the reliability and operation efficiency of the grid.

[0172] Furthermore, the automated repair module is specifically used for:

[0173] Based on the fault diagnosis result, a circuit breaker control unit is activated to isolate the identified fault area, wherein the isolation includes physically disconnecting the faulty line or equipment from the normal power supply part;

[0174] Calculate the grid topology of the non-fault area, generate a new power supply path by enabling backup power sources, backup lines or redistributing existing loads, and send instructions to related switchgear through the communication module to perform topology reconstruction;

[0175] After confirming that the topology adjustment is complete, adjust the voltage level and power supply through the transformer to gradually restore power supply to the normal load area.

[0176] The automated repair module isolates grid faults, dynamically adjusts topology, and restores power to non-faulty areas through a series of coordinated operations, ensuring that the grid can operate quickly and stably. The module initiates the corresponding repair operations based on the fault diagnosis results, and reduces manual intervention through highly automated processes, improving repair efficiency and accuracy.

[0177] When the data processing module generates the fault diagnosis results, the automatic repair module will immediately start the circuit breaker control unit to isolate the fault area. The module first parses the specific fault location and impact range in the fault diagnosis results, and matches it with the topology database of the power grid to determine the lines or equipment that need to be isolated and their associated circuit breaker numbers. The isolation operation is completed by sending instructions to the corresponding circuit breaker or switchgear through the control unit. These instructions include equipment identification, execution actions (such as disconnection), and operation confirmation mechanisms. To ensure the reliability of the operation, the module is designed with a real-time monitoring function to verify the execution of the instructions by receiving the status feedback signal of the circuit breaker. If the target device is not successfully disconnected within the specified time, the module will trigger a backup plan, such as resending the isolation instruction or reporting the abnormality to the monitoring module.

[0178] After completing the isolation of the fault area, the module will enter the grid topology adjustment stage. At this point, the topology optimization engine will take over the operation, which uses the real-time non-fault area operation data and topology information to calculate the new power supply path. The optimization engine selects the best backup power source, backup line or redistributes the existing load based on the load balancing principle and path priority rules. Specifically, the backup power source can include temporarily enabled generator sets or unused power supply lines, while load redistribution is achieved by dynamically adjusting the transformer output or switching the load connection point. The generated new path plan will be encapsulated into an instruction set and sent to the relevant switchgear through the module's built-in communication interface. These instructions include a list of devices that need to be connected or switched, load adjustment parameters, and safety check rules to ensure that the topology adjustment process is safe and reliable.

[0179] After the topology adjustment is completed, the automated repair module will start the power restoration process. The goal of this stage is to gradually restore normal power supply to non-faulty areas. Power restoration is the responsibility of the power restoration unit, and its operation is carried out in a segmented activation manner to avoid secondary problems caused by a sudden increase in load. Before each activation, the module will evaluate whether the current load capacity is sufficient to support the new power supply demand by monitoring the real-time operating status of the transformer and line. If an abnormality is detected, such as overload or voltage fluctuation exceeding the threshold, the module will suspend the recovery operation and re-evaluate the recovery strategy. During the power restoration process, the module will also dynamically adjust the voltage level and output power of the transformer to adapt to the gradually increasing load. Finally, when the power supply of all load areas is restored, the module will notify the monitoring module to record detailed data of the entire repair process.

[0180] The automated repair module is also equipped with a redundant safety mechanism that can quickly switch to a backup plan when isolation or topology adjustment fails. To achieve this, the module is designed with real-time anomaly detection and response functions. When an anomaly is detected in any link, the system will immediately suspend the current operation and send the anomaly to the monitoring module, while trying to re-plan the repair strategy or request manual intervention.

[0181] Through the above design, the automated repair module can realize full-process automated operation from fault isolation to power supply restoration. Its flexibility and reliability significantly enhance the grid's ability to resist risks.

[0182] The monitoring and logging module 104 is used to record the grid operation status, fault diagnosis results and repair operation process, generate historical data reports, and provide fault analysis and operation performance evaluation through a user interface.

