An intelligent power distribution operation and maintenance management system based on 5G transmission

The intelligent power distribution operation and maintenance management system based on 5G transmission solves the problems of insufficient data collection, static topology management, and inaccurate maintenance strategies in traditional power distribution operation and maintenance management. It enables efficient and accurate equipment status monitoring and fault handling, improving the efficiency and reliability of operation and maintenance management.

CN120834647BActive Publication Date: 2025-12-09WENZHOU JIANLI ELECTRIC APPLIANCE CO LTD +1
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202511326057.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-09-17
Publication Date
2025-12-09
Estimated Expiration
2045-09-17

AI Technical Summary

Technical Problem

Traditional power distribution operation and maintenance management models cannot achieve high real-time data acquisition, multi-dimensional data fusion and analysis, dynamic topology management, and precise maintenance strategies, resulting in problems such as biased equipment status judgment, long fault diagnosis time, and high operation and maintenance costs.

Method used

The intelligent power distribution operation and maintenance management system based on 5G transmission acquires equipment status data through a 5G real-time acquisition module, integrates the data through a multi-dimensional feature fusion module, constructs an equipment association strength matrix through a dynamic topology generation module, identifies abnormal fluctuation paths through an anomaly propagation analysis module, and generates a maintenance strategy priority queue through a strategy optimization feedback module, thus forming a closed-loop operation and maintenance management process.

Benefits of technology

It enables high-speed, real-time status monitoring of power distribution equipment, accurately identifies abnormal propagation paths, optimizes maintenance strategies, reduces misjudgments and omissions, rationally allocates operation and maintenance resources, and ensures the stable operation of the power distribution network.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120834647B_ABST
    Figure CN120834647B_ABST
Patent Text Reader

Abstract

The application relates to the technical field of power distribution operation and maintenance management, and discloses an intelligent power distribution operation and maintenance management system based on 5G transmission. The system comprises a 5G real-time acquisition module, a multi-dimensional feature fusion module, a dynamic topology generation module, an abnormal propagation analysis module and a strategy optimization feedback module. The 5G real-time acquisition module obtains current-voltage waveform, equipment temperature sequence and environmental monitoring indexes and other operation state data streams of power distribution equipment through a 5G network; the multi-dimensional feature fusion module separates equipment state features, calculates mutual information and generates an equipment state feature tensor; the dynamic topology generation module constructs a correlation strength matrix according to the feature tensor, generates a hierarchical connection path and a dynamic equipment topology atlas; the abnormal propagation analysis module extracts a state fluctuation sequence, identifies an abnormal transmission path and marks a core propagation node; and the strategy optimization feedback module generates a maintenance strategy priority queue according to the above, feeds back execution results to update the dynamic topology atlas, and improves the intelligence and accuracy of power distribution operation and maintenance management.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power distribution operation and maintenance management, in particular to an intelligent power distribution operation and maintenance management system based on 5G transmission. BACKGROUND

[0002] In the process of power system operation, as the key link connecting the power generation side and the user side, the stable operation of the power distribution network is directly related to the reliability and safety of power supply. With the continuous growth of social electricity demand and the increasing proportion of new energy access, the structure of the power distribution network is becoming increasingly complex, the number of equipment is increasing significantly, and the traditional power distribution operation and maintenance management mode has gradually exposed many problems.

[0003] Under the traditional mode, the collection of the operation state of the power distribution equipment mainly depends on wired transmission mode or low-rate wireless transmission technology. The wired transmission mode not only has high construction cost and long construction period, but also is difficult to achieve full coverage in some complex terrains or old urban areas, resulting in that the equipment state data in some areas cannot be obtained in time. The low-rate wireless transmission technology is limited by bandwidth and cannot transmit large-capacity and high-real-time data such as current and voltage waveforms, so that the operation and maintenance personnel cannot accurately master the real-time operation status of the equipment. In addition, the traditional state monitoring usually only focuses on single-dimensional indicators, such as only monitoring the temperature or current of the equipment, ignoring the correlation between different dimensional data, and cannot fully reflect the overall operation state of the equipment, which is easy to cause misjudgment or omission.

[0004] In terms of power distribution network topology management, the traditional method usually adopts a fixed topology structure for management, which cannot be adjusted in real time according to the changes of the equipment operation state. When the equipment in the power distribution network has state fluctuations or faults, the fixed topology cannot quickly and accurately present the correlation between the equipment, so that the operation and maintenance personnel cannot timely identify the propagation path and core influence node of the fault, prolonging the time of fault troubleshooting and processing. At the same time, when formulating the equipment maintenance strategy, the traditional mode is mostly based on experience or fixed period, lacking dynamic evaluation of the real-time state and fault risk of the equipment, which is easy to cause problems of over-maintenance or insufficient maintenance. Over-maintenance will increase the operation and maintenance cost, while insufficient maintenance may cause frequent equipment failures, affecting the stable operation of the power distribution network.

[0005] With the development of the power system towards intelligence and digitization, the traditional power distribution operation and maintenance management mode cannot meet the needs of the new era, and an intelligent operation and maintenance management system capable of realizing high real-time data collection, multi-dimensional data fusion analysis, dynamic topology management and precise maintenance strategy formulation is urgently needed. SUMMARY

[0006] The purpose of the present application is to provide an intelligent power distribution operation and maintenance management system based on 5G transmission to solve the problems raised in the background.

