A method, system, device, equipment, medium, and product for protecting power transmission lines.

By collecting multi-dimensional status data, performing pre-processing and weighted fusion, and constructing a digital twin model for simulation analysis, the problems of single monitoring dimensions and insufficient fusion of multi-source data for transmission lines are solved, realizing intelligent proactive protection and efficient operation and maintenance of transmission lines.

CN123070925APending Publication Date: 2026-11-10STEJT GRID ELEKTRIK PAUER INZHINIRING RISERCH INSTITYUT KO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611245625.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-08-17
Publication Date
2026-11-10

AI Technical Summary

Technical Problem

Existing transmission line monitoring methods suffer from limitations such as single monitoring dimensions, insufficient multi-source data fusion and analysis capabilities, and a lack of proactive protection measures, leading to the easy omission of potential risks and low operation and maintenance efficiency.

Method used

Collect multi-dimensional status data, perform data preprocessing and multi-dimensional weighted fusion, construct a digital twin model for simulation analysis, generate a health score, and trigger proactive protective actions based on the assessment and diagnosis results.

Benefits of technology

It has achieved a leap from single-point monitoring to multi-dimensional comprehensive diagnosis, improved the safety operation level and maintenance efficiency of transmission lines, and formed an intelligent active protection closed loop throughout the entire life cycle.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123070925A_ABST
    Figure CN123070925A_ABST
Patent Text Reader

Abstract

This invention relates to the field of power system operation and maintenance and intelligent protection technology, and discloses a method, system, device, equipment, medium, and product for transmission line protection. The method includes: collecting multi-dimensional status data and performing pre-processing to obtain data to be processed; performing multi-dimensional weighted fusion to obtain fused features; constructing a digital twin model to perform comprehensive diagnostic analysis of the fused features, obtaining evaluation and diagnostic results information, and triggering active protection actions. This invention achieves unified representation and quality improvement through multi-dimensional data pre-processing and weighted fusion, and combines digital twin model for comprehensive diagnostic analysis of fused features to achieve multi-dimensional evaluation and fault identification of transmission line operating status, triggering active protection actions to complete autonomous hazard handling, forming a fully intelligent closed loop, and improving the safe operation level and maintenance efficiency of transmission lines.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of power system operation and maintenance and intelligent protection technology, specifically to a method, system, device, equipment, medium and product for the protection of transmission lines. Background Technology

[0002] Currently, power transmission lines are the key channels for power transmission, and their operational reliability directly affects the safety and stability of the power grid. With the continuous expansion of the power grid in recent years, a large number of transmission lines have been erected in complex terrain areas. The traditional manual inspection mode can no longer meet the needs of operation and maintenance. The development of Internet of Things, big data and artificial intelligence technologies has promoted the evolution of power transmission line protection from manual inspection to online monitoring, and from passive emergency repair to proactive early warning. However, the overall level of intelligence is still in its initial stage. A full-process intelligent system covering data collection, processing, diagnosis to proactive protection has not yet been formed. There are problems such as single monitoring dimensions, insufficient multi-source data fusion capabilities, and insufficient data processing and intelligent diagnosis capabilities.

[0003] Existing monitoring methods mostly focus on the collection and analysis of electrical parameters, with insufficient coverage of key status parameters such as conductor temperature, environmental forces (e.g., tree obstructions, construction machinery intrusion), and tower structural deformation. There is a lack of a unified data structure and fusion analysis mechanism among various monitoring data, making it difficult to comprehensively reflect the true operating status of the lines and leading to the easy omission of potential risks. Furthermore, a large amount of raw monitoring data is directly transmitted to the cloud, consuming high communication bandwidth. The edge side lacks effective data preprocessing mechanisms, and the ability to identify and correct abnormal data is insufficient. Real-time simulation and prediction capabilities are lacking in the fault diagnosis stage. Protection execution still relies primarily on reactive repairs after a fault occurs, lacking proactive prediction and rapid response measures. Operation and maintenance management largely depends on manual experience, resource allocation is not reasonable, and overall operation and maintenance efficiency is low. Summary of the Invention

[0004] This invention provides a method, system, device, equipment, medium, and product for the protection of power transmission lines, in order to solve the problems of single monitoring dimensions, insufficient multi-source data fusion and analysis capabilities, insufficient processing and intelligent diagnostic capabilities, and lack of active protection measures in existing power transmission line protection technologies.

[0005] In a first aspect, the present invention provides a method for protecting power transmission lines, comprising: Collect multi-dimensional status data and perform pre-processing on the multi-dimensional status data to obtain the data to be processed; The data to be processed is weighted and fused from multiple dimensions to obtain fused features; Based on the 3D point cloud data and design drawings of the transmission line, a geometric model is constructed; based on the material parameters and physical properties of the transmission line, a physical model is constructed; the geometric model and the physical model are merged, and a digital twin model is constructed based on the pre-acquired real-time monitoring data and the merged model. A health score is generated by simulating and analyzing the fused features using a digital twin model; the correlation between multi-dimensional feature vectors in the fused features is quantitatively analyzed to generate multi-parameter coupled correlation information; and the health score and multi-parameter coupled correlation information are used as assessment and diagnostic results information. Active protective actions are triggered based on the assessment and diagnosis results. These actions include at least one of the following: remotely clearing tree obstructions and foreign objects along the transmission line and non-contact removal of unauthorized personnel and animals along the transmission line.

