Ring main unit state online monitoring and intelligent operation and maintenance system based on big data

Abstract

The invention discloses a ring main unit state online monitoring and intelligent operation and maintenance system based on big data, and relates to the technical field of data monitoring, and the system comprises a ring main unit state data collection module which collects operation parameters in real time based on a sensor array disposed in a ring main unit, and generates a standardized feature vector; the equipment health monitoring module is used for performing state recognition and life prediction on the standardized feature vector based on a deep learning model, and generating an equipment health degree index; the intelligent operation and maintenance decision-making module is used for establishing an intelligent operation and maintenance decision-making model based on the health degree index and a preset operation and maintenance strategy library, and generating a maintenance work order based on the output of the intelligent operation and maintenance decision-making model; and the communication module transmits the monitoring data and receives the control instruction. According to the invention, fault early warning, state identification, life estimation and health degree index generation are carried out by combining the sensor array and edge calculation with deep learning, the operation and maintenance strategy is optimized, and the cost and downtime are reduced.

Description

Technical Field

[0001] This invention relates to the field of data monitoring technology, specifically to a big data-based online monitoring and intelligent operation and maintenance system for ring main units. Background Technology

[0002] With the rapid development of smart grids and big data technologies, ring main units (RNBs), as an important component of the power system, play a crucial role in ensuring the stability and reliability of the power system through monitoring and maintenance. Traditional RNB maintenance relies on manual inspections and periodic testing, which suffers from problems such as untimely data acquisition, limited inspection coverage, and poor equipment fault early warning capabilities. This often makes it difficult to detect potential faults in a timely manner, leading to increased equipment damage and downtime, and affecting the stable operation of the power system. In recent years, equipment health monitoring and intelligent operation and maintenance based on big data and artificial intelligence technologies have gradually become key technologies for power system operation and maintenance. By deploying sensor arrays to collect real-time operating parameters of the equipment and combining them with big data analysis and deep learning technologies, the status of RNBs can be monitored online, potential faults can be detected in a timely manner, and the remaining lifespan of the equipment can be predicted, thereby improving equipment operation and maintenance efficiency, reducing fault occurrence, and extending equipment lifespan.

[0003] However, existing monitoring systems are often limited to simple data collection and status assessment, lacking comprehensive management of the equipment lifecycle and refined operation and maintenance decision support. Therefore, there is an urgent need for a more intelligent and comprehensive ring main unit status monitoring and operation and maintenance system to achieve accurate monitoring of equipment health status, fault prediction, and intelligent operation and maintenance decision support. Summary of the Invention

[0004] To address the aforementioned technical issues, this technical solution provides an online monitoring and intelligent operation and maintenance system for ring main units based on big data, thus resolving the problems described above.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: The big data-based online monitoring and intelligent operation and maintenance system for ring main units includes: The ring main unit status data acquisition module is used to collect operating parameters in real time based on the sensor array deployed in the ring main unit, perform edge computing on the real-time data, generate standardized feature vectors, and transmit the generated standardized feature vectors to the equipment health monitoring module. The equipment health monitoring module is used to pre-store the knowledge base and historical fault database of ring main unit equipment, and to perform status identification and life prediction on standardized feature vectors based on a deep learning model to generate an equipment health index. The intelligent operation and maintenance decision module is used to establish an intelligent operation and maintenance decision model based on the health index and the preset operation and maintenance strategy library. Based on the output of the intelligent operation and maintenance decision model, a maintenance work order is generated. The work order includes fault location, maintenance suggestions and spare parts information. The communication module is used to transmit monitoring data and receive control commands, and uses the SM4 encryption algorithm to ensure data security.

