Primary and secondary fusion environment-friendly ring main unit intelligent monitoring system and method

Abstract

The invention relates to the technical field of electric power, in particular to a primary and secondary fusion environment-friendly ring main unit intelligent monitoring system and method, and the system comprises a data collection module which is used for collecting multi-mode monitoring data of a ring main unit to obtain an original monitoring data set; the data processing module is used for performing standardization processing on the original monitoring data set to obtain a standardized multi-modal monitoring data set; the intelligent monitoring module is used for performing state evaluation based on the standardized multi-mode monitoring data set to obtain an equipment state monitoring evaluation result; the digital twinning module is used for constructing a digital twinning model and performing digital twinning analysis on the equipment state monitoring and evaluation result through the digital twinning model to obtain a health index and a fault risk prediction result; the strategy generation module is used for generating an operation and maintenance strategy set based on the health index and the fault risk prediction result; and the strategy execution module is used for executing operation and maintenance operation according to the operation and maintenance strategy set and recording an operation and maintenance execution effect.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric power, and in particular to a primary and secondary fusion environment-friendly ring main unit intelligent monitoring system and method. BACKGROUND

[0002] At present, the monitoring of the ring main unit of the distribution network mainly relies on artificial regular inspection and scattered automation systems, which has significant technical defects: various types of monitoring data are scattered in different systems, forming a data island, and it is difficult to achieve unified analysis and deep mining; state evaluation relies on threshold alarm and manual experience, and early fault warning and accurate diagnosis cannot be achieved; the operation and maintenance strategy lacks foresight and is mostly a passive response, resulting in high maintenance cost and difficulty in guaranteeing power supply reliability. The existing technology lacks a systematic solution that integrates multi-source data fusion, intelligent state evaluation, digital twin prediction and adaptive operation and maintenance, which seriously restricts the transformation and upgrading of the operation and maintenance management of the distribution network to intelligence and precision.

[0003] A Chinese patent with publication number CN120357303A discloses a digital environment-friendly primary and secondary fusion complete ring main unit with Beidou positioning, relating to the technical field of electric power; the primary switch unit and the secondary control unit of the ring main unit are fused to reduce the volume of the ring main unit; a Beidou positioning device is arranged to improve positioning accuracy through Beidou positioning technology; a data acquisition device is arranged to acquire monitoring data and realize intelligent monitoring of the ring main unit; further, based on Beidou positioning information, ring main unit monitoring data and historical switch control information of the secondary control unit, remote monitoring information is generated and reported to a remote monitoring terminal to realize remote monitoring of the ring main unit and improve the safety and reliability of the ring main unit. Thus, the technical solution integrates Beidou positioning technology and primary and secondary equipment fusion technology in the ring main unit, making the ring main unit have the characteristics of small volume, intelligence, convenient operation and safety and reliability. However, this scheme still has the problems of low maintenance efficiency, insufficient fault warning capability and high operation and maintenance cost caused by data island, diagnosis lag and extensive operation and maintenance. SUMMARY

[0004] Therefore, the present application provides a primary and secondary fusion environment-friendly ring main unit intelligent monitoring system and method to overcome the problems of low maintenance efficiency, insufficient fault warning capability and high operation and maintenance cost caused by data island, diagnosis lag and extensive operation and maintenance in the prior art.

[0005] To achieve the above-mentioned purpose, in one aspect, the present application provides a primary and secondary fusion environment-friendly ring main unit intelligent monitoring system, comprising: a data acquisition module, configured to acquire multi-modal monitoring data of the ring main unit to obtain an original monitoring data set; a data processing module, configured to perform standardization processing on the original monitoring data set to obtain a standardized multi-modal monitoring data set; an intelligent monitoring module configured to perform state evaluation based on the standardized multi-modal monitoring dataset to obtain a device state monitoring evaluation result; a digital twin module configured to construct a digital twin model and perform digital twin analysis on the device state monitoring evaluation result by using the digital twin model to obtain a health index and a failure risk prediction result; a strategy generation module configured to generate a set of operation and maintenance strategies based on the health index and the failure risk prediction result; a strategy execution module configured to perform operation and maintenance operations according to the set of operation and maintenance strategies and record operation and maintenance execution effects.

[0006] Further, the data acquisition module acquires multi-modal monitoring data of the ring network cabinet through multiple types of sensors to obtain an original monitoring dataset, including: Through multiple types of sensors deployed in the ring network cabinet and associated facilities, electrical quantity, non-electrical quantity and acoustic data are acquired in parallel; the original data acquired by each type of sensor is encapsulated and time-stamped to generate primary data packets with space-time identifiers; all primary data packets are aggregated to an edge computing gateway and subjected to preliminary verification and caching; the primary data packets that pass the verification are aggregated according to a predetermined time window to output a structured original monitoring dataset.