[0006] This embodiment provides a transmission line protection method that collects multi-dimensional status data and performs pre-processing. It utilizes neighbor node correlation correction to eliminate single-sensor measurement errors, ensuring data accuracy and consistency. Through multi-dimensional weighted fusion, it unifies electrical operating parameters, conductor temperature distribution data, environmental and external force risk data, and tower structural status data into a unified fusion feature, overcoming the limitations of single-dimensional monitoring. A digital twin model is constructed to simulate and quantify the fusion features, obtaining assessment and diagnostic results. This achieves a leap from single-point monitoring to multi-dimensional comprehensive diagnosis of transmission line operating status. Based on the assessment and diagnostic results, it triggers active protection actions, forming a closed loop from data collection and fusion analysis to active protection. This enables intelligent active protection throughout the entire lifecycle of the transmission line, improving its safety operation level and maintenance efficiency.

[0007] As a preferred embodiment of the transmission line protection method of the present invention, the preprocessing of multi-dimensional state data includes: Anomalies are identified and removed from multi-dimensional state data to obtain cleaned state data. Obtain concurrent status data from similar acquisition nodes adjacent to the current acquisition node, and calculate correction coefficients based on the multidimensional correlation characteristics between the cleaned status data and the concurrent status data. Based on the correction coefficient, the neighbor node correlation of the cleaning status data is corrected using the correction formula to obtain the corrected status data. The corrected state data is normalized to obtain standardized feature data.

[0008] The beneficial effects of this preferred technical solution are as follows: by identifying and eliminating anomalies in multi-dimensional status data, and by using the synchronous data of adjacent similar acquisition nodes to calculate correction coefficients for neighboring node correlation correction, the measurement errors caused by environmental interference or equipment deviation of a single sensor are eliminated. Standardized feature data are obtained through normalization processing, providing an accurate data foundation for subsequent multi-dimensional weighted fusion and comprehensive diagnostic analysis, thereby improving the accuracy of transmission line status assessment.

[0009] As a preferred embodiment of the transmission line protection method of the present invention, the preprocessing of multi-dimensional state data further includes: The standardized feature data is subjected to multi-index complexity quantification to obtain a complexity score; Monitor resource usage status and generate current available computing power information; Obtain the transmission quality parameters of the communication network to get the current network status information; Based on the complexity score, current available computing power, and current network status, an offloading decision is made to obtain the data to be processed.

[0010] The beneficial effects of this preferred technical solution are as follows: by performing complex multi-index quantification on standardized feature data and combining resource occupancy status with network transmission quality parameters to comprehensively execute offloading decisions, communication bandwidth consumption and cloud computing pressure are reduced, the processing efficiency and response speed of the entire transmission line protection method are improved, and reliable data support is provided for subsequent comprehensive diagnostic analysis.

[0011] As a preferred embodiment of the transmission line protection method of the present invention, the data to be processed is subjected to multi-dimensional weighted fusion to obtain fused features, including: Extract multi-dimensional feature vectors from the data to be processed; The multi-dimensional feature vectors are weighted and fused to obtain the fused features.

[0012] The beneficial effects of this preferred technical solution are as follows: by extracting multi-dimensional feature vectors from the data to be processed and performing weighted fusion, the data is uniformly represented as fused features, retaining the key information of each dimension, overcoming the limitations of single-dimensional monitoring, improving the comprehensiveness and accuracy of data representation, and enhancing the reliability of transmission line operation status assessment and the accuracy of fault diagnosis.

[0013] In a second aspect, the present invention provides a transmission line protection system, applied to a transmission line protection method according to the first aspect or any corresponding embodiment thereof, the system comprising: The data acquisition unit is installed on the transmission line side to collect multi-dimensional status data of the transmission line; Edge computing nodes, connected to data collectors, are used to perform pre-processing on multi-dimensional state data to obtain data to be processed. The cloud server communicates and connects with the edge computing nodes to perform multi-dimensional weighted fusion of the data to be processed to obtain fused features; a digital twin model is constructed, and the fused features are comprehensively diagnosed and analyzed through the digital twin model to obtain evaluation and diagnostic results information; The implementing agency is used to trigger proactive protective actions based on assessment and diagnostic results.

[0014] Thirdly, the present invention provides a power transmission line protection device, the device comprising: The multi-dimensional status acquisition module is used to collect multi-dimensional status data of transmission lines; The edge preprocessing module is used to perform preprocessing on multi-dimensional state data to obtain the data to be processed; The feature fusion module is used to perform multi-dimensional weighted fusion of the data to be processed to obtain fused features; The diagnostic analysis module is used to build a digital twin model, and to perform comprehensive diagnostic analysis on the fused features through the digital twin model to obtain evaluation and diagnostic results information; The active protection module is used to trigger active protection actions based on assessment and diagnostic results.

[0015] Fourthly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform a power transmission line protection method according to the first aspect or any corresponding embodiment described above.

[0016] Fifthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute a transmission line protection method according to the first aspect or any corresponding embodiment described above.

[0017] In a sixth aspect, the present invention provides a computer program product, including computer instructions for causing a computer to execute a transmission line protection method according to the first aspect or any corresponding embodiment described above. Attached Figure Description

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of a power transmission line protection system according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first process of a power transmission line protection method according to an embodiment of the present invention; Figure 3 This is a second flowchart illustrating a transmission line protection method according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the third process of a power transmission line protection method according to an embodiment of the present invention; Figure 5 This is a structural block diagram of a power transmission line protection device according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0022] As an optional application scenario of this invention, such as Figure 1 As shown, this invention provides a power transmission line protection system, which includes: Data acquisition unit 101 is installed on the transmission line side and is used to collect multi-dimensional status data of the transmission line; Edge computing node 102 is connected to the data collector and is used to perform pre-processing of multi-dimensional state data to obtain data to be processed. The cloud server 103 communicates with the edge computing nodes to perform multi-dimensional weighted fusion of the data to be processed to obtain fusion features; it constructs a digital twin model and uses the digital twin model to perform comprehensive diagnostic analysis on the fusion features to obtain evaluation and diagnostic results information. The actuator 104 is used to trigger active protection actions based on the assessment and diagnosis results.