[0006] Preferably, the ring main unit status data acquisition module specifically includes: Real-time data acquisition unit: Based on current sensors, voltage sensors, temperature and humidity sensors, vibration sensors and status indicator sensors, it collects real-time operating data in the ring main unit, including current, voltage, temperature and humidity and vibration parameters, and synchronizes the collected real-time data in time. Data preprocessing unit: Uses Kalman filtering algorithm to filter noise from the acquired signal and performs linear normalization on parameter data from different sources and with different dimensions; Feature extraction unit: Extracts time-domain features, frequency-domain features, and spatial features from the preprocessed data, standardizes the extracted features to obtain standardized feature vectors, and transmits the standardized feature vectors to the equipment health monitoring module through the communication module for further status identification and lifespan prediction.

[0007] Preferably, the device health monitoring module specifically includes: Status recognition unit: Based on a trained convolutional neural network deep learning model, it classifies feature vectors, identifies the current working status of the ring main unit equipment, including normal, fault, and impending fault, and outputs the health status label of the equipment; Life Prediction Unit: Combining historical operating data and equipment status information, the least squares method is used to solve for the weight parameters of the standardized eigenvector. The weight parameters of the standardized eigenvector are used as input, and the remaining life prediction data is used as output to establish a life prediction model. The remaining life of the equipment is estimated based on regression analysis. Health Index Generation Unit: Based on equipment status identification results and lifespan prediction data, a weighted average method is used to comprehensively calculate the equipment's health index; Anomaly detection and alarm unit: Based on the comparison between the health index and the threshold, it determines whether there are potential anomalies. If the health index is lower than the set threshold, the system will trigger an alarm mechanism to notify the operation and maintenance personnel to carry out maintenance.

[0008] Preferably, the lifetime prediction unit includes: The least squares method is used to minimize the sum of squared errors between the predicted and actual results. A cost function is constructed that measures the sum of squared errors of all sample points. The cost function is minimized by adjusting the weights. The partial derivatives of the cost function are calculated. By setting the partial derivative of the cost function with respect to each weight to zero and solving these equations, the optimal parameters can be obtained. Based on the derived weight values ​​and standardized eigenvectors, a life prediction model is established using regression analysis formulas to estimate the remaining lifespan of the equipment.

[0009] Preferably, the step of comprehensively calculating the health index of the equipment using a weighted average method based on the equipment status identification results and lifespan prediction data specifically includes: The health status label corresponding to the current working state of the equipment is used as one of the weighting factors, and the predicted value of the remaining service life of the equipment is used as the second weighting factor. The weighting factors are comprehensively weighted according to the set weights to obtain the health index of the equipment. The threshold of the health index is set to identify whether the equipment has potential failure risks.

[0010] Preferably, the threshold for setting the health index specifically includes: Collect historical health index data of the equipment, record the health status of the equipment, perform statistical analysis on the health index, obtain the mean and standard deviation of the health index, select a 95% confidence level, and thus determine the threshold.

[0011] Preferably, the intelligent operation and maintenance decision module specifically includes: Operation and maintenance strategy generation unit: Based on the health index of the equipment and historical maintenance data, combined with different equipment types and failure modes, it generates targeted operation and maintenance strategies; Optimization Decision Unit: By adjusting and optimizing the operation and maintenance strategy based on optimization algorithms, the most suitable operation and maintenance solution for the current equipment status is selected; Maintenance personnel task allocation unit: allocates maintenance tasks based on the type of fault, equipment location, and the technical capabilities of the maintenance personnel; Maintenance report generation unit: Generates a detailed report for each maintenance work order, which includes the maintenance process, maintenance results, changes in equipment status, and recommended follow-up maintenance measures.

[0012] Preferably, the step of adjusting and optimizing the operation and maintenance strategy based on the optimization algorithm to select the most suitable operation and maintenance solution for the current equipment state specifically includes: Collect equipment health index, failure mode, historical maintenance data and failure probability data, select operation and maintenance strategies based on equipment status, and generate initial solutions; The objective function is constructed based on the equipment's health index, fault type, and maintenance cost factors, with the aim of minimizing operation and maintenance costs and minimizing downtime. The objective function is solved, and the operation and maintenance strategy is optimized based on the genetic algorithm. In each iteration, the weights are adjusted according to the search mechanism of the algorithm to minimize the objective function. The most suitable operation and maintenance plan is output based on the optimization results.

