Power grid health management system and method based on intelligent sensor

Abstract

The invention relates to the technical field of power system monitoring, and discloses a power grid health management system and method based on an intelligent sensor, and the system comprises an intelligent sensor module which is used for carrying out the multi-physical-quantity signal collection of the operation state of power grid equipment, and carrying out the standardization processing of the collected signals, so as to generate a standardized signal matrix; the data acquisition and transmission module is used for receiving the standardized signal matrix, compressing and encoding the data and then transmitting the data to the data processing module; and the data processing module is used for de-noising the compressed and coded data and fusing the multi-physical quantity signals to generate a multi-dimensional feature data matrix. An intelligent sensor module is adopted to collect physical quantity signals of voltage, current, vibration, partial discharge, temperature and humidity of power grid equipment in real time so as to standardize and unify signal formats, and the problem that the coverage range of traditional single signal collection is low is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system monitoring, and in particular to a power grid health management system and method based on intelligent sensors. Background Art

[0002] As the scale and complexity of modern power grids increase, the reliable operation of power grid equipment is of great significance to the stability and economy of the power system. However, the traditional power grid monitoring and maintenance methods mainly rely on regular inspections and simple parameter collection, which have the following significant shortcomings: Traditional monitoring methods mostly use a single physical quantity as the main monitoring indicator, ignoring the comprehensive impact of other important parameters, resulting in incomplete perception of the status of power grid equipment and failure to detect complex faults in a timely manner; The operating environment of power grid equipment is complex, and the data transmission process is susceptible to electromagnetic interference, resulting in unstable signal transmission. At the same time, with the increase in the number of monitoring points and the amount of collected data, traditional data transmission methods cannot meet the real-time monitoring needs in terms of bandwidth and efficiency; Current diagnostic technologies focus on analyzing faults that have already occurred, but have a weak ability to predict potential faults. In addition, hidden faults cannot be detected in the early stages and can easily evolve into major faults, causing equipment downtime and grid outages. Traditional operation and maintenance relies on manual analysis and judgment, the information display lacks intuitiveness, the alarm mechanism is not intelligent, and it is unable to provide effective decision-making support in a timely manner, resulting in the spread of faults and further increasing maintenance costs and risks.

[0003] Therefore, those skilled in the art provide a smart sensor-based power grid health management system and method to solve the above-mentioned problems. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a power grid health management system and method based on smart sensors to solve the problems raised in the above background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a power grid health management system and method based on smart sensors, the system comprising: An intelligent sensor module is used to collect multi-physical quantity signals of the operating status of power grid equipment and perform standardization processing on the collected signals to generate a standardized signal matrix; The data acquisition and transmission module is used to receive the standardized signal matrix, compress and encode the data, and then transmit it to the data processing module; A data processing module is used to perform denoising on the compressed and encoded data and fuse multi-physical quantity signals to generate a multi-dimensional feature data matrix; The edge computing module is used to perform preliminary anomaly detection on the multi-dimensional feature data matrix and mark abnormal signals; The health assessment and fault diagnosis module is used to assess the health status of power grid equipment based on abnormal signals and the fused multi-dimensional feature data matrix, and to diagnose potential faults of the equipment; The visualization and alarm module is used to display the health status of power grid equipment in real time through a graphical interface, to divide the alarm level according to the health status, and to generate maintenance suggestions.

[0006] Preferably, the intelligent sensor module adopts a multi-physical quantity signal model, and its algorithm formula is: , in, A collection of multi-physical quantity signals representing power grid equipment, Represents the voltage signal, Represents the current signal, Indicates vibration signal, Indicates partial discharge signal, Represents the temperature signal, Indicates humidity signal.