[0007] Further, the data processing module performs standardization processing on the original monitoring dataset to obtain a standardized multi-modal monitoring dataset, including: The original monitoring dataset is subjected to data cleaning and outlier processing to obtain a regularized dataset, the regularized dataset is subjected to format and dimension unification to obtain an intermediate standardized dataset, and the intermediate standardized dataset is subjected to numerical normalization and feature scaling to obtain the standardized multi-modal monitoring dataset.

[0008] Further, the intelligent monitoring module performs state evaluation based on the standardized multi-modal monitoring dataset to obtain a device state monitoring evaluation result, including: Multi-modal feature extraction is performed on the standardized multi-modal monitoring dataset to obtain a time series feature vector set and an event feature vector set, the time series feature vector set and the event feature vector set are input into a pre-trained lightweight AI evaluation model to obtain a preliminary abnormality detection result, logical verification and root cause analysis are performed on the preliminary abnormality detection result based on a neural-symbol hybrid reasoning engine to obtain a verified abnormality diagnosis result, and the verified abnormality diagnosis result and a device operation context are integrated to generate a structured device state monitoring evaluation result.

[0009] Further, the digital twin module constructs a digital twin model, including: Obtaining physical structure parameters and material characteristic data of the ring network cabinet, establishing a three-dimensional geometric model; based on the three-dimensional geometric model of the equipment, a multi-physical field coupling simulation model is constructed; based on the multi-physical field coupling simulation model, a life prediction algorithm is integrated, and an equipment degradation model is established; a dynamic calibration mechanism is deployed to the equipment degradation model, and a calibrated digital twin model is obtained.

[0010] Further, the digital twin module performs digital twin analysis on the equipment state monitoring evaluation result through the digital twin model to obtain health index and fault risk prediction results, including: The equipment state monitoring evaluation result is input into the digital twin model, multi-physical field coupling simulation is performed to obtain a simulation data set, life prediction analysis is performed based on the simulation data set to obtain life evaluation data, fault risk assessment is performed based on the life evaluation data to obtain a fault risk prediction list, and the life evaluation data and the fault risk prediction list are integrated to generate a health index and fault risk prediction result report.

[0011] Further, specifically, the strategy generation module generates a set of operation and maintenance strategies based on the health index and fault risk prediction results, including: According to the health index and fault risk prediction results, a set of preliminary operation and maintenance strategy options is obtained, resource constraint optimization is performed on the set of preliminary operation and maintenance strategy options to obtain an optimized operation and maintenance strategy scheme, and the optimized operation and maintenance strategy scheme is prioritized for execution to obtain a final set of operation and maintenance strategies.

[0012] Further, the strategy execution module executes operation and maintenance operations according to the set of operation and maintenance strategies, and records operation and maintenance execution effects, including: The set of operation and maintenance strategies is converted into an executable instruction set and distributed to an execution terminal; the executable instruction set is executed and the execution process is monitored in real time to obtain execution process data; post-execution equipment state data is collected and compared with expected effects to generate an execution effect evaluation report; system parameters are updated based on the execution effect evaluation report to complete closed-loop optimization.

[0013] Further, the set of operation and maintenance strategies is converted into an executable instruction set and distributed to an execution terminal, specifically: analyzing the work order content, execution time window and resource allocation scheme in the set of operation and maintenance strategies; generating an executable instruction set composed of equipment operation instructions, personnel scheduling instructions and material allocation instructions; the instruction set is distributed to the on-site operation terminal and the remote control system through a secure communication protocol; The executable instruction set is executed, and the execution process is monitored in real time to obtain execution process data, specifically: the remote control system executes the equipment operation according to the instruction, including the opening and closing of the circuit breaker and the starting and stopping of the water pump; the field operation terminal receives the dispatching instruction to guide the maintenance personnel to carry out the maintenance operation according to the plan; the execution process data is collected in real time through the sensor and the video monitoring, including the equipment state change and the operation completion degree; The device state data after execution is collected, and the expected effect is compared to generate an execution effect evaluation report, specifically: after the execution is completed, the device running state data is collected through the sensor network, the collected state data is compared and analyzed with the expected device state improvement target in the operation and maintenance strategy, and an operation effect evaluation report containing the target achievement degree, problem solving rate and efficiency index is generated; The system parameters are updated based on the execution effect evaluation report to complete the closed-loop optimization, specifically: the pre-warning threshold and the strategy rule library parameters are adjusted according to the evaluation result, the execution process data and the effect data are stored in the historical database for model retraining, the system parameter update confirmation information is output, and the closed-loop management of the current operation and maintenance is completed.