[0023] The data acquisition unit 101 includes a current transformer, a voltage transformer, a fiber optic temperature sensor, a lidar, a high-definition camera, a tilt sensor, and strain gauges; the actuator 104 includes an autonomous UAV operation system, which consists of a multi-rotor UAV, a ground control unit, and an operation execution device, including a laser cutter, a foreign object grabber, and an acoustic deflector.

[0024] The data acquisition unit 101 is connected to the edge computing node 102, the cloud server 103 is communicatively connected to the edge computing node 102, and the actuator 104 is communicatively connected to the cloud server 103. The data acquisition unit 101 collects multi-dimensional status data of the transmission line in real time according to a preset sampling frequency, including electrical operating parameters, conductor temperature distribution data, environmental and external force risk data, and tower structure status data, and aggregates this data to the edge computing node 102. Next, the edge computing node 102 performs pre-processing on the multi-dimensional status data, sequentially identifying and removing abnormal data, correcting neighbor node correlations, and standardizing and normalizing the format. Based on complexity scores, current available computing power, and current network status, it executes an offloading decision and transmits the processed data to the cloud. Server 103; then, cloud server 103 performs multi-dimensional weighted fusion of the data to be processed, extracts feature vectors of four dimensions and weights and fuses them to obtain fused features, and at the same time constructs a digital twin model to conduct comprehensive diagnostic analysis of the fused features, generates a health score through finite element simulation, and quantifies the correlation information between features of each dimension to obtain comprehensive evaluation and diagnostic results; finally, cloud server 103 sends the evaluation and diagnostic results to execution agency 104, execution agency 104 triggers active protection actions based on the evaluation and diagnostic results, drives drones to remotely clear tree obstacles and foreign objects along the transmission line, or to perform non-contact expulsion operations against violators and animals, and updates the line status database after completing active protection, forming a complete closed loop from monitoring and diagnosis to active protection.

[0025] According to an embodiment of the present invention, a method for protecting transmission lines is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0026] This embodiment provides a transmission line protection method, which can be used in the aforementioned transmission line protection system. Figure 2 This is a flowchart of a power transmission line protection method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Collect multi-dimensional state data and perform pre-processing on the multi-dimensional state data to obtain the data to be processed.

[0027] Among them, multi-dimensional status data refers to a collection of various monitoring parameters that reflect the operating status of transmission lines, including but not limited to electrical operating parameters such as current, voltage, power factor, conductor temperature distribution data, environmental and external force risk data such as tree obstruction, construction machinery intrusion, foreign objects hanging on the line, and tower structural status data such as tower tilt and structural deformation; and is acquired through various sensors deployed at the transmission line site, including but not limited to current transformers, voltage transformers, fiber optic temperature sensors, lidar, high-definition cameras, tilt sensors and strain gauges.

[0028] Data preprocessing refers to preprocessing multi-dimensional state data. This involves identifying and correcting abnormal data based on its correlation with neighboring nodes, eliminating outliers caused by sensor malfunctions or environmental interference, improving accuracy and consistency, and using complex quantification of multiple indicators and resource status awareness of edge computing nodes to determine whether multi-dimensional state data should be processed locally at the edge node or uploaded to the cloud for in-depth analysis. This optimizes the allocation of computing resources and reduces communication bandwidth consumption.

[0029] Specifically, various sensors deployed at the transmission line site collect multi-dimensional status data in real time at a preset sampling frequency. The preset sampling frequency is adjusted according to the line voltage level, such as once every 100ms for high-voltage lines and once every 500ms for low-voltage lines. Simultaneously, electrical operating parameters, conductor temperature distribution data, environmental and external force risk data, and tower structural status data are obtained from the line monitoring system. Anomalies are identified and eliminated from the collected multi-dimensional status data, removing outliers caused by sensor failures or external interference. Correlation correction is performed using synchronous data collected by similar sensors on adjacent towers at the same time to eliminate measurement errors caused by single sensor deviations. The corrected status data is then formatted and normalized to map monitoring data of different dimensions to a unified numerical range. Based on the complexity score of the data to be processed, the current available computing power of the edge computing nodes, and the current network status of the communication network, the processing method for the data to be processed is comprehensively determined: for data with low complexity and sufficient edge computing power, subsequent processing is completed directly at the edge nodes; for data with high complexity or requiring large-scale computation, it is packaged, marked, and sent to the cloud server for in-depth analysis via the communication network. For example, when the tilt sensor of a certain tower experiences a short-term data jump due to a sudden strong wind, the edge node identifies and corrects the abnormal value by comparing it with the data of adjacent towers during the same period; if the current data complexity is low and the edge computing power is sufficient after correction, subsequent processing is completed at the edge nodes; if the current data complexity score exceeds a set threshold, it is packaged, marked, and uploaded to the cloud for in-depth analysis. Through the above preprocessing, data to be processed that can be used for subsequent fusion diagnosis is obtained.

[0030] Step S202: Perform multi-dimensional weighted fusion on the data to be processed to obtain fusion features.

[0031] Among them, multi-dimensional weighted fusion refers to the process of comprehensively processing monitoring data from different sensors that reflect different states of the transmission line by assigning different weight coefficients to each dimension, forming a unified feature vector that represents the overall operating state of the line; fusion feature refers to the comprehensive feature vector obtained after weighted fusion, which serves as the input for subsequent comprehensive diagnostic analysis of the digital twin model.