[0007] To achieve the above object, the application provides an intelligent power distribution operation and maintenance management system based on 5G transmission, which comprises:

[0008] The 5G real-time acquisition module obtains the running state data stream of the power distribution equipment through the 5G network, wherein the running state data stream comprises current and voltage waveforms, equipment temperature sequences and environmental monitoring indexes;

[0009] The multi-dimensional feature fusion module separates the equipment state features of different dimensions based on the running state data stream, calculates the mutual information between the features of each dimension, and integrates to generate an equipment state feature tensor;

[0010] The dynamic topology generation module constructs the correlation strength matrix between the nodes of the power distribution equipment according to the equipment state feature tensor, generates the equipment hierarchical connection path according to the correlation strength threshold, and forms a dynamic equipment topology map;

[0011] The abnormal propagation analysis module extracts the state fluctuation sequence between the associated equipment nodes based on the dynamic equipment topology map, identifies the abnormal fluctuation transmission path and marks the core propagation node;

[0012] The strategy optimization feedback module generates a device maintenance strategy priority queue according to the core propagation node and its abnormal fluctuation transmission path, and updates the dynamic equipment topology map with the execution result as feedback input.

[0013] Preferably, the multi-dimensional feature fusion module comprises:

[0014] The spectral feature analysis submodule performs multi-scale decomposition on the current and voltage waveforms, extracts the energy distribution ratio of the fundamental frequency component and the harmonic component, and generates a current and voltage spectral feature vector;

[0015] The temperature trend modeling submodule divides the equipment temperature sequence into time windows, calculates the temperature change rate and extreme point position in each window, and outputs an equipment temperature trend feature vector;

[0016] The environmental correlation quantization submodule calculates the contribution weight of the environmental factor to the equipment state based on the time shift correlation between the environmental monitoring index and the equipment temperature sequence;

[0017] The feature tensor integration submodule concatenates the current and voltage spectral feature vector, the equipment temperature trend feature vector and the environmental factor contribution weight to output the equipment state feature tensor after normalization.

[0018] Preferably, the dynamic topology generation module comprises:

[0019] The correlation strength calculation sub-module calculates the cosine similarity and dynamic time warping distance of feature vectors of any two power distribution devices according to the device state feature tensor, and generates a device correlation strength value by weighting;

[0020] The path generation sub-module traverses all device correlation strength values, filters correlation strength values exceeding a preset threshold, and constructs a directed connection link between device nodes in descending order of strength values.

[0021] The topology iteration sub-module performs closed loop detection on the directed connection link, generates a hierarchical device connection path after eliminating redundant links, and outputs a node relationship matrix of the dynamic device topology map.

[0022] Preferably, the abnormal propagation analysis module comprises:

[0023] The fluctuation pattern extraction sub-module collects the state feature change amount of each device node in consecutive time slices based on the node relationship matrix of the dynamic device topology map, and marks the feature offset amount exceeding the normal fluctuation range;

[0024] The propagation path tracking sub-module traces back the abnormal fluctuation source node and records the transfer path node sequence according to the occurrence time sequence of the feature offset amount and the device connection path direction;

[0025] The core node identification sub-module counts the triggered frequency and path coverage of each node in the transfer path node sequence, and selects nodes with high frequency and coverage as core propagation nodes.

[0026] Preferably, the strategy optimization feedback module comprises:

[0027] The strategy priority generation sub-module calculates the device maintenance urgency score according to the device type of the core propagation node and the length of the abnormal fluctuation transfer path, and generates a maintenance strategy priority queue in descending order of the score;

[0028] The feedback mapping sub-module collects the device state feature tensor change amount after execution of the maintenance strategy, quantifies the abnormal fluctuation elimination rate, and maps it to the corresponding device node;

[0029] The topology update sub-module adjusts the correlation strength value between device nodes based on the abnormal fluctuation elimination rate, reconstructs the device connection path, and updates the dynamic device topology map.

[0030] Preferably, the system further comprises a fault prediction module:

[0031] The fault prediction module extracts the state feature decay trend of the key device node based on the updated dynamic device topology map, predicts the remaining effective operation time of the device, and outputs a life warning list.

[0032] Preferably, the system further comprises a multi-stage optimization module:

[0033] The multi-stage optimization module cross- validates the life warning list with a maintenance strategy priority queue, and marks a set of device nodes that need to be processed in priority;

[0034] The multi-stage optimization module corrects the decay rate calculation model of the device state feature tensor according to the maintenance records of the set of device nodes.

[0035] Preferably, the system further comprises a resource scheduling module:

[0036] The resource scheduling module generates an optimal path scheduling scheme based on the geographic location distribution of the devices in the maintenance strategy priority queue and in combination with the maintenance personnel location information.

[0037] Preferably, the system further comprises a digital twin mapping module:

[0038] The digital twin mapping module maps the dynamic device topology atlas and the real-time device state feature tensor to a three-dimensional power grid model to generate a power distribution device operating state heat map.