[0007] Preferably, the data acquisition and transmission module includes: Compressed sensing submodule, used to receive the original signal vector collected by the smart sensor module , and perform dimensionality reduction compression to generate a low-dimensional observation signal , based on the observation matrix Perform signal compression processing, the calculation formula is: , in, is the original signal vector, is the compressed low-dimensional observation signal, is the observation matrix; Anti-interference transmission submodule, used to receive the low-dimensional observation signal generated by the compressed sensing submodule , generating dynamic carrier frequency through spectrum hopping technology , to achieve reliable signal transmission and anti-interference function, the dynamic generation calculation formula of the carrier frequency is: , in, is the current carrier frequency, is the initial frequency, is the frequency step size, is the current index and step counter of the frequency hopping sequence.

[0008] Preferably, the data processing module performs denoising on the signal through a convolutional autoencoder, and the algorithm formula for the denoising is: , in, is the input signal matrix, is the low-dimensional feature extracted by the encoder, is the noise-reduced signal restored by the decoder, is the signal matrix after noise reduction.

[0009] Preferably, the health assessment and fault diagnosis module uses a graph neural network to model the associated fault propagation relationship between devices, and its model is: , in, is the feature vector of node v at the k+1th layer, is the set of neighbor nodes of node v, is the degree of nodes u and v, is the parameter matrix of the kth layer, is the activation function, is the feature vector of node u in the kth layer.

[0010] Preferably, the health assessment and fault diagnosis module predicts the equipment time series state through a long short-term memory network, and its hidden state update formula is: , in, is the hidden state at the current moment, is the hidden state at the previous moment, is the current input, , is the weight matrix, is the bias term, is the activation function.

[0011] Preferably, the health assessment and fault diagnosis module uses a health scoring model to assess the health status of the power grid equipment. The health scoring model formula is: , in, Score your health. is the signal weight, is the signal value, and are the maximum and minimum values ​​of the signal, Determine the signal dimensions to include in the health assessment calculation; The signal weight Through dynamic optimization of the forest algorithm, the calculation formula is: , in, is the signal weight, is the sensor signal set, is the historical target value corresponding to the health score, The forest regression model.

[0012] Preferably, the visualization and alarm module maps the health score H to the color gradient C to achieve real-time display of the health status, and the mapping formula is: , in, is the color gradient, Score your health. is the color mapping function.

[0013] Preferably, the visualization and alarm module sets a hierarchical alarm mechanism based on the health score H, and its alarm rules are: , in, is the alarm level, Score your health.

[0014] A power grid health management method based on smart sensors, comprising: Step 1: Use the intelligent sensor module to collect multi-physical quantity signals of the operating status of the power grid equipment, including voltage signals, current signals, vibration signals, partial discharge signals, temperature signals and humidity signals. After the collection is completed, the signals are processed by normalization and standardization algorithms to eliminate the differences in physical quantity units and magnitudes, generate a standardized signal matrix, and provide consistent input data for subsequent data processing; Step 2: Receive the standardized signal matrix, use the compressed sensing algorithm to reduce the dimension of the signal, convert the high-dimensional signal into a low-dimensional signal, and then encode the data through the anti-interference mechanism to obtain a low-dimensional compressed signal; Step 3: Receive low-dimensional compressed signals. First, remove the noise in the signal through a noise reduction algorithm. Then, use a feature fusion method to uniformly process the multi-physical quantity signals to generate a multi-dimensional feature data matrix, providing high-dimensional feature input for equipment health assessment and fault diagnosis. Step 4: Receive the multi-dimensional feature data matrix, use the anomaly detection algorithm to perform preliminary analysis on the data, identify abnormal signals and mark them; Step 5: Based on the multi-dimensional feature data matrix and the marked abnormal signals, a comprehensive assessment is made on the health status of the power grid equipment to determine the current operating status of the equipment. The potential failures of the equipment are analyzed by combining historical data and abnormal signals. In addition, the fault diagnosis algorithm is used to predict the future risks of the equipment to provide a basis for equipment operation and maintenance. Step 6: Receive the health score and fault diagnosis results, and display the operating status of the power grid equipment in real time through a graphical interface. The health status of the equipment is intuitively presented through a color gradient, so that the alarm level is divided according to the health score and specific maintenance suggestions are generated.