[0032] Multi-dimensional weighted fusion maps different types of monitoring data, such as electrical operating parameters, conductor temperature distribution data, environmental and external force risk data, and tower structural status data, from the heterogeneous original data space to a unified high-dimensional feature space. This enables various types of data to be jointly analyzed within the same framework, overcoming the limitation that single-dimensional monitoring cannot fully reflect the true operating status of the line.

[0033] Specifically, feature vectors of four dimensions are extracted from the data to be processed after pre-processing: electrical dimension feature vector, conductor dimension feature vector, environmental dimension feature vector, and tower dimension feature vector. The weight coefficients of each dimension are determined according to the current operating conditions of the line, such as load level and weather conditions. For example, the weight of the environmental dimension is increased during thunderstorms, and the weight of the electrical dimension is increased during heavy load operation. The feature vectors of each dimension are multiplied by their corresponding weight coefficients and then summed to obtain the fused features.

[0034] Step S203: Construct a geometric model based on the 3D point cloud data and design drawings of the transmission line; construct a physical model based on the material parameters and physical properties of the transmission line; merge the geometric model and the physical model, and construct a digital twin model based on the pre-acquired real-time monitoring data and the merged model.

[0035] Among them, 3D point cloud data refers to a set of high-precision 3D spatial coordinate points of the transmission line and its surrounding environment obtained by UAV laser scanning; design drawings refer to CAD design drawings of the transmission line and tower structure drawings; material parameters refer to the physical property parameters of the material of each component of the transmission line, including the elastic modulus, coefficient of linear expansion, and rated tensile strength of the conductor, the yield strength and elastic modulus of the tower, and the insulation performance parameters of the insulator; physical properties refer to the electrical, mechanical, and environmental properties of each component.

[0036] The geometric model is a three-dimensional digital model that accurately reflects the spatial geometry of the transmission line, based on three-dimensional point cloud data and design drawings. The physical model is a digital model with physical behavior simulation capabilities formed by assigning material parameters and physical properties to the geometric model. Real-time monitoring data refers to the multi-dimensional status data collected in real time by various sensors deployed at the transmission line site. The digital twin model is a high-fidelity simulation model that accurately maps the actual state of the physical transmission line by merging the geometric model and the physical model and updating it with real-time monitoring data.

[0037] Specifically, the process involves acquiring 3D point cloud data of the transmission line through UAV laser scanning, importing it into CAD design drawings and tower structure drawings, and then denoising, filtering, and registering the 3D point cloud data to align it with the design drawings in a unified coordinate system. Using region growing and feature extraction algorithms, the 3D contour information of key components such as towers, conductors, insulator strings, and hardware is segmented from the point cloud. Combined with the dimensional parameters and spatial relationships in the design drawings, a refined geometric model of each component is constructed and assembled into a complete geometric model. Simultaneously, the material parameters of each component are imported, integrating electrical, mechanical, and environmental physical properties to construct a physical model. The material properties in the physical model are precisely correlated to the corresponding component mesh units in the geometric model to achieve model fusion. Real-time monitoring data is accessed through a data interface, driving the physical parameters in the digital twin model to update with the real-time monitoring data. For example, sag and stress state are corrected based on real-time conductor temperature, and wind load application is adjusted based on real-time wind speed, resulting in a digital twin model that reflects the current real-time state of the transmission line online.

[0038] Step S204: Simulate and analyze the fused features using a digital twin model to generate a health score; quantify the correlation between multi-dimensional feature vectors in the fused features to generate multi-parameter coupled correlation information; use the health score and multi-parameter coupled correlation information as assessment and diagnostic results information.

[0039] Among them, the fusion feature refers to the comprehensive feature vector obtained after multi-dimensional weighted fusion, which integrates key information from four dimensions: electrical dimension features, conductor dimension features, environmental dimension features, and tower dimension features; simulation analysis refers to the process of using the fusion feature as boundary conditions and load input to the digital twin model, and performing real-time simulation calculations of the key physical states of the transmission line under the current operating conditions through finite element analysis; health score refers to the quantitative health evaluation score calculated according to the simulation analysis results, which integrates multiple indicators such as conductor stress, tower structure deformation, and insulator stress, and is output in percentage form to reflect the overall health status of the transmission line; correlation quantitative analysis refers to the process of quantitatively evaluating the linear and nonlinear correlation relationships between the feature parameters of each dimension in the fusion feature; multi-parameter coupling correlation information refers to the information set generated through quantitative analysis that reflects the mutual influence relationship between the parameters of each dimension and the potential fault propagation path; and assessment and diagnosis result information refers to the complete diagnostic conclusion formed by integrating the health score and multi-parameter coupling correlation information.

[0040] Specifically, the fused features obtained in step S202 are input into the digital twin model constructed in step S203. After receiving the fused features, the digital twin model uses the electrical dimension features, conductor dimension features, environmental dimension features, and tower dimension features as boundary conditions and load inputs. Finite element analysis is used to perform real-time simulation calculations of the key physical states of the transmission line under current operating conditions, including the stress distribution and sag change of the conductor under the coupling effects of self-weight, wind load, icing, and thermal expansion; the stress response and deformation of the tower structure under wind load and uneven icing; and the stress state of the insulator string under combined electrical and mechanical effects. After the simulation calculation is completed, a line health score is output based on the preset health status scoring criteria, which integrates various simulation results. The health status score is based on whether the conductor stress is close to or exceeds... The health score is calculated by weighting various indicators such as whether the rated tensile strength threshold, the deformation of the tower structure exceeds the safety allowable range, and the stress on the insulator is within the normal range, and output in percentage form. While performing digital twin simulation, the linear and nonlinear correlations between the feature parameters of each dimension in the fused features are quantitatively analyzed. The Pearson correlation coefficient is used to quantify the degree of linear correlation, and the mutual information method is used to quantify the nonlinear correlation, generating multi-parameter coupled correlation information. The health score and multi-parameter coupled correlation information are integrated to form a complete assessment and diagnosis result, which includes both a macro-level quantitative evaluation of the current health of the line and a micro-level analysis of the mutual influence between the parameters of each dimension and the potential fault propagation path, providing a decision-making basis for triggering subsequent active protection actions.