[0014] On the other hand, the embodiment also provides a method for intelligent monitoring of a primary and secondary fusion environmental ring network cabinet, which comprises: Step S1, collecting multi-modal monitoring data of the ring network cabinet to obtain an original monitoring data set; Step S2, standardizing the original monitoring data set to obtain a standardized multi-modal monitoring data set; Step S3, performing state evaluation based on the standardized multi-modal monitoring data set to obtain a device state monitoring evaluation result; Step S4, constructing a digital twin model and performing digital twin analysis on the device state monitoring evaluation result through the digital twin model to obtain a health index and a fault risk prediction result; Step S5, generating an operation and maintenance strategy set based on the health index and the fault risk prediction result; Step S6, executing operation and maintenance operation according to the operation and maintenance strategy set and recording operation and maintenance execution effect.

[0015] Compared with the prior art, the beneficial effects of the present application are that the system accurately acquires multi-dimensional monitoring data through the data acquisition module, solves the problem of scattered data sources and heterogeneous formats in traditional monitoring, and provides a complete and unified data basis for equipment state evaluation; the system also standardizes the multi-source heterogeneous data through the data processing module, realizes the feature alignment and dimension unification of multi-modal data, and overcomes the technical bottleneck of poor data quality and difficulty in fusion analysis in traditional systems; the system also performs intelligent diagnosis based on standardized data through the intelligent monitoring module, realizes the accurate identification and early warning of abnormal equipment state, and significantly improves the reliability of state evaluation; the system also constructs a high-fidelity virtual model through the digital twin module and performs multi-physical field simulation, realizes the quantitative evaluation of equipment health state and the accurate prediction of fault risk, and changes the maintenance strategy from "periodic maintenance" to "predictive maintenance"; the system also automatically generates operation and maintenance schemes based on health indexes and risk prediction through the strategy generation module, realizes the intelligentization and precision of operation and maintenance decision, and greatly reduces the operation and maintenance cost; the system also converts the strategy into executable instructions through the strategy execution module and records the effect, realizes the closed-loop management and continuous optimization of the operation and maintenance process, and significantly improves the power supply reliability. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 FIG. 1 is a structural schematic diagram of a secondary fusion environment-friendly ring main unit intelligent monitoring system according to the present application; Figure 2 FIG. 2 is a flowchart of a method of a secondary fusion environment-friendly ring main unit intelligent monitoring system according to the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose and advantages of the present application more clear and obvious, the present application will be further described below in conjunction with examples; it should be understood that the specific examples described herein are only used to explain the present application, and are not used to limit the present application.

[0018] The preferred embodiments of the present application will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application, and are not used to limit the protection scope of the present application.

[0019] It should be noted that in the description of the present application, the terms "upper", "lower", "left", "right", "inner", "outer" and the like indicate the direction or positional relationship terms based on the direction or positional relationship shown in the drawings, which are only for the convenience of description, and do not indicate or imply that the device or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application.

[0020] Moreover, it needs to be explained that, in the description of the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connection", "connecting" should be understood broadly, for example, can be fixed connection, can also be detachable connection, or integrally connected; can be mechanical connection, can also be electrical connection; can be directly connected, can also be indirectly connected through intermediate medium, can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0021] Please refer to Figure 1 The system comprises: A data acquisition module is configured to acquire multi-modal monitoring data of the ring main unit and obtain an original monitoring data set. A data processing module is configured to perform standardization processing on the original monitoring data set and obtain a standardized multi-modal monitoring data set. An intelligent monitoring module is configured to perform state evaluation based on the standardized multi-modal monitoring data set and obtain a device state monitoring evaluation result. A digital twin module is configured to construct a digital twin model and perform digital twin analysis on the device state monitoring evaluation result through the digital twin model to obtain a health index and a failure risk prediction result. A strategy generation module is configured to generate a set of operation and maintenance strategies based on the health index and the failure risk prediction result. A strategy execution module is configured to perform operation and maintenance operations according to the set of operation and maintenance strategies and record operation and maintenance execution effects.

[0022] Specifically, the system realizes intelligent management from data acquisition to operation and maintenance execution by constructing an intelligent monitoring full-process automation chain of ring main units. The system accurately acquires multi-dimensional monitoring data through a data acquisition module, solves the problem of scattered data sources and heterogeneous formats in traditional monitoring, and provides a complete and unified data basis for equipment state evaluation. The system also standardizes multi-source heterogeneous data through a data processing module, realizes feature alignment and dimension unification of multi-modal data, and overcomes the technical bottleneck of poor data quality and difficulty in fusion analysis in traditional systems. The system also performs intelligent diagnosis based on standardized data through an intelligent monitoring module, realizes accurate identification and early warning of abnormal equipment state, and significantly improves the reliability of state evaluation. The system also constructs a high-fidelity virtual model and performs multi-physical field simulation through a digital twin module, realizes quantitative evaluation of equipment health state and accurate prediction of fault risk, and changes the maintenance strategy from "periodic maintenance" to "predictive maintenance". The system also automatically generates operation and maintenance schemes based on health indexes and risk predictions through a strategy generation module, realizes the intelligentization and precision of operation and maintenance decision-making, and significantly reduces operation and maintenance costs. The system also converts strategies into executable instructions and records effects through a strategy execution module, realizes closed-loop management and continuous optimization of the operation and maintenance process, and significantly improves power supply reliability.