[0183] The monitoring and logging module 104 is a key part of the real-time fault detection and automatic repair system of the power grid. Its main functions include recording the power grid operation status, fault diagnosis results and repair operation process, generating detailed historical data reports, and providing fault analysis and operation performance evaluation through the user interface. The module design combines the dual requirements of real-time and data analysis, and provides comprehensive support for the operation and management of the power grid through an efficient recording mechanism, flexible display methods and powerful analysis functions.

[0184] The monitoring and logging module first receives real-time data and operation results through the communication interface with the data processing module 102 and the automated repair module 103. The received data includes operating status parameters such as voltage, current, frequency, temperature, etc., the type, location, and impact range of fault diagnosis, and the steps and time nodes of the repair operation. The module assigns accurate time information to each record through the timestamp mechanism to ensure that data from different sources remain consistent in the time dimension.

[0185] The recording function is the basis of this module, and the key events in the operation of the power grid are recorded in layers through the log recording unit. The first layer is the real-time recording layer, which records all operating data and fault information in original form to ensure the integrity and traceability of the data. The second layer is the event recording layer, which is used to capture and organize important events in operation, such as the time points when the fault occurs, the start and end of the repair operation, and warnings or abnormal information related to the operation status of the power grid. The third layer is the report generation layer, which generates formatted historical data reports based on the recorded data, including operating curves, fault summaries, and repair operation logs. These reports can be exported to common formats (such as PDF or CSV) for long-term storage and further analysis.

[0186] In order to facilitate real-time monitoring and interaction for users, the module is equipped with a user interface unit to present the operation status and history of the power grid in a visual way. The user interface adopts a multi-dimensional display method, including real-time monitoring view, event list and performance evaluation dashboard. In the real-time monitoring view, parameters such as voltage, current and frequency are displayed in the form of dynamic charts, and users can intuitively view the current operation status of the power grid. All key events are listed in the event list, and users can click on the event to obtain detailed information, such as the topology map of the fault location or the execution steps of the repair operation. The performance evaluation dashboard provides a quantitative evaluation of the quality of power grid operation through indicators such as mean repair time, fault frequency and system stability score.

[0187] The monitoring and logging module also has intelligent analysis capabilities, which can perform in-depth mining based on historical data. For example, the module can identify common failure modes through cluster analysis of multiple failure data, and discover potential causes related to failures through correlation analysis. In addition, the module supports simulating past failures and repair processes through playback functions, helping users verify the system's response speed and the effectiveness of repair strategies.

[0188] The module is designed with data security and reliability in mind. All log records are stored redundantly, locally and in cloud servers, to prevent data loss. The module also uses a permission management mechanism to ensure that only authorized users can access sensitive data or perform data export operations.

[0189] The monitoring and log module 104 realizes the full process functions from data recording to advanced analysis, providing solid support for the transparent management and continuous optimization of the power grid operation status.

[0190] Furthermore, the monitoring and logging module is specifically used for:

[0191] The status acquisition unit obtains real-time operation data, including voltage, current, frequency and temperature parameters, records abnormal data when a fault occurs, and generates a snapshot of the operation status before and after the fault;

[0192] During the fault repair process, the specific steps and execution time of isolation operations, topology adjustments, and power restoration are recorded in real time;

[0193] After the repair is completed, a complete log report including grid operation status data, fault cause analysis and repair process is generated and displayed to the operator and stored through a visual interface.

[0194] The monitoring and logging module is an important part of the real-time fault detection and automatic repair system of the power grid. It is responsible for realizing comprehensive monitoring of the power grid operation status, accurate recording of fault data, and complete tracking of the repair process, providing reliable data support for subsequent operation evaluation and optimization. The module ensures the transparency of the operation status and the systematic management of information through the collaborative work of the status acquisition unit, real-time recording function, and log report generation unit.

[0195] The module obtains the operation data of the power grid in real time through the state acquisition unit, including key parameters such as voltage, current, frequency and temperature. The acquisition of these data is based on the communication interface with the multi-level perception module. The acquisition unit can receive data streams at a high frequency and attach an accurate timestamp to each data to ensure the timing consistency of the data. Under normal operating conditions, the module continues to store the collected data and monitor parameter changes in real time. If an abnormality is detected, such as a significant deviation in voltage or frequency, the module will immediately trigger the recording function of the abnormal data. The abnormal record not only includes the abnormal parameter value, but also captures the key operating status before and after the fault occurs, and generates a snapshot of the operating status. These snapshots provide the system with a preliminary inference basis for the cause of the fault by comprehensively analyzing current and historical data.