[0013] Preferably, the allocation of maintenance tasks based on the fault type, equipment location, and the technical capabilities of the maintenance personnel specifically includes: Maintenance task priority determination unit: Based on the equipment's health index, fault type, and impact range, assess the urgency of the fault, calculate the priority of each maintenance task, and schedule maintenance tasks based on their priorities.

[0014] Preferably, the communication module specifically includes: Command receiving and response unit: Receives control commands from the intelligent operation and maintenance decision module, including operation commands and maintenance work order commands, parses the received commands, and forwards them to the corresponding equipment for execution; Data encryption and decryption unit: Uses the SM4 encryption algorithm to encrypt the acquired real-time data and decrypt the received data or instructions to restore the original data and control instructions.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention proposes to collect data in real time using a sensor array and perform edge computing, combined with a deep learning model for fault warning and status identification. The system estimates the remaining lifespan of the equipment, generates a health index, assists in intelligent operation and maintenance decision-making, and automatically generates maintenance work orders. By optimizing operation and maintenance strategies, it reduces operation and maintenance costs and downtime, thereby improving the system's economic efficiency. At the same time, the SM4 encryption algorithm ensures data transmission security, and the system dynamically adjusts task priorities based on equipment health and maintenance personnel capabilities to improve maintenance efficiency. Attached Figure Description

[0016] Figure 1 This is a system framework diagram of the present invention; Figure 2 This is a flowchart illustrating the steps of the present invention. Detailed Implementation

[0017] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0018] Reference Figure 1 As shown, the big data-based online monitoring and intelligent operation and maintenance system for ring main units includes: The ring main unit status data acquisition module is used to collect operating parameters in real time based on the sensor array deployed in the ring main unit, perform edge computing on the real-time data, generate standardized feature vectors, and transmit the generated standardized feature vectors to the equipment health monitoring module. The equipment health monitoring module is used to pre-store the knowledge base and historical fault database of ring main unit equipment, and to perform status identification and life prediction on standardized feature vectors based on a deep learning model to generate an equipment health index. The intelligent operation and maintenance decision module is used to establish an intelligent operation and maintenance decision model based on the health index and the preset operation and maintenance strategy library. Based on the output of the intelligent operation and maintenance decision model, it generates maintenance work orders, which include fault location, maintenance suggestions and spare parts information. The communication module is used to transmit monitoring data and receive control commands, and uses the SM4 encryption algorithm to ensure data security.

[0019] The ring main unit status data acquisition module specifically includes: Real-time data acquisition unit: Based on current sensors, voltage sensors, temperature and humidity sensors, vibration sensors and status indicator sensors, it collects real-time operating data in the ring main unit, including current, voltage, temperature and humidity and vibration parameters, and synchronizes the collected real-time data in time. Data preprocessing unit: Uses Kalman filtering algorithm to filter noise from the acquired signal and performs linear normalization on parameter data from different sources and with different dimensions; Feature extraction unit: Extracts time-domain features, frequency-domain features and spatial features from preprocessed data, standardizes the extracted features to obtain standardized feature vectors, and transmits the standardized feature vectors to the equipment health monitoring module through the communication module for further status identification and life prediction. By introducing a sensor array for multi-dimensional data acquisition, comprehensive monitoring of equipment operation status is achieved, including real-time monitoring of parameters such as current, voltage, temperature, humidity, and vibration. This ensures the accuracy and comprehensiveness of equipment status data. Edge computing technology is used to process real-time data, reducing data transmission latency and improving real-time performance and response speed. At the same time, generating standardized feature vectors simplifies subsequent deep learning processing.