[0041] Step S205: Trigger active protection actions based on the assessment and diagnosis results. Active protection actions include at least one of the following: remotely clearing tree obstructions and foreign objects along the transmission line and non-contact removal of illegal personnel and animals along the transmission line.

[0042] Among them, proactive protective actions refer to unmanned safety response measures that are actively triggered based on assessment and diagnostic results. Proactive protective actions include, but are not limited to, remotely clearing tree obstructions and foreign objects along transmission lines, and non-contact removal of unauthorized personnel and animals along transmission lines.

[0043] Specifically, when the generated assessment and diagnosis results indicate that there are safety hazards or risks in the power line, corresponding protection instructions are issued to the autonomous drone operation system deployed along the transmission line corridor based on the type and severity of the hazard reflected in the assessment and diagnosis results. After receiving the instructions, the drone flies to the target area according to the preset route plan. For tree-related hazards, the drone remotely cuts off branches that exceed the safe range using an onboard laser cutting device. For hazards caused by foreign objects tangling in the lines, the drone uses a robotic arm to grab and remove the foreign objects. For hazards caused by unauthorized personnel or animals intruding, the drone uses a sonic repelling device to emit harmless sound waves to achieve non-contact repelling. The entire operation process requires no on-site human intervention, realizing autonomous, remote, and unmanned hazard handling, effectively reducing the safety risks of manual on-site operations and shortening the response time for hazard handling.

[0044] This embodiment provides a transmission line protection method that collects multi-dimensional status data and performs pre-processing. It utilizes neighbor node correlation correction to eliminate single-sensor measurement errors, ensuring data accuracy and consistency. Through multi-dimensional weighted fusion, it unifies electrical operating parameters, conductor temperature distribution data, environmental and external force risk data, and tower structural status data into a unified fusion feature, overcoming the limitations of single-dimensional monitoring. A digital twin model is constructed to simulate and quantify the fusion features, obtaining assessment and diagnostic results. This achieves a leap from single-point monitoring to multi-dimensional comprehensive diagnosis of transmission line operating status, improving assessment accuracy and fault identification capabilities. Based on the assessment and diagnostic results, it triggers active protection actions, forming a closed loop from data collection and fusion analysis to active protection. This enables intelligent active protection throughout the entire lifecycle of the transmission line, improving its safe operation and maintenance efficiency.

[0045] This embodiment provides a transmission line protection method, which can be used in the aforementioned transmission line protection system. Figure 3 This is a flowchart of a power transmission line protection method according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps: Step S301: Collect multi-dimensional state data and perform pre-processing on the multi-dimensional state data to obtain the data to be processed.

[0046] Specifically, step S301 includes: Step S3011: Identify and remove abnormal data from the multi-dimensional state data to obtain cleaned state data.

[0047] Specifically, this embodiment uses a sliding window filtering algorithm to smooth the collected multi-dimensional state data. The sliding window size is set to 10 sampling points. The mean of the data within the sliding window is calculated as an intermediate result. An anomaly threshold is determined based on the statistical characteristics of the data within the sliding window. The anomaly threshold is the mean of the data within the sliding window plus three times the standard deviation of the data within the window. When the anomaly threshold is exceeded, the data is judged as abnormal and is removed. At the same time, linear interpolation can be used to complete the missing data.

[0048] Step S3012: Obtain the synchronous state data collected by the same type of collection nodes adjacent to the current collection node, and calculate the correction coefficient based on the multidimensional correlation characteristics between the cleaned state data and the synchronous state data.

[0049] Specifically, after data cleaning, the system acquires concurrent state data from adjacent nodes of the same type within the same time period. A multi-factor regression model is then constructed, with inputs including four factors related to the relationship between the current node and its neighbors: data cosine similarity, spatial distance, electromagnetic environment similarity, and time synchronization error. Spatial distance is calculated using tower coordinates or GPS location; nodes that are closer together typically have higher data correlation. Electromagnetic environment similarity is based on a comparison of historical electric and magnetic field strength statistics near the node; greater electromagnetic environment similarity leads to stronger data comparability. Time synchronization error is provided by a distributed clock synchronization module; a smaller time synchronization error is more beneficial for data alignment.

[0050] The four factors are linearly weighted and combined using a multi-factor regression model, and then mapped to the 0-1 interval using the Sigmoid function to obtain the value of the correction coefficient k. The higher the linear weighted combination result, the closer the correction coefficient k value is to 1, indicating that the data of adjacent collection nodes is more reliable. The lower the linear weighted combination result, the closer the correction coefficient k value is to 0, indicating that the data of adjacent collection nodes is less reliable.

[0051] Step S3013: Based on the correction coefficient, the neighbor node correlation of the cleaned state data is corrected using the correction formula to obtain the corrected state data; the corrected state data is then normalized to obtain standardized feature data.

[0052] Specifically, after obtaining the correction coefficient k, the cleaning status data is corrected using a correction formula, which is as follows: (1); in, To correct the status data, For cleaning status data, This is the status data for the same period. The correction coefficient ranges from 0 to 1. If the data of adjacent nodes has high reliability (i.e., the correction coefficient k is close to 1), the corrected state data will refer more to the data of adjacent nodes. If the data of adjacent nodes has low reliability (i.e., the correction coefficient k is close to 0), the corrected state data will basically retain the value of the original cleaned state data.