[0015] The present invention provides a power grid health management system and method based on intelligent sensors, which has the following beneficial effects: 1. The present invention adopts intelligent sensor modules to collect physical quantity signals of voltage, current, vibration, partial discharge, temperature and humidity of power grid equipment in real time, so as to standardize and process the signal format, solve the problem of low coverage of traditional single signal collection, and provide comprehensive and reliable data input for subsequent health management.

[0016] 2. The present invention utilizes a compressed sensing algorithm to perform dimensionality reduction processing on multi-dimensional signals, thereby reducing the data transmission bandwidth requirement. At the same time, it utilizes spectrum hopping technology to dynamically adjust the carrier frequency, enhance the signal's anti-interference capability, effectively ensure the data transmission quality in complex electromagnetic environments, and provide a stable data link for power grid status monitoring.

[0017] 3. The present invention combines the health scoring algorithm to quantitatively evaluate the operating status of the equipment, and uses the time series prediction model and anomaly detection technology to identify the potential failure risks of the equipment, solving the problem of low prediction of hidden faults in traditional diagnostic methods, and providing a decision-making basis for the scientific operation and maintenance of power grid equipment.

[0018] 4. The present invention maps the health score into a visual color gradient and alarm classification to display the health status of the equipment in real time, generate maintenance suggestions, improve the efficiency and response speed of operation and maintenance work, avoid the spread of faults caused by delayed processing, and provide a convenient operation and maintenance platform for intelligent power grid management. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a system framework diagram of the present invention; Figure 2 It is a schematic diagram of the data acquisition and transmission module of the present invention; Figure 3 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0020] In order to make the technical personnel in the technical field understand the scheme of the present invention, the technical scheme in the embodiment of the present invention will be clearly and completely described below in combination with the drawings in the embodiment of the present invention. Obviously, the described embodiment is a partial embodiment of the present invention, not a complete embodiment. Based on the embodiment of the present invention, other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present invention.

[0021] The present invention is described in detail below in conjunction with the accompanying drawings: Example: Please refer to the attached Figure 1 ~Attached Figure 3 The embodiment of the present invention provides a power grid health management system based on smart sensors, the system comprising: An intelligent sensor module is used to collect multi-physical quantity signals of the operating status of power grid equipment and perform standardization processing on the collected signals to generate a standardized signal matrix; The data acquisition and transmission module is used to receive the standardized signal matrix, compress and encode the data, and then transmit it to the data processing module; A data processing module is used to perform denoising on the compressed and encoded data and fuse multi-physical quantity signals to generate a multi-dimensional feature data matrix; The edge computing module is used to perform preliminary anomaly detection on the multi-dimensional feature data matrix and mark abnormal signals; The health assessment and fault diagnosis module is used to assess the health status of power grid equipment based on abnormal signals and the fused multi-dimensional feature data matrix, and to diagnose potential faults of the equipment; The visualization and alarm module is used to display the health status of power grid equipment in real time through a graphical interface, to divide the alarm level according to the health status, and to generate maintenance suggestions.