[0023] Specifically, the data acquisition module acquires multi-modal monitoring data of the ring main unit through multiple types of sensors to obtain an original monitoring data set, including: Through multiple types of sensors deployed inside the ring main unit and associated facilities, electrical, non-electrical, and acoustic data are collected in parallel. The original data collected by each type of sensor is encapsulated and synchronized with a time stamp to generate primary data packets with space-time identifiers. All primary data packets are aggregated to an edge computing gateway and subjected to preliminary verification and caching. The primary data packets that pass the verification are aggregated according to a predetermined time window, and a structured original monitoring data set is output.

[0024] Specifically, through multiple types of sensors deployed inside the ring main unit and associated facilities, electrical, non-electrical, and acoustic data are collected in parallel. Specifically, through pre-installed wireless temperature sensors with a sampling frequency of 1 Hz, temperature data of key points such as cable joints and circuit breaker contacts are collected. At the same time, current and voltage waveform data in the circuit are collected through a mutual inductor. The ambient temperature and humidity inside the cabinet are collected through a temperature and humidity sensor. The cabinet door opening and closing state is monitored through a door magnetic sensor. The water depth in the cable trench is monitored through a water level sensor. The mechanical vibration acceleration is monitored through a vibration sensor. The sound signal during the operation of the ring main unit is continuously collected through a high-fidelity microphone array with a sampling rate of 44.1 kHz. The raw data collected by various sensors is packaged and time-stamped synchronously to generate primary data packets with space-time identification, specifically: the microcontroller built-in each sensor node performs analog-to-digital conversion on the collected raw analog signals; the edge computing gateway applies a unified millisecond-level time stamp to all accessed sensor data streams through the NTP protocol, and adds a sensor ID and a ring net cabinet asset code to each data packet; the tagged multi-dimensional data is packaged in a preset format (such as JSON or Protocol Buffers) to generate primary data packets; All primary data packets are aggregated to the edge computing gateway and subjected to preliminary checking and caching, specifically: the edge computing gateway receives all primary data packets through multi-protocol interfaces (such as RS-485, ZigBee, LoRa); the received data packets are subjected to CRC checking, and the failed data packets are discarded, and the successfully received data packets are subjected to time series caching in the temporary storage area of the gateway; The primary data packets that pass the checking are aggregated according to a predetermined time window to output a structured raw monitoring data set, specifically: the system takes 1 minute as an aggregation time window, integrates all primary data packets that pass the checking in the time window according to the sensor type and time sequence, generates a structured raw monitoring data set containing complete information such as temperature data sequence, current and voltage waveform segments, environmental parameters, state switch quantity, and sound signal segments, and outputs the data set to a data bus for use in subsequent standardization processing steps.

[0025] Specifically, the data processing module standardizes the raw monitoring data set to obtain a standardized multi-modal monitoring data set, including: The raw monitoring data set is subjected to data cleaning and outlier processing to obtain a regularized data set, the regularized data set is subjected to format and dimension unification to obtain an intermediate standardized data set, and the intermediate standardized data set is subjected to numerical normalization and feature scaling to obtain a standardized multi-modal monitoring data set.

[0026] Specifically, the raw monitoring data set is subjected to data cleaning and outlier processing to obtain a regularized data set, specifically: for continuous data such as temperature and current, if instantaneous missing occurs, linear interpolation of the two valid sampling points before and after is used for filling; based on the Ralda criterion (3σ criterion), abnormal data points obviously deviating from the normal range are identified and removed. For example, for the cable joint temperature sequence, the mean value and standard deviation are calculated, and the data points exceeding the range of [mean value-3σ, mean value+3σ] are marked as invalid and removed; for the vacancy caused by removing the outliers, the sliding window mean value method is used again for data repair; The format and dimension of the regularized data set are unified to obtain an intermediate standardized data set, specifically: the sampling time stamps of all sensor data are aligned to the whole second moment, for non-integer second sampling data, the nearest neighbor interpolation method is used for matching, different formats of data (such as analog quantity, state quantity, waveform data) are uniformly converted into floating point array or integer flag bit, and are packaged into a unified data frame structure, and all physical quantities are converted into standard international units. For example, temperature is converted from Fahrenheit to Celsius, and current is converted from milliamperes to amperes; The intermediate standardized data set is subjected to numerical normalization and feature scaling to obtain a standardized multi-modal monitoring data set, specifically: for continuous numerical features such as temperature and current, Min-Max scaling is used to linearly map them to the [0, 1] interval; for categorical data such as "cabinet door state" (open / close), one-hot encoding is performed to convert it into a binary vector; finally, a standardized multi-modal monitoring data set with consistent feature scales, which can be directly input into subsequent AI models, is generated.