[0053] The modified state data is formatted and normalized. For example, the maximum-minimum normalization method is used to map all modified state data to the [0,1] interval to obtain standardized feature data.

[0054] Step S3014: Perform multi-index complexity quantification on the standardized feature data to obtain a complexity score; monitor resource occupancy status to generate current available computing power information; obtain transmission quality parameters of the communication network to obtain current network status information.

[0055] Specifically, for the evaluation of standardized feature data, two indicators can be used: feature entropy and temporal mutation detection. Feature entropy is used to measure the uncertainty of multidimensional data. Shannon entropy is calculated based on the probability distribution of data from each sensor. The higher the entropy value, the more abnormal or complex the data pattern. Temporal mutation detection quantifies the degree of data change by calculating the Mahalanobis distance between the current data and the historical window mean. The cumulative sum algorithm is used to identify statistically significant change points.

[0056] The two metrics, feature entropy and temporal mutation detection, are weighted and fused to generate a complexity score ranging from 0 to 100. The higher the complexity score, the higher the complexity of the standardized feature data, and the more necessary it is to upload it to the cloud for in-depth analysis. Continuously monitor the computing power utilization and memory usage status of the current edge nodes, calculate the remaining available computing power resources, such as obtaining the total number of CPU cores, the percentage of computing power used, and the memory usage rate of the current node through the operating system interface, and quantify the idle computing power resources into the currently available computing power information, with a value range between 0 and 100.

[0057] Real-time monitoring of transmission quality parameters of the current communication link, including but not limited to network transmission round-trip latency and uplink bandwidth margin; for example, by periodically sending heartbeat probe packets to the cloud server to measure the round-trip latency of data packets from the edge node to the cloud server and back; at the same time, monitoring the actual available bandwidth of the current uplink, calculating the uplink bandwidth margin, and integrating the transmission quality parameters into the current network status information, with values ​​ranging from 0 to 100.

[0058] Step S3015: Based on the complexity score, current available computing power information, and current network status information, an offloading decision is made to obtain the data to be processed.

[0059] Specifically, the complexity score, current available computing power, and current network status are input into a preset offloading decision model to comprehensively determine the data processing method. The input dimensions of the preset offloading decision model include: complexity score, current available computing power, and current network status. At the same time, it combines the fault type priority table issued by the cloud to determine the urgency level of the current data. The preset offloading decision model is pre-configured with decision rules corresponding to different input combinations. The preset thresholds corresponding to each decision rule are periodically issued and updated in real time by the cloud server after statistical analysis of historical operating data, so that the preset thresholds can adapt to changes in different line sections and operating conditions. The urgency level is updated by the cloud intelligent diagnostic module based on historical fault statistics.

[0060] After comprehensive evaluation, three types of unloading decision results are output: completely local processing, hybrid processing, or completely cloud processing.

[0061] The decision rules of the preset unloading decision model are as follows: When the complexity score is below the preset threshold and the edge computing power is sufficient, complete edge intelligent analysis is performed locally, and only the preprocessed feature data is uploaded to the cloud as data to be processed; when the complexity score is high, such as a sudden increase in feature entropy or drastic fluctuations in time series, and the network condition is good, the standardized feature data is packaged and labeled with high priority, and uploaded to the cloud as data to be processed for in-depth analysis; when the edge computing power is close to saturation and the network quality is poor, only the key preliminary warning information is uploaded, and the transmission of non-urgent data is temporarily suspended; for data with high urgency, such as severe overheating of conductors or sharp tilting of towers, regardless of the complexity score and network condition, a local warning is forcibly triggered and the data is immediately packaged with high priority and uploaded to the cloud as data to be processed.

[0062] Step S302: Perform multi-dimensional weighted fusion on the data to be processed to obtain fusion features.

[0063] Specifically, step S302 includes: Step a: Extract multi-dimensional feature vectors from the data to be processed; perform weighted fusion of the multi-dimensional feature vectors to obtain fused features.

[0064] Specifically, feature vectors in four dimensions are extracted from the data to be processed: electrical dimension feature vector. , Wire dimension feature vector Environmental dimension feature vector and tower dimension feature vector .

[0065] After extracting the feature vectors in four dimensions, a multi-dimensional weighted fusion is performed. The fusion formula is as follows: (2); in, This is the fused composite feature vector; The weights are respectively assigned to electrical dimension features, conductor dimension features, environmental dimension features, and tower dimension features, and satisfy the following conditions: .

[0066] Before weighted fusion, the four feature vectors are standardized to map them to the same numerical range, eliminating differences between different units. The weighting coefficients for each dimension are then determined in real-time based on the current operating status of the transmission line. The weighting is adjusted based on factors including, but not limited to, line load levels, weather severity, and historical fault modes; for example, the environmental dimension weight is increased during thunderstorms. Increase the dimensional weight of the conductor when the conductor temperature rises abnormally. Increase the weight of electrical dimensions during heavy load operation. The adjustment of weight coefficients is achieved by linking fuzzy rule tables with real-time monitoring data. The weights are recalculated every five minutes to ensure that the fused weights can respond promptly to changes in operating conditions. The feature vectors of each dimension are multiplied by their corresponding weights and then superimposed to obtain the comprehensive feature vector. .

[0067] Step S303: Construct a geometric model based on the 3D point cloud data and design drawings of the transmission line; construct a physical model based on the material parameters and physical properties of the transmission line; merge the geometric model and the physical model, and construct a digital twin model based on the pre-acquired real-time monitoring data and the merged model.

[0068] Specifically, step S303 includes: Step b: Construct a geometric model based on the 3D point cloud data and design drawings of the transmission line; construct a physical model based on the material parameters and physical properties of the transmission line; merge the geometric model and the physical model, and obtain a digital twin model based on the pre-acquired real-time monitoring data and the merged model.