[0022] The intelligent sensor module collects multiple physical quantity signals of the operating status of power grid equipment, including electrical signals, mechanical signals, environmental signals and partial discharge information. Through standardized processing, the intelligent sensor module converts multiple signals into a standardized signal matrix in a unified format, providing high-quality and multi-dimensional basic data for subsequent data processing and health assessment, and ensuring the comprehensiveness of monitoring and consistency of basic data; The data acquisition and transmission module uses compressed sensing technology to reduce the dimension of the standardized signal matrix, significantly reducing the amount of transmitted data and optimizing bandwidth utilization. At the same time, combined with the anti-interference transmission mechanism, it effectively improves the transmission reliability of signals in complex electromagnetic environments, ensures data integrity and transmission stability, and provides efficient real-time data flow for the power grid system. The data processing module performs denoising on the compressed and encoded data, using advanced algorithms to significantly reduce noise interference in the signal and improve data quality. At the same time, it integrates multi-physical quantity signals into a multi-dimensional feature data matrix through feature fusion technology, providing high-precision and high-reliability input data for subsequent health assessment and fault diagnosis; The edge computing module quickly performs preliminary anomaly detection and marks abnormal signals through real-time analysis of multi-dimensional feature data matrices, shortening the time from anomaly occurrence to identification, reducing data transmission delays, and at the same time, alleviating the burden of cloud computing, providing key support for the system to achieve rapid response and real-time warning; The health assessment and fault diagnosis module quantifies the health status of the equipment and generates a health score based on abnormal signals and fused multi-dimensional feature data matrices. At the same time, it combines historical data and machine learning models to predict potential faults, accurately identifying hidden problems and high-risk equipment, providing a scientific decision-making basis for power grid operation and maintenance, and avoiding operation interruptions and economic losses caused by sudden equipment failures. The visualization and alarm module displays the health status of power grid equipment in real time through a graphical interface. Combined with color gradients and alarm levels, it enables operation and maintenance personnel to intuitively understand the operating status of the equipment, provide real-time monitoring of the health status, generate specific maintenance suggestions based on the health score, optimize operation and maintenance efficiency, and at the same time, improve the pertinence and timeliness of equipment maintenance.

[0023] The intelligent sensor module adopts a multi-physical quantity signal model algorithm, and its algorithm formula is: , in, Represents a collection of multi-physical quantity signals of network devices. Represents the voltage signal, Represents the current signal, Indicates vibration signal, Indicates partial discharge signal, Represents the temperature signal, Indicates humidity signal.

[0024] The intelligent sensor module adopts a multi-physical quantity signal model, which integrates multiple key parameters of power grid equipment in a unified and collective form to comprehensively reflect the operating status of the equipment. The advantage of the model is that it can monitor electrical, mechanical and environmental parameters at the same time, provide multi-dimensional real-time data of the equipment, effectively improve the monitoring range and depth of the power grid operation status, and provide accurate and diverse basic data support for subsequent health assessment and fault diagnosis.

[0025] The data acquisition and transmission module includes: Compressed sensing submodule, used to receive the original signal vector collected by the smart sensor module , and perform dimensionality reduction compression to generate a low-dimensional observation signal , based on the observation matrix Perform signal compression processing, the calculation formula is: , in, is the original signal vector, is the compressed low-dimensional observation signal, is the observation matrix; Anti-interference transmission submodule, used to receive the low-dimensional observation signal generated by the compressed sensing submodule , generating dynamic carrier frequency through spectrum hopping technology , to achieve reliable signal transmission and anti-interference function, the dynamic generation calculation formula of the carrier frequency is: , in, is the current carrier frequency, is the initial frequency, is the frequency step size, is the current index and step counter of the frequency hopping sequence.

[0026] The data acquisition and transmission module improves the efficiency and reliability of data transmission by combining the compressed sensing submodule and the anti-interference transmission submodule. The compressed sensing submodule uses the observation matrix to reduce the dimension of the original signal vector and converts high-dimensional data into low-dimensional observation signals, which significantly reduces the data transmission bandwidth requirements and storage resource consumption. The anti-interference transmission submodule dynamically generates carrier frequency through spectrum hopping technology, enhances the signal's anti-interference ability in complex electromagnetic environments, ensures the stability and integrity of data transmission, effectively solves the inefficiency and signal interference problems encountered by the power grid monitoring system in large-scale real-time data transmission, and provides a reliable data transmission channel for the health management system.

[0027] The data processing module denoises the signal through the convolutional autoencoder algorithm. The convolutional autoencoder algorithm formula for denoising is: , in, is the input signal matrix, is the low-dimensional feature extracted by the encoder, is the noise-reduced signal restored by the decoder, is the signal matrix after noise reduction.