[0027] Specifically, the intelligent monitoring module performs state evaluation based on the standardized multi-modal monitoring data set to obtain a device state monitoring evaluation result, including: The standardized multi-modal monitoring data set is subjected to multi-modal feature extraction to obtain a time series feature vector set and an event feature vector set, the time series feature vector set and the event feature vector set are input into a pre-trained lightweight AI evaluation model to obtain a preliminary abnormality detection result, the preliminary abnormality detection result is subjected to logical verification and root cause analysis based on a neural-symbol hybrid reasoning engine to obtain a verified abnormality diagnosis result, and the verified abnormality diagnosis result and the device running context are comprehensively analyzed to generate a structured device state monitoring evaluation result.

[0028] Specifically, the standardized multi-modal monitoring data set is subjected to multi-modal feature extraction to obtain a time series feature vector set and an event feature vector set, specifically: for continuous monitoring data such as temperature and current, sliding window technology is used to extract time domain features (such as mean, variance, peak) and frequency domain features (such as main frequency components obtained by FFT transformation); for discrete data such as switch state changes and alarm events, event statistical features (such as event frequency, duration, correlation) are extracted, and for sound signals, acoustic feature vectors are extracted through mel frequency cepstral coefficients; inputting the time sequence feature vector set and the event feature vector set into a pre-trained lightweight AI evaluation model to obtain a preliminary abnormality detection result, specifically, using a lightweight convolutional neural network optimized based on ResNet-18 to process time sequence features to identify temperature abnormality trends and current fluctuation patterns, using a gradient boosting decision tree model to analyze event features to evaluate switch operation abnormality probabilities, and the model outputting a preliminary abnormality detection result containing abnormality types (such as overheating, mechanical jamming, and insulation deterioration) and abnormality confidence levels; performing logical verification and root cause analysis on the preliminary abnormality detection result based on a neural-symbol hybrid reasoning engine to obtain a verified abnormality diagnosis result, specifically, matching and verifying the preliminary abnormality detection result with a pre-defined device fault knowledge graph, the knowledge graph containing 300+ fault mode and symptom association rules, using a graph neural network to analyze the association relationships between multiple abnormality points to accurately locate fault sources, and based on a structural causal model to distinguish symptoms from root causes to avoid misjudgment; generating a structured device state monitoring evaluation result by comprehensively integrating the verified abnormality diagnosis result and device operation context, and generating a structured device state monitoring evaluation result by comprehensively integrating the verified abnormality diagnosis result and device operation context: fusing the verified abnormality diagnosis result with current load level, environmental conditions, and operation time of the device to generate a structured device state monitoring evaluation result containing device health state score (0-100 points), main abnormality type, fault risk level (high / medium / low), and recommended attention area, encapsulating the result as a JSON format data packet, and outputting to a subsequent digital twin analysis step.

[0029] Specifically, the digital twin module includes constructing a digital twin model, which includes: obtaining physical structure parameters and material characteristic data of the ring main unit, establishing a three-dimensional geometric model, constructing a multi-physical field coupling simulation model based on the device three-dimensional geometric model, integrating a life prediction algorithm based on the multi-physical field coupling simulation model, establishing a device degradation model, and deploying a dynamic calibration mechanism to the device degradation model to obtain a calibrated digital twin model.

[0030] Specifically, the physical structure parameters and material characteristic data of the ring main unit are obtained to establish a three-dimensional geometric model, specifically: based on device design drawings and three-dimensional scanning data, the size parameters and assembly relationships of each component are extracted, a parameterized modeling method is used to construct a three-dimensional geometric model containing circuit breakers, disconnectors, and cable joints, and material characteristic parameters including electrical conductivity, thermal conductivity, and mechanical strength parameters are assigned to each component of the model; Based on the device three-dimensional geometric model, a multi-physics field coupling simulation model is constructed, specifically: based on the geometric model, an electrical characteristic simulation model is established, including circuit equivalent parameters; a thermodynamic simulation model is constructed to calculate the current-induced heating and environmental heat transfer effect, a mechanical characteristic simulation model is established to simulate the kinematic characteristics of the operating mechanism, and multi-physics field coupling boundary conditions are set to form a complete coupled simulation model; Based on the multi-physics field coupling simulation model, a life prediction algorithm is integrated to establish a device degradation model, specifically: integrating a thermal aging algorithm for insulating materials into the coupled simulation model, and adding a mechanical component wear prediction algorithm; combining historical operation data to establish a comprehensive life assessment model, and outputting a device degradation model containing degradation characteristics; A dynamic calibration mechanism is deployed for the device degradation model to obtain a calibrated digital twin model, specifically: using Kalman filtering algorithm to correct model parameters, establishing a model error feedback channel to automatically adjust model bias, setting model update trigger conditions to realize model self-correction, and outputting a real-time calibrated digital twin model.