[0069] Specifically, high-precision 3D raw point cloud data of the transmission line and its surrounding environment is acquired. Simultaneously, CAD design drawings and tower structure drawings of the line are imported. Point cloud processing software is used to denoise, filter, and register the raw point cloud data, removing ground clutter and isolated noise points. The processed point cloud data is then registered and aligned with the design drawings in a unified coordinate system. Three-dimensional contour information of key components such as towers, conductors, insulator strings, and fittings is segmented from the point cloud using region growing and feature extraction algorithms. Combined with precise dimensional parameters and spatial relationships from the design drawings, 3D modeling software is used to construct geometric models of various components of the transmission line, including but not limited to the tower body, crossarms, and foundations of towers, the sag curves of conductors, and the string structure of insulator strings. These models are then assembled into a complete geometric model.

[0070] Based on the material parameters of each component of the transmission line, including but not limited to the material type of conductors such as steel-cored aluminum stranded wire, elastic modulus, Poisson's ratio, coefficient of linear expansion, and rated tensile strength; the steel type, yield strength, and elastic modulus of the towers; the material and insulation performance parameters of the insulators; and the connection method and load-bearing capacity of the fittings, a physical model is constructed by integrating electrical properties such as rated voltage and current carrying capacity, mechanical properties such as self-weight load, wind load, and icing load calculation parameters, and environmental properties such as the influence coefficients of temperature and humidity on material performance.

[0071] The constructed geometric model is fused with the physical model to obtain a digital twin model. The fusion process accurately associates the material properties in the physical model with the corresponding component mesh elements in the geometric model. After the fusion is completed, the pre-acquired real-time monitoring data is connected, including but not limited to electrical operating parameters, conductor temperature distribution data, environmental and external force risk data, and tower structure status data collected in real time by various sensors deployed at the transmission line site.

[0072] Real-time monitoring data is synchronized to the digital twin model via a data interface, driving the various physical parameters in the digital twin model to update with the real-time monitoring data. For example, the sag and stress state of the conductor are corrected according to the real-time conductor temperature, the application of wind load is adjusted according to the real-time wind speed, and the attitude reference of the model is corrected according to the real-time tower tilt angle data. Driven and corrected by the real-time monitoring data, the digital twin model can reflect the real state of the line under the current working conditions online.

[0073] Step S304: Simulate and analyze the fused features using a digital twin model to generate a health score; quantify the correlation between multi-dimensional feature vectors in the fused features to generate multi-parameter coupled correlation information; use the health score and multi-parameter coupled correlation information as assessment and diagnostic result information.

[0074] Specifically, step S304 includes: Step c: Construct a geometric model based on the 3D point cloud data and design drawings of the transmission line; construct a physical model based on the material parameters and physical properties of the transmission line; merge the geometric model and the physical model, and construct a digital twin model based on the pre-acquired real-time monitoring data and the merged model.

[0075] Specifically, the digital twin model constructed by integrating the features is driven to perform real-time simulation analysis. After receiving the integrated features, the digital twin model uses the electrical, conductor, environmental, and tower dimensions as boundary conditions and load inputs. The digital twin model performs real-time simulation calculations of the key physical states of the transmission line under the current operating conditions through finite element analysis. These include the stress distribution and sag variation of the conductor under the coupled effects of its own weight, wind load, icing, and thermal expansion. The stress distribution refers to the force per unit area borne by each point inside the conductor under different load conditions (such as its own weight, wind load, icing, and thermal expansion effect); the sag variation refers to the change in the vertical distance between the lowest point of the conductor and the suspension point when the conductor is suspended between two towers, as external conditions (such as temperature, icing, and wind force) change; the stress response and deformation of the tower structure under wind load and uneven icing; and the stress state of the insulator string under the combined effects of electrical and mechanical forces.

[0076] After the simulation calculation is completed, a line health score is output based on the preset health status scoring criteria, taking into account various simulation results. The scoring criteria include: whether the conductor stress is close to or exceeds the rated tensile strength threshold, whether the tower structure deformation exceeds the safety allowable range, and whether the insulator stress is within the normal range. After each indicator is weighted according to preset weights, the health score is output in percentage form.

[0077] After the simulation calculation is completed, the line health score is output based on the preset health status scoring criteria and the comprehensive simulation results. The weights of each indicator and the preset safety thresholds of the preset health status scoring criteria are periodically distributed to each edge node and updated in real time by the cloud server after statistical analysis of industry standards and historical fault data. The scoring criteria include: whether the conductor stress is close to or exceeds the rated tensile strength threshold, whether the tower structure deformation exceeds the safety allowable range, and whether the insulator stress is within the normal range. After each indicator is weighted according to its corresponding indicator weight, the health score is output in the form of a percentage.

[0078] While performing digital twin simulation, the linear and nonlinear correlations between feature vectors of each dimension in the fused features are quantitatively analyzed. In this embodiment, the Pearson correlation coefficient is used to quantify the degree of linear correlation, and the calculation formula is as follows: (3); Where r is the linear correlation coefficient, with a value range of [-1, 1], and n is the number of valid samples; Let be the values ​​of electrical parameters, ambient temperature, etc. in the i-th sample; Let represent the values ​​of parameters such as conductor temperature and icing thickness in the i-th sample.

[0079] Simultaneously, the mutual information method is used to quantify nonlinear correlations, and the calculation formula is as follows: (4); in, Let X be the mutual information between parameters X and Y, where X is the set of all possible values ​​of parameters such as electrical parameters and conductor stress, Y is the set of all possible values ​​of parameters such as ambient temperature and icing thickness, p(x,y) is the joint probability distribution of X=x and Y=y, p(x) is the marginal probability distribution of parameter X=x, and p(y) is the marginal probability distribution of parameter Y=y.