[0020] The equipment health monitoring module specifically includes: Status recognition unit: Based on a trained convolutional neural network deep learning model, it classifies feature vectors, identifies the current working status of the ring main unit equipment, including normal, fault, and impending fault, and outputs the health status label of the equipment; Life Prediction Unit: Combining historical operating data and equipment status information, the least squares method is used to solve for the weight parameters of the standardized eigenvector. The weight parameters of the standardized eigenvector are used as input, and the remaining life prediction data is used as output to establish a life prediction model. The remaining life of the equipment is estimated based on regression analysis. Health Index Generation Unit: Based on equipment status identification results and lifespan prediction data, a weighted average method is used to comprehensively calculate the equipment's health index; Anomaly detection and alarm unit: Based on the comparison between the health index and the threshold, it determines whether there are potential anomalies. If the health index is lower than the set threshold, the system will trigger an alarm mechanism to notify the operation and maintenance personnel to carry out maintenance. By combining deep learning models for status recognition, the system can not only identify the current health status of equipment but also predict its remaining lifespan. Through intelligent classification of equipment status tags, the system can accurately provide health assessments, construct lifespan prediction models using the least squares method, and estimate the remaining lifespan of equipment through regression analysis. This avoids traditional, simple experience-based prediction methods and provides more accurate prediction results.

[0021] The lifetime prediction unit includes: The least squares method is used to minimize the sum of squared errors between the predicted and actual results. A cost function is constructed that measures the sum of squared errors of all sample points. The cost function is minimized by adjusting the weights. The partial derivatives of the cost function are calculated. By setting the partial derivative of the cost function with respect to each weight to zero and solving these equations, the weight values ​​are obtained. as well as The optimal parameters; Based on the obtained weight values ​​and standardized eigenvectors, a life prediction model is established using regression analysis formulas to estimate the remaining lifespan of the equipment. The regression analysis formula is as follows:

[0022] This is the predicted remaining service life of the equipment. These are the weights of the regression model. This is the temperature feature vector. For current characteristic vectors, For the nth eigenvector, For the error term, The weights of the temperature feature vector. The weights of the current eigenvectors. The weights of the nth eigenvector; The lifespan prediction module not only considers the equipment's historical operating data, but also uses the least squares method to dynamically adjust the weights of the feature vectors, making the prediction of the equipment's remaining lifespan more accurate. It adopts a regression analysis formula and uses optimized weight values ​​to accurately predict the equipment's remaining lifespan, providing a scientific basis for equipment maintenance and avoiding over-maintenance or missed inspections.

[0023] Based on equipment condition identification results and lifespan prediction data, a weighted average method is used to comprehensively calculate the equipment health index, which specifically includes: The health status label corresponding to the current working state of the equipment is used as one of the weighting factors, and the predicted value of the remaining service life of the equipment is used as the second weighting factor. The weighting factors are comprehensively weighted according to the set weights to obtain the health index of the equipment. The threshold of the health index is set to identify whether the equipment has potential failure risks. The formula for calculating the equipment health index is as follows:

[0024] In the formula, H represents the health index of the equipment, and S represents the current health status label of the equipment, with 1 for normal, 0.5 for impending failure, and 0 for failure. Predicted remaining useful life of the equipment. and These are the weighting factors for the current operating status and the predicted remaining useful life. , ; The health index combines condition identification results and lifespan prediction data, and uses a weighted average method for comprehensive calculation to ensure a comprehensive assessment of equipment health. This enables more accurate identification of potential failure risks. The use of the mean and standard deviation of the equipment's historical health index as the basis for threshold calculation further improves the reliability of the health index threshold, making the alarm mechanism more scientific and sensitive.

[0025] Setting the threshold for the health index specifically includes: Collect historical health index data of the equipment, record the health status of the equipment, perform statistical analysis on the health index, obtain the mean and standard deviation of the health index, select a 95% confidence level, and thus determine the threshold. The threshold calculation formula is as follows:

[0026] In the formula, For the threshold, This represents the average value of the equipment health index. The standard deviation of the equipment health index. It is a constant, with a value of 1.96, corresponding to a 95% confidence level; By adopting an optimization algorithm-based operation and maintenance strategy adjustment, combined with the equipment health index, historical maintenance data, and failure probability, the system can accurately predict equipment operation and maintenance needs, reduce operation and maintenance costs, and decrease equipment failure rate. By using a genetic algorithm to optimize the operation and maintenance strategy, the system can adjust the operation and maintenance plan in a timely manner according to changes in equipment status, thereby achieving the best operation and maintenance results.