[0039] Preferably, the system further comprises a decision verification module:

[0040] The decision verification module compares the power distribution device operating state heat map with the historical operation and maintenance records, verifies the execution effectiveness of the maintenance strategy priority queue, and outputs a deviation report.

[0041] Compared with the prior art, the present application has the following advantages:

[0042] The intelligent power distribution operation and maintenance management system based on 5G transmission acquires the operating state data stream of the power distribution device through the 5G real-time acquisition module using the 5G network, including the current voltage waveform, device temperature sequence, and environmental monitoring indicators. The 5G network has the characteristics of high bandwidth, low latency, and wide connectivity, can break through the limitations of traditional transmission methods, realize high-speed and real-time acquisition of the operating state data of the power distribution device, and ensure that the operation and maintenance personnel can timely and accurately master the real-time operating conditions of the device, avoiding the deviation in the judgment of the device state caused by the untimely or incomplete data transmission.

[0043] The multi-dimensional feature fusion module separates device state features of different dimensions based on the obtained running state data stream and calculates mutual information between the dimensions to generate a device state feature tensor. This module breaks the limitations of traditional single-dimensional monitoring, fully considers the correlation between device state data of different dimensions, and through deep fusion analysis of multi-dimensional data, can more comprehensively and objectively reflect the overall running state of the device, allowing the operation and maintenance personnel to no longer be limited to single-index judgment, but to understand the device running condition from the overall level, reducing misjudgment or missed judgment caused by one-sided data, and providing a more comprehensive basis for subsequent device state evaluation and fault analysis.

[0044] The dynamic topology generation module constructs a correlation strength matrix between power distribution device nodes based on the device state feature tensor, generates a device hierarchical connection path based on a correlation strength threshold, and forms a dynamic device topology map. Unlike traditional fixed topology management methods, this module can adjust the topology structure in real time according to the changes in device running state, clearly presenting the correlation between devices as the state changes. When the device state fluctuates, the dynamic topology map can quickly reflect the changes in the correlation strength between device nodes, helping operation and maintenance personnel to intuitively understand the mutual influence between devices and laying the foundation for subsequent abnormal propagation analysis.

[0045] The abnormal propagation analysis module extracts the state fluctuation sequence between correlated device nodes based on the dynamic device topology map, identifies the abnormal fluctuation transmission path and marks the core propagation nodes. With the help of the device correlation relationship presented by the dynamic topology map, this module can accurately track the propagation trajectory of abnormal fluctuations in the power distribution network and accurately lock the core nodes that play a key role in abnormal propagation. Through the information obtained by this module, operation and maintenance personnel can quickly locate the abnormal root cause and impact range, avoiding blind searching during fault troubleshooting, and significantly shortening the preparation time for abnormal handling.

[0046] The strategy optimization feedback module generates a device maintenance strategy priority queue based on the core propagation nodes and their abnormal fluctuation transmission paths, and updates the dynamic device topology map with the execution results as feedback input. This module makes the formulation of device maintenance strategies no longer dependent on experience or fixed cycles, but based on real-time abnormal conditions and correlation of devices, achieving dynamic optimization of maintenance strategies. Through the generation of a priority queue, operation and maintenance personnel can clearly prioritize and sequence maintenance work, reasonably allocate operation and maintenance resources, avoid wasting resources on non-critical devices, and ensure timely maintenance of critical devices. In addition, feedback of maintenance execution results for updating the dynamic topology map can keep the topology map consistent with the actual running state and maintenance of the device, further improving the accuracy of subsequent topology analysis, abnormal identification, and maintenance strategy formulation, forming a closed-loop operation and maintenance management process, continuously improving the operation efficiency and reliability of the entire power distribution operation and maintenance management system, and ensuring the stable operation of the power distribution network. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 Timing diagram for the intelligent power distribution operation and maintenance management system based on 5G transmission described in the present application;

[0048] Figure 2 Flowchart for the workflow of the multi-dimensional feature fusion module;

[0049] Figure 3 Flowchart for the workflow of the abnormal propagation analysis module;

[0050] Figure 4 Flowchart for the workflow of the fault prediction module. DETAILED DESCRIPTION

[0051] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0052] Please refer to Figure 1 The present application provides an intelligent power distribution operation and maintenance management system based on 5G transmission, which comprises:

[0053] The running state data stream of the power distribution equipment is obtained by the 5G real-time acquisition module, including current and voltage waveform, equipment temperature sequence and environmental monitoring indicators. The multi-dimensional feature fusion module separates the device state features of different dimensions based on the running state data stream, calculates the mutual information between the features of each dimension, and integrates to generate a device state feature tensor. The dynamic topology generation module constructs the correlation strength matrix between the nodes of the power distribution equipment according to the device state feature tensor, generates the device hierarchical connection path according to the correlation strength threshold, and forms a dynamic device topology map. The abnormal propagation analysis module extracts the state fluctuation sequence between the associated device nodes based on the dynamic device topology map, identifies the abnormal fluctuation transmission path and marks the core propagation node. The strategy optimization feedback module generates a device maintenance strategy priority queue according to the core propagation node and its abnormal fluctuation transmission path, and updates the dynamic device topology map with the execution result as feedback input.