[0031] Specifically, the digital twin module performs digital twin analysis on the device state monitoring and evaluation results through the digital twin model to obtain health index and failure risk prediction results, including: The device state monitoring and evaluation results are input into the digital twin model, multi-physics field coupling simulation is performed to obtain a simulation data set, life prediction analysis is performed based on the simulation data set to obtain life assessment data, failure risk assessment is performed based on the life assessment data to obtain a failure risk prediction list, and the life assessment data and failure risk prediction list are combined to generate a health index and failure risk prediction result report.

[0032] Specifically, the device state monitoring and evaluation results are input into the digital twin model, multi-physics field coupling simulation is performed to obtain a simulation data set, specifically: abnormal data in the device state monitoring and evaluation results are used as input parameters to drive the digital twin model, electrical-thermal-mechanical multi-physics field coupling simulation calculation is performed, and a simulation data set containing temperature field distribution, stress distribution, and electromagnetic field intensity is output; Based on the simulation data set, life prediction analysis is performed to obtain life assessment data, specifically: temperature parameters in the simulation data set are input into the thermal aging model to calculate the remaining life of insulating materials, stress parameters in the simulation data set are input into the mechanical wear model to calculate the remaining life of mechanical components, and life assessment data containing the predicted values of the remaining life of each component is output; Performing a failure risk assessment based on the life assessment data to obtain a failure risk prediction list, specifically: inputting the life assessment data into a Weibull distribution model, calculating the failure probability of each component, combining the device operating environment parameters, correcting the failure probability calculation results, and outputting a failure risk prediction list sorted by risk level; Integrating the life assessment data and the failure risk prediction list to generate a health index and failure risk prediction result report, specifically: based on the life assessment data, using a weighted algorithm to calculate the health index, integrating the failure risk prediction list to generate the failure risk prediction, and outputting a complete analysis report containing the health index and the failure risk prediction.

[0033] Specifically, the strategy generation module generates a set of operation and maintenance strategies based on the health index and failure risk prediction results, including: According to the health index and failure risk prediction results, a set of preliminary operation and maintenance strategy options is obtained, resource constraint optimization is performed on the set of preliminary operation and maintenance strategy options, an optimized operation and maintenance strategy scheme is obtained, and the optimized operation and maintenance strategy scheme is prioritized for execution to obtain a final set of operation and maintenance strategies.

[0034] Specifically, according to the health index and failure risk prediction results, a set of preliminary operation and maintenance strategy options is obtained, specifically: comparing the health index with the preset threshold interval to determine the basic maintenance level, classifying and analyzing the risk types and probability levels in the failure risk prediction, and matching to obtain a set of preliminary operation and maintenance strategy options containing maintenance types and execution time limits based on a pre-defined strategy rule library; Resource constraint optimization is performed on the set of preliminary operation and maintenance strategy options to obtain an optimized operation and maintenance strategy scheme, specifically: obtaining the current available operation and maintenance resource state, including personnel scheduling, spare parts inventory, combining device topology location information to calculate the optimal operation and maintenance path and resource allocation scheme, balancing maintenance cost and risk control demand based on a multi-objective optimization algorithm to generate an optimized operation and maintenance strategy scheme; The optimized operation and maintenance strategy scheme is prioritized for execution to obtain a final set of operation and maintenance strategies, specifically: considering the failure risk level, the importance of the device, and the power supply influence range, calculating the urgency and importance scores of each strategy execution using the analytic hierarchy process to generate a final set of operation and maintenance strategies sorted by priority, including specific work order content, execution time window, and resource allocation scheme.

[0035] Specifically, the strategy execution module executes operation and maintenance operations according to the set of operation and maintenance strategies and records the operation and maintenance execution effect, including: The operation and maintenance strategy set is converted into an executable instruction set and is delivered to an execution terminal; the executable instruction set is executed and the execution process is monitored in real time to obtain execution process data; device state data after execution is collected, compared with expected effects, and an execution effect evaluation report is generated; system parameters are updated based on the execution effect evaluation report to complete closed-loop optimization.