[0027] The intelligent operation and maintenance decision-making module specifically includes: Operation and maintenance strategy generation unit: Based on the health index of the equipment and historical maintenance data, combined with different equipment types and failure modes, it generates targeted operation and maintenance strategies; Optimization Decision Unit: By adjusting and optimizing the operation and maintenance strategy based on optimization algorithms, the most suitable operation and maintenance solution for the current equipment status is selected; Maintenance personnel task allocation unit: allocates maintenance tasks based on the type of fault, equipment location, and the technical capabilities of the maintenance personnel; Maintenance report generation unit: Generates a detailed report for each maintenance work order. The detailed report includes the maintenance process, maintenance results, changes in equipment status, and recommended follow-up maintenance measures. The priority determination mechanism for maintenance tasks ensures the priority and rationality of task allocation by comprehensively considering multiple factors such as equipment health index, fault type and impact scope, thereby improving maintenance efficiency. The system intelligently allocates tasks based on the technical capabilities of maintenance personnel, which not only optimizes resource allocation but also avoids maintenance delays and errors caused by mismatches in personnel capabilities.

[0028] By adjusting and optimizing the operation and maintenance strategy based on optimization algorithms, the most suitable operation and maintenance solution for the current equipment status is selected, specifically including: Collect equipment health index, failure mode, historical maintenance data and failure probability data, select operation and maintenance strategies based on equipment status, and generate initial solutions; The objective function is constructed based on the equipment's health index, fault type, and maintenance cost factors, with the aim of minimizing operation and maintenance costs and minimizing downtime. The objective function is solved, and the operation and maintenance strategy is optimized based on the genetic algorithm. In each iteration, the weights are adjusted according to the search mechanism of the algorithm to minimize the objective function. The most suitable operation and maintenance plan is output based on the optimization results.

[0029] Based on the type of fault, equipment location, and the technical capabilities of the maintenance personnel, the specific allocation of maintenance tasks includes: Maintenance task priority determination unit: Based on the equipment's health index, fault type, and impact range, assess the urgency of the fault, calculate the priority of each maintenance task, and schedule maintenance tasks based on their priorities. The priority calculation formula is as follows:

[0030] In the formula, Prioritize maintenance tasks. This refers to the health index of the equipment. Score the severity of the fault type. A score for the extent of the fault's impact. The weights are respectively for the health index, fault type, and scope of impact.

[0031] The communication module specifically includes: Command receiving and response unit: Receives control commands from the intelligent operation and maintenance decision module, including operation commands and maintenance work order commands, parses the received commands, and forwards them to the corresponding equipment for execution; Data encryption and decryption unit: Uses the SM4 encryption algorithm to encrypt the acquired real-time data and decrypt the received data or instructions to restore the original data and control instructions; The SM4 encryption algorithm is used to encrypt data, ensuring the security of all transmitted data within the system. In particular, when transmitting monitoring data and receiving control commands, the confidentiality and integrity of information are ensured. Through the command receiving and response unit, control commands are forwarded to the device execution module, enabling operation and maintenance decisions to be reflected in device management quickly and accurately, thereby improving the system's response speed and operation and maintenance efficiency.