[0054] Embodiment 1: Please refer to Figure 2, the multi-dimensional feature fusion module processes the raw data stream from the 5G real-time acquisition module to convert it into normalized tensor data that can comprehensively represent the device state. The current and voltage waveforms received by the system are high-frequency sampled time series data that continuously enter at millisecond intervals. These waveform data are processed through multi-scale decomposition, and the wavelet transform method is used to decompose the signal into different frequency subbands. Each subband corresponds to a frequency range, and by calculating the energy proportion of each subband, a vector representing the fundamental frequency and harmonic distribution characteristics is formed. This vector can reflect the power quality condition and the degree of harmonic pollution, for example, a decrease in fundamental frequency energy proportion may indicate the presence of a nonlinear load, and an increase in a specific harmonic energy may point to a certain device fault.

[0055] The processing of the device temperature sequence uses a sliding time window mechanism, and the window length is dynamically adjusted according to the device type and operating history. For devices prone to overheating, a shorter window is used to capture rapid changes, while for devices with large thermal inertia, a longer analysis window is used. Within each window, the temperature change rate is calculated through the difference operation between adjacent sampling points, and the local extreme point position is detected. These features together form a temperature trend feature vector that can reflect the heating law and heat dissipation characteristics of the device. For example, a continuously rising temperature change rate may indicate insulation aging, and an abnormal temperature extreme value distribution may indicate a local overheating problem.

[0056] The environmental monitoring indicators include humidity, dust concentration, and wind speed, among other multi-dimensional parameters. These parameters have complex relationships with the device temperature sequence. By calculating the time-shift mutual information between environmental indicators and temperature data, the influence degree and lag effect of different environmental factors on the device temperature are quantified. For example, humidity changes may not have a significant impact on the device temperature until several hours later, and this time-shift characteristic is captured through mutual information calculation. The contribution weight calculation uses a multivariate regression analysis method to determine the influence weight of each environmental factor on the device state, forming an environmental correlation feature vector.

[0057] The feature tensor integration process multi-dimensionally splices the above three feature vectors. The current and voltage frequency spectrum feature vector contains the energy distribution information of multiple frequency components, the device temperature trend feature vector contains the change rate and extreme point features, and the environmental factor contribution weight vector represents the influence degree of the external environment. The multi-dimensional array after splicing is normalized, and the min-max scaling method is used to map each feature dimension to a unified numerical range, eliminating the magnitude difference caused by different physical dimensions. The final output device state feature tensor is a structured multi-dimensional data object that can simultaneously reflect the electrical characteristics, thermodynamic characteristics, and environmental correlation characteristics of the device. This tensor serves as a unified device state representation, providing standardized input for subsequent topology construction and anomaly analysis.

[0058] The whole processing adopts a pipeline architecture, and each sub-module is executed sequentially but supports parallel processing. The spectrum feature analysis sub-module deploys a special hardware acceleration wavelet transform calculation for digital signal processing. The temperature trend modeling sub-module uses a sliding window caching mechanism to realize real-time temperature feature extraction. The environmental correlation quantization sub-module maintains a time series database to store historical environmental data for time shift correlation calculation. The feature tensor integration sub-module realizes the alignment and splicing of feature vectors, ensuring that the features from different sources are strictly synchronized in time stamp.

[0059] When the system is running, the multi-dimensional feature fusion module continuously receives real-time data streams transmitted by the 5G network, and outputs device state feature tensors at fixed time intervals. Each output tensor is accompanied by complete timestamp information and device identification information, ensuring that the data source can be accurately traced back in subsequent processing steps. The tensor data structure design supports flexible expansion, and can accommodate new feature dimensions without changing the overall framework. This implementation enables the system to adapt to different sizes and types of power distribution networks, providing a unified and comprehensive device state representation basis for intelligent operation and maintenance management.

[0060] Embodiment 2: see Figure 3 The implementation process of the dynamic topology generation module starts with the input of the device state feature tensor. This module processes structured tensor data output from the multi-dimensional feature fusion module, which contains standardized state features of all devices in the power distribution network. The correlation strength calculation sub-module extracts the corresponding feature vectors for each pair of power distribution device nodes for similarity analysis. Cosine similarity calculation is used to evaluate the similarity of feature vectors in spatial distribution, reflecting the static correlation characteristics of device state. At the same time, dynamic time warping distance calculation is used to measure the similarity of device state change patterns in the time dimension. This calculation can handle the time offset problem that may exist between different devices. The two measurement results are fused through a pre-set weighting coefficient to generate a comprehensive device correlation strength value. For example, when two transformers show harmonic feature growth patterns in the same time interval and the temperature change curves are highly consistent, they will get a higher correlation strength score.

[0061] The path generation sub-module receives the correlation strength calculation results of all device pairs, and the system pre-sets a dynamically adjusted strength threshold for screening significant correlation relationships. This threshold is determined based on historical operation data statistical analysis. Device correlation relationships that exceed the threshold are retained and sorted from high to low according to the strength value. Each valid correlation relationship is converted into a directed connection link, and the link direction is determined by the time sequence of state changes. For example, when the voltage fluctuation of substation A always appears before the current anomaly of power distribution cabinet B, the system establishes a directed link from A to B. These links constitute the initial framework of the device correlation network.