[0196] During the fault repair process, the monitoring and logging module plays a core recording function. The module tracks every step of the automated repair module in real time, including the isolation operation of the circuit breaker, topology adjustment, and specific steps for power restoration. When each operation is performed, the module records the relevant time point, the identification information of the executing device, and the operation results, such as whether the isolation circuit breaker is successfully disconnected, or whether there are load anomalies during power restoration. In addition, the module will capture the dynamic changes in the grid operating parameters during the repair process, so as to evaluate the effectiveness of the repair measures in subsequent analysis. For example, during the segmented activation process of power restoration, the module can record the current and voltage fluctuations when each line is restored, so as to determine whether the power supply strategy needs to be optimized.

[0197] After the fault is repaired, the monitoring and logging module will enter the log report generation phase. The module will organize and summarize all the data in the entire repair process to generate a complete log report. The report contains a detailed record of the grid operation status, the initial parameters of the fault and their changing trends, the complete process of the repair operation, and the final recovery results. In addition, the report also includes a detailed analysis of the cause of the fault, such as identifying possible fault sources through correlation analysis, or predicting the potential risks of similar faults through trend analysis. The log report is stored in a standardized format and supports multiple file formats such as PDF and CSV, which is convenient for long-term archiving or export for use in other systems.

[0198] In order to facilitate operators' quick decision-making and long-term management, the module is equipped with a visual interface. The interface uses an intuitive graphical display method to present operating data and repair processes in the form of curves, topology diagrams, and timelines. Operators can use the interface to view the grid status, browse key fault information, or replay the repair process in real time. In addition, the interface also supports customized performance evaluation functions, such as calculating the average repair time or the frequency of faults by analyzing log reports, helping grid managers optimize system operation strategies.

[0199] The design of the monitoring and logging module also focuses on data security and reliability. The module uses a dual redundant storage mechanism to save data synchronously to local and cloud servers to prevent data loss due to hardware failure or network interruption. The module also sets access control to ensure that only authorized users can view or export sensitive data.

[0200] Through the above design, the monitoring and logging module realizes the whole process management from data collection to fault analysis, from real-time monitoring to historical archiving, providing a solid technical guarantee for the efficient operation of the power grid.

[0201] Although the present application is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present application. Any technical personnel in this field may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.

Claims

1. A real-time fault detection and automatic repair system for a power grid, characterized in that: include: A multi-level perception module, used to collect the operation data of the power grid through multiple types of sensors, and send the collected operation data to the data processing module; wherein the operation data includes voltage, current, frequency and temperature; A data processing module, configured to receive the operation data provided by the multi-level perception module; analyze the operation data through an embedded intelligent algorithm to identify potential faults, and generate a fault diagnosis result when a fault is detected, wherein the fault diagnosis result includes the fault type, fault location, and impact range; An automated repair module, configured to perform repair operations according to the fault diagnosis results generated by the data processing module, wherein the repair operations include isolating the fault area, reconstructing the grid topology, and restoring normal power supply; The monitoring and logging module is used to record the grid operation status, fault diagnosis results and repair operation process, generate historical data reports, and provide fault analysis and operation performance evaluation through the user interface.

2. The real-time fault detection and automatic repair system for power grid according to claim 1, characterized in that: The multi-level perception module is specifically used for: Deploy voltage sensors and current sensors at substations, transmission and distribution lines, and load ends to collect voltage and current data of each node in real time. The voltage sensor is used to detect the instantaneous value of the node voltage, and the current sensor is used to monitor the amplitude and direction of the current. Install temperature sensors at high-load equipment and key line locations to regularly detect the temperature rise of the equipment casing and lines, and send temperature data to the data processing unit through the wireless communication module; A frequency acquisition device is integrated in the main substation to continuously sample changes in system frequency, capture frequency deviations caused by load fluctuations or faults, and encapsulate all collected data and transmit them to the data processing module.