[0028] The data processing module denoises the signal through a convolutional autoencoder algorithm. The algorithm uses an encoder to extract low-dimensional features of the input signal matrix, and reconstructs the denoised signal through a decoder, ultimately generating a denoised signal matrix. The advantage is that it can effectively eliminate noise interference in the signal, especially electromagnetic noise and signal distortion commonly found in complex power grid environments, while retaining key feature information, significantly improving data quality and reliability, and providing data support for subsequent multi-dimensional feature fusion and health assessment, thereby improving the analysis accuracy and stability of the power grid health management system.

[0029] The health assessment and fault diagnosis module uses graph neural network to model the associated fault propagation relationship between devices. The model is: , in, is the feature vector of node v at the k+1th layer, is the set of neighbor nodes of node v, is the degree of nodes u and v, is the parameter matrix of the kth layer, is the activation function, is the feature vector of node u in layer k; The health assessment and fault diagnosis module predicts the equipment time series state through the long short-term memory network, and its hidden state update formula is: , in, is the hidden state at the current moment, is the hidden state at the previous moment, is the current input, , is the weight matrix, is the bias term, is the activation function; The health assessment and fault diagnosis module uses a health scoring model to assess the health status of power grid equipment. The health scoring model formula is: , in, Score your health. is the signal weight, is the signal value, and are the maximum and minimum values ​​of the signal, Determine the signal dimensions to include in the health assessment calculation; Signal weight Through dynamic optimization of the forest algorithm, the calculation formula is: , in, is the signal weight, is the sensor signal set, is the historical target value corresponding to the health score, The forest regression model.

[0030] The health assessment and fault diagnosis module provides accurate assessment of the operating status of power grid equipment and effective prediction of potential faults through the joint application of algorithms. This module uses graph neural network modeling to model the associated fault propagation relationship between devices, which can capture the complex interactions and fault propagation paths between devices, and analyze the health status of the power grid system as a whole. At the same time, the long and short-term memory network is used to predict the time series status of equipment, which can accurately identify hidden fault trends and provide forward-looking guidance for operation and maintenance work. In addition, this module quantitatively evaluates the equipment status through the health scoring model, and dynamically optimizes the signal weights with the forest algorithm to ensure that the contribution of each signal to the health status is reasonably distributed, effectively solving the limitations of traditional single-dimensional diagnosis, providing health assessment and fault diagnosis capabilities, significantly reducing the risk of equipment failure, and improving the safety and maintenance efficiency of the power grid system.

[0031] The visualization and alarm module maps the health score H to the color gradient C to achieve real-time display of the health status. The mapping formula is: , in, is the color gradient, Score your health. is the color mapping function; The visualization and alarm module sets a hierarchical alarm mechanism based on the health score H, and its alarm rules are as follows: , in, is the alarm level, Score your health.

[0032] The visualization and alarm module intuitively displays the health status of power grid equipment by mapping health scores to color gradients, allowing operation and maintenance personnel to quickly understand the equipment operating status. Through the color mapping function, the health status of the equipment is graded from healthy to warning to fault, improving the intuitiveness and operability of information expression. In addition, the hierarchical alarm mechanism based on health scores can achieve a step-by-step progression from prompt warnings to emergency alarms by setting different alarm rules, ensuring that operation and maintenance personnel can take appropriate measures in a timely manner to prevent potential problems from worsening. Overall, this module greatly improves the visualization expression of equipment status information and the efficiency of early warning response, providing powerful auxiliary decision support for power grid health management.