[0036] Specifically, the operation and maintenance strategy set is converted into an executable instruction set and is delivered to an execution terminal, specifically: the work order content, execution time window, and resource allocation scheme in the operation and maintenance strategy set are parsed; an executable instruction set composed of device operation instructions, personnel scheduling instructions, and material allocation instructions is generated; the instruction set is delivered to a field operation terminal and a remote control system through a secure communication protocol; The executable instruction set is executed and the execution process is monitored in real time to obtain execution process data, specifically: the remote control system executes device operations according to the instructions, including circuit breaker opening and closing and water pump starting and stopping; the field operation terminal receives scheduling instructions to guide maintenance personnel to carry out maintenance operations according to the plan; execution process data is collected in real time through sensors and video monitoring, including device state changes and operation completion degrees; Device state data after execution is collected, compared with expected effects, and an execution effect evaluation report is generated, specifically: after execution is completed, device state data is collected through a sensor network, the collected state data is compared and analyzed with expected device state improvement targets in the operation and maintenance strategy, and an operation effect evaluation report containing target achievement degrees, problem solving rates, and efficiency indicators is generated; System parameters are updated based on the execution effect evaluation report to complete closed-loop optimization, specifically: the pre-warning threshold and strategy rule library parameters are adjusted according to the evaluation results, execution process data and effect data are stored in a historical database for model retraining, system parameter update confirmation information is output, and closed-loop management of this operation and maintenance is completed.

[0037] Please refer to Figure 2 The method comprises the following steps: Step S1, collecting multi-modal monitoring data of the ring main unit to obtain an original monitoring data set; Step S2, performing standardization processing on the original monitoring data set to obtain a standardized multi-modal monitoring data set; Step S3, performing state evaluation based on the standardized multi-modal monitoring data set to obtain a device state monitoring evaluation result; Step S4, constructing a digital twin model and performing digital twin analysis on the device state monitoring evaluation result through the digital twin model to obtain a health index and a fault risk prediction result; Step S5, generating a set of operation and maintenance strategies based on the health index and the failure risk prediction result; Step S6, performing operation and maintenance operation according to the set of operation and maintenance strategies, and recording operation and maintenance execution effect.

[0038] So far, the technical solutions of the present application have been described in combination with the preferred embodiments shown in the drawings, but it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to the related technical features without deviating from the principles of the present application, and the technical solutions after these changes or replacements will all fall within the protection scope of the present application.

Claims

1. A primary and secondary integrated environmental protection ring network cabinet intelligent monitoring system, characterized in that, include: The data acquisition module is used to collect multimodal monitoring data of the ring main unit to obtain the raw monitoring dataset; The data processing module is used to standardize the original monitoring dataset to obtain a standardized multimodal monitoring dataset. The intelligent monitoring module is used to perform condition assessment based on the standardized multimodal monitoring dataset to obtain equipment condition monitoring assessment results; The digital twin module is used to construct a digital twin model and perform digital twin analysis on the equipment status monitoring and evaluation results through the digital twin model to obtain health index and fault risk prediction results. The strategy generation module is used to generate a set of operation and maintenance strategies based on the health index and the fault risk prediction results; The strategy execution module is used to execute operation and maintenance operations according to the set of operation and maintenance strategies, and record the operation and maintenance execution results.

2. The intelligent monitoring system for integrated primary and secondary environmental protection ring network cabinets according to claim 1, characterized in that, The data acquisition module collects multimodal monitoring data of the ring main unit through multiple types of sensors, and the raw monitoring dataset includes: Multiple sensors deployed inside the ring main unit and related facilities are used to collect electrical, non-electrical, and acoustic data in parallel. The raw data collected by various sensors are encapsulated and timestamped to generate primary data packets with spatiotemporal identifiers. All primary data packets are aggregated to the edge computing gateway and preliminarily verified and cached. The verified primary data packets are aggregated according to a predetermined time window to output a structured raw monitoring dataset.

3. The intelligent monitoring system for integrated primary and secondary environmental protection ring network cabinets according to claim 1, characterized in that, The data processing module standardizes the original monitoring dataset to obtain a standardized multimodal monitoring dataset, including: The original monitoring dataset is cleaned and outlier processed to obtain a regularized dataset. The regularized dataset is then standardized in terms of format and dimensions to obtain an intermediate standardized dataset. Finally, the intermediate standardized dataset is subjected to numerical normalization and feature scaling to obtain a standardized multimodal monitoring dataset.

4. The intelligent monitoring system for integrated primary and secondary environmental protection ring network cabinets according to claim 1, characterized in that, The intelligent monitoring module performs a status assessment based on the standardized multimodal monitoring dataset, and the resulting equipment status monitoring assessment results include: Multimodal feature extraction is performed on the standardized multimodal monitoring dataset to obtain a time-series feature vector set and an event feature vector set. The time-series feature vector set and the event feature vector set are input into a pre-trained lightweight AI evaluation model to obtain preliminary anomaly detection results. Logical verification and root cause analysis are performed on the preliminary anomaly detection results based on a neural symbolic hybrid inference engine to obtain verified anomaly diagnosis results. The verified anomaly diagnosis results are combined with the equipment operating context to generate structured equipment status monitoring evaluation results.