[0062] The topology iteration submodule processes the initial link set in a structured manner. First, the submodule detects closed-loop structures in the network, such as when a loop path of A→B→C→A occurs, the system identifies the closed loop and removes the least strong redundant link. Then, the minimum spanning tree algorithm is applied to delete secondary connections while ensuring network connectivity, forming a loop-free tree structure. Finally, the device nodes are hierarchically divided according to the correlation strength value, with high strength devices located in the upper layer nodes. For example, regional substations are placed at the top of the topology due to their wide influence range, and end distribution boxes are placed at the bottom. After processing, the node relationship matrix is output, which clearly records the hierarchical position of each device node and its upstream and downstream connection relationships.

[0063] The abnormal propagation analysis module works based on the dynamic device topology map, and the fluctuation pattern extraction submodule continuously monitors the state feature changes of each device node. The system sets a normal fluctuation range for each feature dimension, which is obtained by analyzing historical device operation data. When a feature value of a device node exceeds the normal range in consecutive time slices, it is marked as a feature offset. For example, if the temperature feature of a switch cabinet is continuously higher than the historical mean value by three standard deviations for three consecutive 5-minute time slices, it is identified as an effective offset event.

[0064] The propagation path tracking submodule is started immediately after detecting a feature offset event. The submodule first determines the time point of the offset event, and then reverses the trace according to the directed connection direction in the topology map. The system traces back to the upstream nodes along the device connection path and checks the state records of each upstream node in earlier time slices. When a certain upstream node is found to have the same type of feature offset and the occurrence time is earlier than the current node, it is marked as a potential source. For example, when the current of distribution transformer B appears harmonic offset, the system traces back and finds that the upstream substation A has a similar offset 15 minutes ago, then judges A as the abnormal source, and records the transmission path as A→B.

[0065] The core node identification submodule statistically analyzes the historical propagation path data. The system maintains all identified abnormal propagation path records, and calculates the frequency of each node appearing in the propagation path. At the same time, the path coverage index of each node is calculated, which reflects the degree of the node as a hub in the abnormal propagation network. For example, a regional tie switch appears in 32 abnormal propagation paths in three months, and its downstream influence range covers 15% of the device nodes in the network. The system sets a frequency threshold and a coverage threshold, and marks a node as a core propagation node when it exceeds both thresholds. These core nodes usually correspond to key connection points or weak devices in the power distribution network.

[0066] The dynamic topology generation task is executed by a dedicated graph computing engine, and the anomaly propagation analysis is implemented in real time using a stream processing framework. The system maintains a state feature sliding window memory for each device node to ensure quick access to historical state data. The node relationship matrix and anomaly propagation records are stored in a time series database, supporting efficient time range queries and pattern analysis operations. This implementation enables the system to adapt to real-time analysis requirements of large-scale power distribution networks, providing dynamic updated network relationship models and anomaly propagation features for operational decision-making.

[0067] Embodiment 3: Refer to Figure 4 The implementation process of the strategy optimization feedback module is based on the core propagation nodes and their abnormal fluctuation transmission paths output by the anomaly propagation analysis module. The strategy priority generation submodule first classifies each core propagation node by device type, with different types of devices having different fault impact coefficients. At the same time, the length of each abnormal fluctuation transmission path is calculated, i.e., the number of device nodes passed through from the source node to the terminal node. The device maintenance urgency score is calculated by the following formula:

[0068]

[0069] wherein: represents the maintenance urgency score of the i-th core propagation node, represents the device type weight coefficient, represents the abnormal fluctuation transmission path length, represents the abnormal trigger frequency of the node within the statistical period, , , are the adjustment coefficients of each parameter, respectively. After the score calculation is completed, the system sorts the maintenance strategy priority queue from high to low according to the score value. This queue not only contains the device identifier and priority order, but also records the abnormal type and maintenance suggestion corresponding to each device.

[0070] The feedback mapping submodule starts working after the maintenance strategy is executed. This submodule continuously collects the state feature tensor of the device after maintenance and compares it with the baseline tensor before maintenance. The system calculates the change in each feature dimension, with special attention to the feature dimensions that previously exhibited abnormal fluctuations. The abnormal fluctuation elimination rate is calculated using the reduction ratio of feature offset, and this elimination rate is mapped to the corresponding device node, with the timestamp and specific content of the maintenance operation recorded.

[0071] The topology update submodule adjusts the device association relationship based on the feedback mapping results. According to the size of the abnormal fluctuation elimination rate, the system adjusts the association strength value between the device node and the adjacent nodes in proportion. The association strength of the device node with the upstream nodes is correspondingly weakened for high elimination rate devices, indicating that maintenance effectively reduces the risk of abnormal propagation. The association strength adjustment formula is: wherein represents the updated correlation strength, represents the original correlation strength, represents the abnormal fluctuation elimination rate, is an adjustment factor. After the strength value is updated, the system re-executes the generation process of the device connection path, and reconstructs the entire dynamic device topology map.