3. The real-time fault detection and automatic repair system for power grid according to claim 1, characterized in that: The automatic repair module is specifically used for: Based on the fault diagnosis result, a circuit breaker control unit is activated to isolate the identified fault area, wherein the isolation includes physically disconnecting the faulty line or equipment from the normal power supply part; Calculate the grid topology of the non-fault area, generate a new power supply path by enabling backup power sources, backup lines or redistributing existing loads, and send instructions to related switchgear through the communication module to perform topology reconstruction; After confirming that the topology adjustment is complete, adjust the voltage level and power supply through the transformer to gradually restore power supply to the normal load area.

4. The real-time fault detection and automatic repair system for power grid according to claim 1, characterized in that: The monitoring and logging module is specifically used for: The status acquisition unit obtains real-time operation data, including voltage, current, frequency and temperature parameters, records abnormal data when a fault occurs, and generates a snapshot of the operation status before and after the fault; During the fault repair process, the specific steps and execution time of isolation operations, topology adjustments, and power restoration are recorded in real time; After the repair is completed, a complete log report including grid operation status data, fault cause analysis and repair process is generated and displayed to the operator and stored through a visual interface.

5. The real-time fault detection and automatic repair system for power grid according to claim 1, characterized in that: The intelligent algorithm adopted by the data processing module is implemented using the following steps: The operation data collected by the multi-level perception module is decomposed by wavelet transform, and low-frequency components are extracted by removing high-frequency noise; sliding window time series analysis is performed on the low-frequency components to extract characteristic data reflecting the operation status of the power grid and generate power grid characteristic data; wherein the extracted characteristic data includes the current waveform change rate, voltage imbalance and frequency offset characteristics; The feature data is input into a pre-trained support vector machine classifier, and the classification boundary is dynamically optimized based on historical samples and real-time load data to generate a diagnosis result of the fault type; abnormal operating parameters related to the fault type are marked according to the diagnosis result, and the fault type includes short circuit, overload, line break or equipment abnormality; According to the diagnosis results of the fault type and the marked abnormal operating parameters, the source of the voltage or current change is analyzed based on the abnormal current propagation path by tracing back the physical structure of the power grid layer by layer; based on the analysis results of the source of the voltage or current change, the specific location of the fault is determined in combination with the operating characteristics of the equipment and lines, and the fault location results including the identification of the faulty equipment or line are generated; Based on the fault location results, combined with the connection relationship and real-time load status of the equipment in the power grid, the fault impact range is analyzed by step-by-step propagation, and the operating status changes of substations, transmission lines and load equipment and their affected areas are gradually calculated; when the impact is weakened to a pre-set negligible range, complete detailed information on the affected area is generated, including equipment identification, operating parameter change values ​​and specific impact range.

6. The real-time fault detection and automatic repair system for power grid according to claim 5, characterized in that: The operation data collected by the multi-level perception module is decomposed by wavelet transform, and low-frequency components are extracted by removing high-frequency noise, including: According to the following formula (1) and formula (2), define the wavelet basis function ψ j,k (t) and φ j,k (t): Where, t represents the sampling time; j represents the scale parameter; k represents the time shift parameter; ψ(t) and φ(t) are basis functions of the wavelet function, as shown in the following formulas (3) and (4): ψ(t)=exp(-αt 2 )cos(2πβt) (3) φ(t)=exp(-αt 2 ) (4) Among them, α is the frequency offset adjustment parameter; β is the waveform adjustment parameter; t represents the sampling time; According to the following formulas (5) and (6), the running data x(t) is decomposed into multiple scales to generate the high-frequency component D j (t) and low-frequency component A j (t): According to the following formula (7), calculate the high-frequency component threshold T: Wherein, η is the proportional factor set based on the statistical characteristics of power grid operation data; N is the number of sampling points; D j The high-frequency component of (t)|>T is set to zero to remove noise, and the denoised high-frequency component is obtained; By performing inverse wavelet transform on the denoised high-frequency and low-frequency components, the low-frequency components reflecting the operating status of the power grid are reconstructed and extracted as the key feature input to describe the power grid status.