[0032] In summary, the advantages of this invention are as follows: Based on real-time data acquisition from sensor arrays within the ring main unit, standardized feature vectors are generated through edge computing, enabling real-time monitoring of equipment status. Combined with deep learning models, status identification is performed to promptly detect potential equipment faults and prevent the impact of equipment failures on the power system. By combining historical operating data and real-time status information, the remaining service life of the equipment is estimated through a life prediction model. At the same time, a health index of the equipment is generated to help maintenance personnel formulate equipment maintenance plans in advance and avoid sudden failures due to overuse of the equipment. Through the intelligent operation and maintenance decision model, based on the health index and the preset operation and maintenance strategy library, maintenance work orders are automatically generated, and fault location, maintenance suggestions and spare parts information are provided to help operation and maintenance personnel make maintenance decisions and assign tasks efficiently. The system adjusts and optimizes operation and maintenance strategies based on optimization algorithms to minimize operation and maintenance costs and downtime, reduce the time cost and economic loss of equipment repair, and improve the overall economic efficiency of the system. By employing the SM4 encryption algorithm to encrypt real-time data and control commands, the system ensures the security of transmitted data and prevents data from being stolen or tampered with during transmission. Based on the equipment's health index, fault type, and the technical capabilities of maintenance personnel, the system can dynamically adjust the priority of maintenance tasks to ensure that faults in critical equipment can be handled in a timely manner and improve maintenance efficiency.

[0033] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A big data-based online monitoring and intelligent operation and maintenance system for ring main unit status, characterized in that: include: The ring main unit status data acquisition module is used to collect operating parameters in real time based on the sensor array deployed in the ring main unit, perform edge computing on the real-time data, generate standardized feature vectors, and transmit the generated standardized feature vectors to the equipment health monitoring module. The equipment health monitoring module is used to pre-store the knowledge base and historical fault database of ring main unit equipment, and to perform status identification and life prediction on standardized feature vectors based on a deep learning model to generate an equipment health index. The intelligent operation and maintenance decision module is used to establish an intelligent operation and maintenance decision model based on the health index and the preset operation and maintenance strategy library. Based on the output of the intelligent operation and maintenance decision model, a maintenance work order is generated. The work order includes fault location, maintenance suggestions and spare parts information. The communication module is used to transmit monitoring data and receive control commands, and uses the SM4 encryption algorithm to ensure data security.

2. The big data-based online monitoring and intelligent operation and maintenance system for ring main unit status as described in claim 1, characterized in that, The ring main unit status data acquisition module specifically includes: Real-time data acquisition unit: Based on current sensors, voltage sensors, temperature and humidity sensors, vibration sensors and status indicator sensors, it collects real-time operating data in the ring main unit, including current, voltage, temperature and humidity and vibration parameters, and synchronizes the collected real-time data in time. Data preprocessing unit: Uses Kalman filtering algorithm to filter noise from the acquired signal and performs linear normalization on parameter data from different sources and with different dimensions; Feature extraction unit: Extracts time-domain features, frequency-domain features, and spatial features from the preprocessed data, standardizes the extracted features to obtain standardized feature vectors, and transmits the standardized feature vectors to the equipment health monitoring module through the communication module for further status identification and lifespan prediction.

3. The big data-based online monitoring and intelligent operation and maintenance system for ring main units according to claim 2, characterized in that, The device health monitoring module specifically includes: Status recognition unit: Based on a trained convolutional neural network deep learning model, it classifies feature vectors, identifies the current working status of the ring main unit equipment, including normal, fault, and impending fault, and outputs the health status label of the equipment; Life Prediction Unit: Combining historical operating data and equipment status information, the least squares method is used to solve for the weight parameters of the standardized eigenvector. The weight parameters of the standardized eigenvector are used as input, and the remaining life prediction data is used as output to establish a life prediction model. The remaining life of the equipment is estimated based on regression analysis. Health Index Generation Unit: Based on equipment status identification results and lifespan prediction data, a weighted average method is used to comprehensively calculate the equipment's health index; Anomaly detection and alarm unit: Based on the comparison between the health index and the threshold, it determines whether there are potential anomalies. If the health index is lower than the set threshold, the system will trigger an alarm mechanism to notify the operation and maintenance personnel to carry out maintenance.