[0033] A power grid health management method based on smart sensors, comprising: Step 1: Use the intelligent sensor module to collect multi-physical quantity signals of the operating status of the power grid equipment, including voltage signals, current signals, vibration signals, partial discharge signals, temperature signals and humidity signals. After the collection is completed, the signals are processed by normalization and standardization algorithms to eliminate the differences in physical quantity units and magnitudes, generate a standardized signal matrix, and provide consistent input data for subsequent data processing; Step 2: Receive the standardized signal matrix, use the compressed sensing algorithm to reduce the dimension of the signal, convert the high-dimensional signal into a low-dimensional signal, and then encode the data through the anti-interference mechanism to obtain a low-dimensional compressed signal; Step 3: Receive low-dimensional compressed signals. First, remove the noise in the signal through a noise reduction algorithm. Then, use a feature fusion method to uniformly process the multi-physical quantity signals to generate a multi-dimensional feature data matrix, providing high-dimensional feature input for equipment health assessment and fault diagnosis. Step 4: Receive the multi-dimensional feature data matrix, use the anomaly detection algorithm to perform preliminary analysis on the data, identify abnormal signals and mark them; Step 5: Based on the multi-dimensional feature data matrix and the marked abnormal signals, a comprehensive assessment is made on the health status of the power grid equipment to determine the current operating status of the equipment. The potential failures of the equipment are analyzed by combining historical data and abnormal signals. In addition, the fault diagnosis algorithm is used to predict the future risks of the equipment to provide a basis for equipment operation and maintenance. Step 6: Receive the health score and fault diagnosis results, and display the operating status of the power grid equipment in real time through a graphical interface. The health status of the equipment is intuitively presented through a color gradient, so that the alarm level is divided according to the health score and specific maintenance suggestions are generated.

[0034] The method of the present invention realizes the intelligent and efficient health management of the power grid through the whole process design from signal acquisition, data processing to health assessment and visual display. Its advantages are that it comprehensively covers the operating status of equipment, significantly improves data quality, enhances signal transmission reliability, and reduces operation and maintenance costs through accurate assessment and fault prediction, ensuring the safety and stability of the power grid, and providing innovative solutions for the management of smart grids.

[0035] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A power grid health management system based on smart sensors, characterized in that: include: An intelligent sensor module is used to collect multi-physical quantity signals of the operating status of power grid equipment and perform standardization processing on the collected signals to generate a standardized signal matrix; The data acquisition and transmission module is used to receive the standardized signal matrix, compress and encode the data, and then transmit it to the data processing module; A data processing module is used to perform denoising on the compressed and encoded data and fuse multi-physical quantity signals to generate a multi-dimensional feature data matrix; The edge computing module is used to perform preliminary anomaly detection on the multi-dimensional feature data matrix and mark abnormal signals; The health assessment and fault diagnosis module is used to assess the health status of power grid equipment based on abnormal signals and the fused multi-dimensional feature data matrix, and to diagnose potential faults of the equipment; The visualization and alarm module is used to display the health status of power grid equipment in real time through a graphical interface, to divide the alarm level according to the health status, and to generate maintenance suggestions.

2. The smart sensor-based power grid health management system according to claim 1, characterized in that: The intelligent sensor module adopts a multi-physical quantity signal model, and its algorithm formula is: ， in, A collection of multi-physical quantity signals representing power grid equipment, Represents the voltage signal, Represents the current signal, Indicates vibration signal, Indicates partial discharge signal, Represents the temperature signal, Indicates humidity signal.

3. The smart sensor-based power grid health management system according to claim 1, characterized in that: The data acquisition and transmission module includes: Compressed sensing submodule, used to receive the original signal vector collected by the smart sensor module , and perform dimensionality reduction compression to generate a low-dimensional observation signal , based on the observation matrix Perform signal compression processing, the calculation formula is: ， in, is the original signal vector, is the compressed low-dimensional observation signal, is the observation matrix; Anti-interference transmission submodule, used to receive the low-dimensional observation signal generated by the compressed sensing submodule , generating dynamic carrier frequency through spectrum hopping technology , to achieve reliable signal transmission and anti-interference function, the dynamic generation calculation formula of the carrier frequency is: ， in, is the current carrier frequency, is the initial frequency, is the frequency step size, is the current index and step counter of the frequency hopping sequence.