[0072] The fault prediction module works based on the updated topology map. The module first identifies the key device nodes in the network, and the selection criteria include the centrality position of the node in the topology, the historical abnormal frequency, and the maintenance record. For each key node, the system extracts the time series data of its state feature tensor, and analyzes the change trend of each feature dimension. In particular, for features sensitive to device life, such as the temperature cumulative effect of insulating materials and the operation frequency record of mechanical parts, a time series fitting method is used to establish a decay model. The prediction of the remaining effective operation time of the device is based on the time point when the feature value reaches the preset failure threshold, while considering the influence of the device operating environment and load conditions. The final output life warning list includes device identification, predicted failure time, confidence assessment, and a list of key decay features.

[0073] During the implementation of the system, the strategy optimization feedback module and the fault prediction module form a closed-loop cooperation. After each maintenance strategy is executed, the feedback data is not only used to update the topology relationship, but also used to calibrate the fault prediction model. The life warning list and the maintenance strategy priority queue are cross-verified, and when a device appears in both the high-priority maintenance queue and the short-term life warning list, the system will increase the maintenance urgency. All maintenance records and prediction results are stored in the historical database to optimize the device state feature decay rate calculation model and continuously improve the prediction accuracy.

[0074] The entire implementation architecture adopts micro-service design, and the strategy optimization feedback module and the fault prediction module run as independent services and exchange data through a message queue. The maintenance strategy priority queue is pushed to the operation and maintenance management platform, and the life warning list is sent to the scheduling system at the same time. The system establishes a digital archive for each device, complete records of its state feature history, maintenance records, and prediction data, providing technical support for the whole life cycle management of power distribution equipment.

[0075] Example 4: The multi-stage optimization module receives the life warning list from the failure prediction module and the maintenance strategy priority queue from the strategy optimization feedback module. This module establishes a device cross-analysis matrix to match the device identifications in the two lists. For device nodes that exist in both lists, the system extracts their maintenance urgency scores and predicted remaining life data, and sets double judgment conditions for emergency labeling. When a device simultaneously meets the conditions of a maintenance score higher than the threshold S_th and a remaining life lower than the threshold T_risk, it is labeled as a red emergency state; when only one condition is met, it is labeled as a yellow attention state. For example, a certain 110 kV oil-immersed transformer has a score of 92 points (out of 100) in the priority queue, and the life warning shows that the remaining operating time is only 45 days, so the system classifies it as a red emergency device. The final generated device node set that needs to be processed first contains device identification, emergency level, and recommended processing time window.

[0076] Table 1: Device node emergency labeling logic comparison table.

[0077]

[0078] This module synchronously accesses the device maintenance history database to extract the complete maintenance records of the labeled devices. Each record contains fields such as maintenance time, operation type, replacement parts, and comparison of feature values before and after maintenance. The system establishes a feature degradation model for each type of device, such as for the spring fatigue feature of a circuit breaker mechanism, the model contains the corresponding relationship between operation times and spring pressure degradation. When a new maintenance record is stored, the system compares the actual maintenance effect of the device with the predicted value of the model. The actual improvement rate of the contact wear feature value of a certain vacuum circuit breaker after maintenance is 78%, while the model predicts a value of 85%, so the system starts the model parameter calibration program. The increment learning mechanism is used for degradation rate correction, based on the gradient of the feature tensor before and after maintenance, the feature degradation coefficient of this type of device is dynamically adjusted. The corrected model will be applied to the life prediction calculation of subsequent devices of the same type.

[0079] The resource scheduling module works based on the priority processing device node set. This module connects the device asset management system to obtain device geographic information data, including substation coordinates, distribution room locations, tower GPS points, etc. At the same time, it accesses the real-time positioning data of the mobile terminal of the operation and maintenance personnel, and obtains personnel skill qualification information. The system establishes a device-personnel matching matrix, first filters maintenance teams with the qualifications to handle device failures, and then calculates the optimal path from the current location of each team to the set of devices to be processed.

[0080] The path planning uses an improved ant colony algorithm, considering the following constraints: device handling emergency level (red devices need to be prioritized), device geographic location distribution density (regional concentrated device batch processing), personnel skill matching degree (expert device priority allocation), and estimated single-point operation time. The system optimizes the calculation with the dual goals of the shortest total distance and the highest emergency device coverage rate. For example, a certain dispatch involves 17 devices (including 3 red emergency devices) distributed within an 8-kilometer radius. The system generates inspection paths for two maintenance teams:

[0081] Team A path: current personnel location → red device S-101 (3.2 km away) → yellow device D-205 (1.8 km away) → red device T-307 (4.1 km away)

[0082] Team B path: current personnel location → red device R-208 (2.7 km away) → concentrated device group {D-211, D-215, D-219} (500m radius area) → yellow device S-104 (3.3 km away)

[0083] The generated dispatch plan includes detailed navigation paths, estimated arrival times, operation time budgets, and device handling sequences. The plan is pushed to maintenance personnel through a mobile app and real-time monitoring of execution progress. When personnel arrive at the device location, the system automatically records the actual arrival time; when the device status returns to normal, the maintenance personnel feed back the completion information through the APP. These execution data are fed back to the multi-stage optimization module for verifying the accuracy of the device emergency level marking and serving as a reference for subsequent maintenance strategy adjustment.