4. The big data-based online monitoring and intelligent operation and maintenance system for ring main units according to claim 3, characterized in that, The lifetime prediction unit includes: The least squares method is used to minimize the sum of squared errors between the predicted and actual results. A cost function is constructed that measures the sum of squared errors of all sample points. The cost function is minimized by adjusting the weights. The partial derivatives of the cost function are calculated. The optimal parameters are obtained by solving these equations after setting the partial derivative of the cost function with respect to each weight to zero. Based on the derived weight values ​​and standardized eigenvectors, a life prediction model is established using regression analysis formulas to estimate the remaining lifespan of the equipment.

5. The big data-based online monitoring and intelligent operation and maintenance system for ring main units according to claim 3, characterized in that, The calculation of the equipment health index based on equipment status identification results and lifespan prediction data using a weighted average method specifically includes: The health status label corresponding to the current working state of the equipment is used as one of the weighting factors, and the predicted value of the remaining service life of the equipment is used as the second weighting factor. The weighting factors are comprehensively weighted according to the set weights to obtain the health index of the equipment. The threshold of the health index is set to identify whether the equipment has potential failure risks.

6. The big data-based online monitoring and intelligent operation and maintenance system for ring main units according to claim 5, characterized in that, The specific steps for setting the threshold for the health index include: collecting historical health index data of the device, recording the health status of the device, performing statistical analysis on the health index, obtaining the mean and standard deviation of the health index, and selecting a 95% confidence level to determine the threshold.

7. The big data-based online monitoring and intelligent operation and maintenance system for ring main units according to claim 1, characterized in that, The intelligent operation and maintenance decision-making module specifically includes: Operation and maintenance strategy generation unit: Based on the health index of the equipment and historical maintenance data, combined with different equipment types and failure modes, it generates targeted operation and maintenance strategies; Optimization Decision Unit: By adjusting and optimizing the operation and maintenance strategy based on optimization algorithms, the most suitable operation and maintenance solution for the current equipment status is selected; Maintenance personnel task allocation unit: allocates maintenance tasks based on the type of fault, equipment location, and the technical capabilities of the maintenance personnel; Maintenance report generation unit: Generates a detailed report for each maintenance work order, which includes the maintenance process, maintenance results, changes in equipment status, and recommended follow-up maintenance measures.

8. The big data-based online monitoring and intelligent operation and maintenance system for ring main unit status according to claim 7, characterized in that, The step of adjusting and optimizing the operation and maintenance strategy based on optimization algorithms to select the most suitable operation and maintenance solution for the current equipment status specifically includes: Collect equipment health index, failure mode, historical maintenance data and failure probability data, select operation and maintenance strategies based on equipment status, and generate an initial solution; The objective function is constructed based on the equipment's health index, fault type, and maintenance cost factors, with the aim of minimizing operation and maintenance costs and minimizing downtime. The objective function is solved, and the operation and maintenance strategy is optimized based on the genetic algorithm. In each iteration, the weights are adjusted according to the search mechanism of the algorithm to minimize the objective function. The most suitable operation and maintenance plan is output based on the optimization results.

9. The big data-based online monitoring and intelligent operation and maintenance system for ring main unit status according to claim 7, characterized in that, The process of allocating maintenance tasks based on fault type, equipment location, and the technical capabilities of maintenance personnel specifically includes: assessing the urgency of the fault based on the equipment's health index, fault type, and scope of impact; calculating the priority of each maintenance task; and scheduling maintenance tasks based on their priorities.

10. The big data-based online monitoring and intelligent operation and maintenance system for ring main units according to claim 7, characterized in that, The communication module specifically includes: Command receiving and response unit: Receives control commands from the intelligent operation and maintenance decision module, including operation commands and maintenance work order commands, parses the received commands, and forwards them to the corresponding equipment for execution; Data encryption and decryption unit: Uses the SM4 encryption algorithm to encrypt the acquired real-time data and decrypt the received data or instructions to restore the original data and control instructions.

Images