4. The smart sensor-based power grid health management system according to claim 1, characterized in that: The data processing module performs denoising on the signal through a convolutional autoencoder, and the algorithm formula for denoising is: ， in, is the input signal matrix, is the low-dimensional feature extracted by the encoder, is the noise reduction signal restored by the decoder, is the signal matrix after noise reduction.

5. The smart sensor-based power grid health management system according to claim 1, characterized in that: The health assessment and fault diagnosis module uses a graph neural network to model the associated fault propagation relationship between devices, and its model is: , in, is the feature vector of node v at the k+1th layer, is the set of neighbor nodes of node v, is the degree of nodes u and v, is the parameter matrix of the kth layer, is the activation function, is the feature vector of node u in the kth layer.

6. The smart sensor-based power grid health management system according to claim 1, characterized in that: The health assessment and fault diagnosis module predicts the equipment time series state through the long short-term memory network, and its hidden state update formula is: ， in, is the hidden state at the current moment, is the hidden state at the previous moment, is the current input, , is the weight matrix, is the bias term, is the activation function.

7. The smart sensor-based power grid health management system according to claim 1, characterized in that: The health assessment and fault diagnosis module uses a health scoring model to assess the health status of power grid equipment. The health scoring model formula is: ， in, Score your health. is the signal weight, is the signal value, and are the maximum and minimum values ​​of the signal, Determine the signal dimensions to include in the health assessment calculation; The signal weight Through dynamic optimization of the forest algorithm, the calculation formula is: ， in, is the signal weight, is the sensor signal set, is the historical target value corresponding to the health score, The forest regression model.

8. The smart sensor-based power grid health management system according to claim 1, characterized in that: The visualization and alarm module maps the health score H to the color gradient C to achieve real-time display of the health status. The mapping formula is: , in, is the color gradient, Score your health. is the color mapping function.

9. The smart sensor-based power grid health management system according to claim 1, characterized in that: The visualization and alarm module sets a hierarchical alarm mechanism based on the health score H, and its alarm rules are: , in, is the alarm level, Score your health.

10. A method for managing power grid health based on smart sensors, based on a power grid health management system based on smart sensors according to any one of claims 1 to 9, characterized in that: include: Step 1: Use the intelligent sensor module to collect multi-physical quantity signals of the operating status of the power grid equipment, including voltage signals, current signals, vibration signals, partial discharge signals, temperature signals and humidity signals. After the collection is completed, the signals are processed by normalization and standardization algorithms to eliminate the differences in physical quantity units and magnitudes, generate a standardized signal matrix, and provide consistent input data for subsequent data processing; Step 2: Receive the standardized signal matrix, use the compressed sensing algorithm to reduce the dimension of the signal, convert the high-dimensional signal into a low-dimensional signal, and then encode the data through the anti-interference mechanism to obtain a low-dimensional compressed signal; Step 3: Receive low-dimensional compressed signals. First, remove the noise in the signal through a noise reduction algorithm. Then, use a feature fusion method to uniformly process the multi-physical quantity signals to generate a multi-dimensional feature data matrix, providing high-dimensional feature input for equipment health assessment and fault diagnosis. Step 4: Receive the multi-dimensional feature data matrix, use the anomaly detection algorithm to perform preliminary analysis on the data, identify abnormal signals and mark them; Step 5: Based on the multi-dimensional feature data matrix and the marked abnormal signals, a comprehensive assessment is made on the health status of the power grid equipment to determine the current operating status of the equipment. The potential failures of the equipment are analyzed by combining historical data and abnormal signals. In addition, the fault diagnosis algorithm is used to predict the future risks of the equipment to provide a basis for equipment operation and maintenance. Step 6: Receive the health score and fault diagnosis results, and display the operating status of the power grid equipment in real time through a graphical interface. The health status of the equipment is intuitively presented through a color gradient, so that the alarm level is divided according to the health score and specific maintenance suggestions are generated.

Images