[0084] The entire implementation process uses a distributed architecture, with the multi-stage optimization module running on a data analysis server and the resource scheduling module deployed on a cloud computing platform. The device node set update trigger mechanism is set to automatically execute every hour, and real-time scheduling is triggered immediately when an emergency red device is found. The system maintains a spatiotemporal database of device geographic information, recording device location change history; personnel location data are updated every 30 seconds to ensure the timeliness of the dispatch plan. The dispatch plan generation engine has a timeout control mechanism, which automatically outputs the current optimal solution when the calculation exceeds the preset time, ensuring the timeliness of operation and maintenance response.

[0085] Example 5: The implementation of the digital twin mapping module is based on dynamic device topology maps and real-time device state feature tensors. This module first imports a three-dimensional geographic information system model of the power distribution network, which includes detailed three-dimensional models of substation buildings, power distribution rooms, power transmission line corridors, and tower devices. Each three-dimensional model object has a unique device identification code, which is mapped to the device information in the real-time database. The system uses coordinate transformation algorithms to accurately match device logical nodes with three-dimensional space entities, ensuring the positional consistency of virtual models and physical devices.

[0086] Each dimension data in the device state feature tensor is mapped to different visualization channels of the three-dimensional model. The current-voltage spectrum feature is presented by the color temperature change of the device shell, with cold tones for normal states and warm tones for abnormal states according to severity. The temperature trend feature uses heat map rendering technology to generate a temperature distribution gradient on the device surface, with red gradient for high temperature areas and blue gradient for low temperature areas. Environmental monitoring indicators are visualized through environmental special effects, such as humidity indicators presented by spatial fog density and dust concentration displayed through particle effects. These visualization effects together form the power distribution equipment operation state heat map, allowing operators to intuitively understand the overall network equipment operation status through a three-dimensional perspective.

[0087] The decision verification module runs continuously in the background, comparing the real-time generated heat map with the historical operation and maintenance record database. The historical database stores panoramic snapshots of all previous maintenance events, including the device state heat map before maintenance, the maintenance measures taken, and the state changes after maintenance. The system uses image feature comparison algorithms to extract the feature vector of the abnormal area in the current heat map and match the similarity with the abnormal patterns in the historical records. When a high similarity is found between the current abnormal pattern and a historical event, the system automatically retrieves the handling records and effect evaluation data of that event.

[0088] The effectiveness verification of the maintenance strategy priority queue is achieved through time series comparison. The system records the strategy execution time point, intercepts the heat map data in a specific time window before and after execution, and calculates quantitative indicators such as the area change rate of the abnormal area and the color intensity change value. For example, after a maintenance operation on an overloaded transformer, the system detects that the red area of the device in the heat map has decreased by 62%, and the color intensity has decreased from the highest warning level to the normal range. At the same time, it analyzes the state transmission on the associated line of the device and confirms that the abnormal fluctuations have not spread to upstream and downstream devices.

[0089] The deviation report generation mechanism is based on multi-dimensional data analysis. The system compares the differences between the expected effect and the actual effect of the maintenance strategy, identifying three types: significant effect, general effect, and poor effect. For operations with significant effect, the system records the feature pattern of the maintenance measure and stores it in the best practice library. For operations with poor effect, it analyzes possible reasons such as maintenance timing delay, incomplete measures, and unsynchronized handling of associated devices. The report output uses a structured format, including deviation description, possible cause analysis, and improvement suggestions. Each report is associated with a specific device identifier and maintenance event number, supporting historical tracing and effect review.

[0090] The system establishes a digital twin model updating mechanism during implementation. When the physical equipment changes, such as equipment replacement and line reconstruction, the three-dimensional model is updated synchronously. Real-time data stream processing adopts a distributed architecture to ensure high-concurrency visualization rendering of large-scale equipment state data. Historical data retrieval optimizes the index structure of the time series database to support fast query comparison. The visualization effect configuration adopts parameterized design, allowing users to adjust the display weight and presentation of different features according to their focus.

[0091] The entire digital twin system supports multi-dimensional perspective viewing, and operators can freely switch between global overview, regional focus, and single-device detailed observation modes. The system records user operation logs and analysis paths to provide data support for subsequent optimization of human-computer interaction experience. All visualization effects are based on physically accurate rendering technology to ensure that color, shape, and location visual elements accurately reflect the actual state of the equipment, providing intuitive and reliable visual evidence for operation and maintenance decisions.

[0092] It should be noted that, in this text, relational terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply any actual such relationship or order between the entities or operations. Moreover, the terms "include", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or device.