7. The real-time fault detection and automatic repair system for power grid according to claim 6, characterized in that: The step of performing a sliding window time series analysis on the low-frequency component, extracting characteristic data reflecting the operation status of the power grid, and generating power grid characteristic data includes: Perform wavelet decomposition on the operating data of current, voltage and frequency respectively to generate the corresponding low-frequency component A current (t), A voltage (t) and A frequency (t), and use the sliding window technology to perform time series analysis on each low-frequency component, define the sliding window length W and step size S, and extract the following features from different windows: According to the following formula (8), calculate the current waveform change rate R current : Where N is the number of data segments in the window, N = W / S; m i is the fitting slope of the i-th data segment in the window; m i-1 is the fitting slope of the i-1th data segment in the window; m i The following formula (9) is used for calculation: Among them, W i is the i-th sliding window, whose time range is [t i , t i +W], where W is the window length; t i is the starting time of the i-th sliding window; t is the sampling time point; is the mean of the time points within the window, calculated using the following formula (10): Where n is the number of sampling points in the window; is the mean value of the low-frequency component in the window, calculated using the following formula (11): Where n is the number of sampling points in the window; According to the following formula (12), calculate the voltage unbalance U unbalance : Among them, t k Indicates the start time of the kth sliding window; W is the sliding window length; S is the step size; According to the following formula (13), the frequency offset characteristic F is calculated offset : Among them, ω normal is the normal frequency of the power grid; ω inst (t) is the instantaneous frequency at time t, calculated using the following formula (14): Wherein, H represents the Hilbert transform symbol; arg is the phase angle calculation function; The calculated current waveform change rate R current , voltage unbalance U unbalance And the frequency offset characteristic F offet Integrate and generate grid characteristic data.

8. The real-time fault detection and automatic repair system for power grid according to claim 5, characterized in that: The feature data is input into a pre-trained support vector machine classifier, and the classification boundary is dynamically optimized based on historical samples and real-time load data to generate a diagnosis result of the fault type, including: receiving characteristic data of the operation status of the power grid, the characteristic data including the current waveform change rate, voltage imbalance and frequency offset characteristics; performing normalization processing on the input characteristic data to ensure that the dimensions of different characteristics are consistent; The support vector machine classifier is trained using a historical sample data set, wherein the historical sample data set includes a fault type label and corresponding feature data; the fault type includes short circuit, overload, line break and equipment abnormality; The decision boundary of the classifier is dynamically adjusted in combination with real-time load data. The classification model is optimized by updating the weighted distance formula between support vectors. The optimization target is the following formula (15): Where w is the weight vector of the classifier; ξ i is the slack variable of the i-th sample; n is the number of samples; β is the load-sensitive weight coefficient; load i is the load data of the i-th sample; load represents the load data of all samples.

9. The real-time fault detection and automatic repair system for power grid according to claim 5, characterized in that: The method of analyzing the source of voltage or current change based on the diagnosis result of the fault type and the marked abnormal operating parameters by tracing back the physical structure of the power grid layer by layer and taking the abnormal current propagation path as the basis includes: Based on the fault type diagnosis results and abnormal operation parameters, identify the initial node associated with the abnormal data in the physical structure of the power grid; and record the real-time operation status of the initial node and the connected upstream and downstream nodes; The physical structure of the power grid is traced back layer by layer, and the upstream and downstream nodes or lines connected to it are checked in sequence along the abnormal current propagation path from the initial node. The propagation direction of the current or voltage anomaly is determined by comparing the voltage change difference and current imbalance characteristics of adjacent nodes. In each layer of backtracking, historical operation data, topology structure and real-time load status are combined to identify the main path of abnormal propagation, and finally determine the initial source of current or voltage change, and mark the initial source as a suspected fault point.

10. The real-time fault detection and automatic repair system for power grid according to claim 9, characterized in that: The analysis result of the source of the voltage or current change and the determination of the specific location of the fault in combination with the operating characteristics of the equipment and the line include: Analyze the operating parameters of the marked suspected fault point and its surrounding equipment, check the load current change rate of the equipment, the voltage drop amplitude of the line, and the timing characteristics of the current imbalance; Combined with the operating characteristics of the equipment and lines, including the rated load capacity of the equipment, the impedance characteristics of the line and the historical failure mode, comprehensively evaluate whether the suspected fault point meets the actual fault characteristics, and screen out the most likely fault point or fault line; The final fault point location is confirmed by matching with the power grid topology information.

Images