5. The intelligent monitoring system for integrated primary and secondary environmental protection ring network cabinets according to claim 1, characterized in that, The digital twin module constructs the digital twin model, including: The physical structural parameters and material properties of the ring main unit are acquired, and a three-dimensional geometric model is established. Based on the three-dimensional geometric model of the equipment, a multi-physics field coupled simulation model is constructed. Based on the multi-physics field coupled simulation model, a life prediction algorithm is integrated to establish an equipment degradation model. A dynamic calibration mechanism is deployed on the equipment degradation model to obtain a calibrated digital twin model.

6. The intelligent monitoring system for integrated primary and secondary environmental protection ring network cabinets according to claim 1, characterized in that, The digital twin module performs digital twin analysis on the equipment status monitoring and evaluation results through the digital twin model to obtain health index and fault risk prediction results, including: The equipment condition monitoring and evaluation results are input into the digital twin model, multiphysics coupling simulation is performed to obtain a simulation dataset, life prediction analysis is performed based on the simulation dataset to obtain life assessment data, failure risk assessment is performed based on the life assessment data to obtain a failure risk prediction list, and a health index and failure risk prediction result report is generated by combining the life assessment data and the failure risk prediction list.

7. The intelligent monitoring system for integrated primary and secondary environmental protection ring network cabinets according to claim 1, characterized in that, Specifically, the strategy generation module generates a set of operation and maintenance strategies based on the health index and fault risk prediction results, including: Based on the health index and the fault risk prediction results, a preliminary set of operation and maintenance strategy options is obtained by matching strategies. The preliminary set of operation and maintenance strategy options is then optimized by resource constraints to obtain an optimized operation and maintenance strategy scheme. Finally, the optimized operation and maintenance strategy scheme is prioritized to obtain a final set of operation and maintenance strategies.

8. The intelligent monitoring system for integrated primary and secondary environmental protection ring network cabinets according to claim 1, characterized in that, The strategy execution module executes maintenance operations according to the set of maintenance strategies and records the maintenance execution results, including: The set of operation and maintenance strategies is converted into an executable instruction set and sent to the execution terminal; the executable instruction set is executed, and the execution process is monitored in real time to obtain execution process data; the device status data after execution is collected, compared with the expected effect, and an execution effect evaluation report is generated; the system parameters are updated based on the execution effect evaluation report to complete closed-loop optimization.

9. The intelligent monitoring system for integrated primary and secondary environmental protection ring network cabinets according to claim 8, characterized in that, The set of operation and maintenance strategies is transformed into an executable instruction set and sent to the execution terminal. Specifically, this involves: parsing the work order content, execution time window, and resource allocation scheme in the set of operation and maintenance strategies; generating an executable instruction set consisting of equipment operation instructions, personnel scheduling instructions, and material allocation instructions; and sending the instruction set to the field operation terminal and remote control system through a secure communication protocol. The executable instruction set is executed, and the execution process is monitored in real time to obtain execution process data. Specifically, the remote control system executes equipment operations according to the instructions, including circuit breaker opening and closing, and water pump start and stop; the field operation terminal receives dispatch instructions to guide maintenance personnel to carry out maintenance operations according to plan; and the execution process data, including equipment status changes and operation completion rate, is collected in real time through sensors and video monitoring. Collect equipment status data after execution, compare it with the expected effect, and generate an execution effect evaluation report. Specifically, after execution, collect equipment operating status data through sensor network, compare and analyze the collected status data with the expected equipment status improvement targets in the operation and maintenance strategy, and generate an operation effect evaluation report that includes target achievement, problem resolution rate, and efficiency indicators. The system parameters are updated based on the execution effect evaluation report to complete the closed-loop optimization. Specifically, the warning threshold and strategy rule base parameters are adjusted according to the evaluation results, the execution process data and effect data are stored in the historical database for model retraining, and the system parameter update confirmation information is output to complete the closed-loop management of this operation and maintenance.

10. A method for applying to the intelligent monitoring system of the primary and secondary integrated environmental protection ring network cabinet as described in any one of claims 1-9, characterized in that, Step S1: Collect multimodal monitoring data of the ring main unit to obtain the raw monitoring dataset; Step S2: Standardize the original monitoring dataset to obtain a standardized multimodal monitoring dataset; Step S3: Perform a condition assessment based on the standardized multimodal monitoring dataset to obtain the equipment condition monitoring assessment results; Step S4: Construct a digital twin model and perform digital twin analysis on the equipment status monitoring and evaluation results through the digital twin model to obtain health index and fault risk prediction results; Step S5: Generate a set of operation and maintenance strategies based on the health index and the fault risk prediction results; Step S6: Perform maintenance operations according to the set of maintenance strategies and record the maintenance execution results.

Images