[0093] Although embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A smart power distribution operation and maintenance management system based on 5G transmission, characterized in that, The system includes: The 5G real-time acquisition module acquires the operating status data stream of the power distribution equipment through the 5G network. The operating status data stream includes current and voltage waveforms, equipment temperature sequences, and environmental monitoring indicators. Based on the operating status data stream, the multi-dimensional feature fusion module separates the device status features of different dimensions, calculates the mutual information between the features of each dimension, and integrates them to generate a device status feature tensor. The dynamic topology generation module constructs an association strength matrix between power distribution equipment nodes based on the equipment state feature tensor, and generates equipment hierarchical connection paths according to the association strength threshold to form a dynamic equipment topology map. Based on the dynamic device topology map, the anomaly propagation analysis module extracts the state fluctuation sequence between related device nodes, identifies the anomaly propagation path, and marks the core propagation nodes. The strategy optimization feedback module generates a device maintenance strategy priority queue based on the core propagation node and its abnormal fluctuation transmission path, and uses the execution result as feedback input to update the dynamic device topology map; The strategy optimization feedback module includes: The strategy priority generation submodule calculates the equipment maintenance urgency score based on the device type and abnormal fluctuation transmission path length of the core propagation node, and generates an equipment maintenance strategy priority queue according to the score. The feedback mapping submodule collects the changes in the equipment status feature tensor after the execution of the maintenance strategy, quantifies the abnormal fluctuation elimination rate, and maps it to the corresponding equipment node. The topology update submodule adjusts the correlation strength values ​​between device nodes based on the abnormal fluctuation elimination rate, reconstructs the device connection paths, and then updates the dynamic device topology map. The equipment maintenance urgency score is calculated using the following formula: in: This represents the maintenance urgency score of the i-th core propagation node. This indicates the weighting coefficient for the equipment type. Indicates the length of the abnormal fluctuation propagation path. This indicates the frequency of anomaly triggers for that node within the statistical period. , , These are the adjustment coefficients for each parameter.

2. The intelligent power distribution operation and maintenance management system based on 5G transmission according to claim 1, characterized in that, The multi-dimensional feature fusion module includes: The spectrum feature analysis submodule performs multi-scale decomposition on the current and voltage waveforms, extracts the energy distribution ratio of the fundamental frequency component and harmonic components, and generates a current and voltage spectrum feature vector. The temperature trend modeling submodule divides the equipment temperature sequence into time windows, calculates the temperature change rate and extreme point location within each window, and outputs the equipment temperature trend feature vector. The environmental correlation quantification submodule calculates the contribution weight of environmental factors to the equipment status based on the time-shift correlation between the environmental monitoring indicators and the equipment temperature sequence. The feature tensor integration submodule concatenates the current and voltage spectrum feature vectors, the equipment temperature trend feature vectors, and the environmental factor contribution weights into tensors, and outputs the equipment state feature tensor after normalization.

3. The intelligent power distribution operation and maintenance management system based on 5G transmission according to claim 2, characterized in that, The dynamic topology generation module includes: The association strength calculation submodule calculates the cosine similarity and dynamic time warping distance of the feature vectors of any two power distribution devices based on the device state feature tensor, and generates a weighted device association strength value. The path generation submodule iterates through all device association strength values, filters association strength values ​​that exceed a preset threshold, and constructs directed connection links between device nodes in descending order of strength value; The topology iteration submodule performs closed-loop detection on the directed connection links, eliminates redundant links, generates hierarchical device connection paths, and outputs a node relationship matrix of the dynamic device topology graph.

4. The intelligent power distribution operation and maintenance management system based on 5G transmission according to claim 3, characterized in that, The anomaly propagation analysis module includes: The fluctuation pattern extraction submodule collects the state feature changes of each device node in continuous time slices based on the node relationship matrix of the dynamic device topology map, and marks the feature offsets that exceed the normal fluctuation range. The propagation path tracing submodule traces back the source node of the abnormal fluctuation and records the sequence of nodes along the propagation path based on the occurrence sequence of the feature offset and the direction of the device connection path. The core node identification submodule counts the trigger frequency and path coverage of each node in the transmission path node sequence, and selects nodes with both high frequency and high coverage as core propagation nodes.

5. The intelligent power distribution operation and maintenance management system based on 5G transmission according to claim 1, characterized in that, The system also includes a fault prediction module: The fault prediction module extracts the state feature decay trend of key equipment nodes based on the updated dynamic equipment topology map, predicts the remaining effective running time of the equipment, and outputs a lifespan warning list.

6. The intelligent power distribution operation and maintenance management system based on 5G transmission according to claim 5, characterized in that, The system also includes a multi-stage optimization module: The multi-stage optimization module cross-validates the lifespan warning list with the equipment maintenance strategy priority queue and marks the set of equipment nodes that need to be prioritized. The multi-stage optimization module corrects the decay rate calculation model of the device state feature tensor based on the maintenance records of the device node set.

7. The intelligent power distribution operation and maintenance management system based on 5G transmission according to claim 6, characterized in that, The system also includes a resource scheduling module: The resource scheduling module generates the optimal path scheduling scheme based on the geographical distribution of equipment in the equipment maintenance strategy priority queue and the location information of maintenance personnel.

8. The intelligent power distribution operation and maintenance management system based on 5G transmission according to claim 7, characterized in that, The system also includes a digital twin mapping module: The digital twin mapping module maps the dynamic equipment topology map and the real-time equipment state feature tensor to the three-dimensional power grid model, generating a heat map of the power distribution equipment's operating status.

9. The intelligent power distribution operation and maintenance management system based on 5G transmission according to claim 8, characterized in that, The system also includes a decision verification module: The decision verification module compares the heat map of the power distribution equipment's operating status with historical operation and maintenance records to verify the effectiveness of the equipment maintenance strategy priority queue and outputs a deviation report.

Citation Information

Patent Citations

  • Intelligent exploratory data mining system

    CN120542437A

  • Dynamic electric power question answering system optimization method and system based on knowledge graph

    CN120632043A