[0080] By comprehensively and quantitatively analyzing the correlation between linear and nonlinear relationships, multi-parameter coupled correlation information is generated.

[0081] The health score provides a quantitative evaluation of the overall health status of the line, while the multi-parameter coupled correlation information clarifies the mutual influence between parameters of each dimension and the propagation path of potential faults. By integrating the health score with the multi-parameter coupled correlation information, a complete assessment and diagnostic result is generated.

[0082] Step S305: Trigger active protection actions based on the assessment and diagnosis results. Active protection actions include at least one of the following: remotely clearing tree obstructions and foreign objects along the transmission line and non-contact removal of unauthorized personnel and animals along the transmission line.

[0083] Specifically, step S305 includes: Step d: Based on the assessment and diagnosis results, perform at least one of the following operations: remotely remove tree obstructions and foreign objects along the transmission line; and perform non-contact removal of unauthorized personnel and animals along the transmission line.

[0084] Specifically, the cloud server pushes the generated assessment and diagnosis results to the implementing agency, also known as the proactive protection execution terminal. The proactive protection execution terminal has a built-in early warning threshold judgment mechanism. When the health score in the received assessment and diagnosis results is lower than the preset safety threshold, or when there is a clear type and location of hidden danger, the corresponding proactive protection process is triggered without manual intervention.

[0085] The active protection execution end constructs an autonomous drone operation system, consisting of a multi-rotor drone, a ground control unit, and an operation execution device. In the pre-planned flight path stage, based on the route coordinate data in the geographic information system and combined with the hazard locations indicated by the assessment and diagnosis results, including tree obstruction locations, foreign object attachment points, and areas of activity of unauthorized personnel or animals, a flight path is generated at a certain distance along both sides of the route and at a certain height above the conductor through a path planning algorithm. Several waypoints are set in the path, and parameters such as the drone's flight speed and dwell time are specified. Various flight parameters involved in the pre-planned flight path, such as flight altitude, safe distance, and waypoint spacing, are pre-configured and regularly updated by the cloud server based on factors such as line voltage level, tower structure size, and lidar scanning area.

[0086] The drone is equipped with a lidar obstacle avoidance sensor and a high-definition camera. During flight, the lidar scans the environment in front in real time. When it detects obstacles such as trees, buildings, or other aircraft, it immediately transmits the obstacle location information to the flight control unit. The control unit adjusts the flight attitude and flight path through obstacle avoidance algorithms to achieve real-time autonomous obstacle avoidance.

[0087] The operation execution device includes a laser cutter, a foreign object grabber, and a sonic deflector. For tree obstructions, the laser cutter adjusts its output power according to the safe distance between the tree obstruction and the power line, focusing a high-energy laser beam on the cutting point to cut branches that exceed the safe range in a short time, ensuring that the trees and power lines maintain a sufficient safe distance. For foreign objects attached to the power line, such as plastic bags and kite strings, the foreign object grabber uses a multi-degree-of-freedom robotic arm to grab and transfer them to a safe area, preventing the foreign objects from causing short circuits. For unauthorized personnel and animals, the sonic deflector emits sound waves of a specific frequency that do not harm humans or animals but can cause discomfort, achieving non-contact deflection and protecting the safety of the power transmission line without harming living organisms.

[0088] Throughout the operation, the drone transmits images and data to the ground control unit in real time, allowing operators to monitor the progress and effectiveness of the operation. After the operation is completed, the drone returns to the preset take-off and landing point, completing the entire active protection process.

[0089] This embodiment provides a transmission line protection method that eliminates single-sensor measurement errors and effectively improves data quality and consistency by collecting multi-dimensional status data and combining it with neighbor node correlation correction. It overcomes the limitation of single-dimensional monitoring in comprehensively reflecting the line's operating status by using multi-dimensional weighted fusion to create unified fusion features. Furthermore, it generates health scores and multi-parameter coupled correlation information through digital twin models for simulation analysis and correlation quantification of the fusion features, achieving a leap from single-point monitoring to multi-dimensional comprehensive diagnosis of the transmission line's operating status, improving assessment accuracy and fault identification capabilities. Finally, based on the assessment and diagnosis results, it triggers an autonomous UAV system to perform remote clearing or non-contact expulsion operations, forming a complete closed loop from data collection, fusion analysis, diagnostic assessment to proactive protection. This solves the problems of single monitoring dimensions, insufficient multi-source data fusion capabilities, inadequate data processing and intelligent diagnostic capabilities, and lack of proactive protection measures in existing technologies, thereby improving the safe operation level and maintenance efficiency of transmission lines.

[0090] As one or more specific application embodiments of the present invention, the transmission line protection method provided by the present invention will be further described in detail, such as... Figure 4 As shown, it includes the following steps: 1. Multi-dimensional status data acquisition and pre-processing: Multi-source data spatiotemporal alignment and cleaning: Current transformers, voltage transformers, fiber optic temperature sensors, lidar, high-definition cameras, tilt sensors, and strain gauges deployed at the transmission line site are used to collect electrical operating parameters, conductor temperature distribution data, environmental and external force risk data, and tower structural status data in real time according to a preset sampling frequency, constructing a multi-dimensional status dataset; the time delay between the data from each sensor is determined by a cross-correlation function to achieve sub-millisecond alignment, ensuring that multi-source data are fused and analyzed under a unified time reference.

[0091] Anomaly identification and neighbor node correction: Anomalies are identified and removed from the original multi-dimensional state data. Outliers caused by sensor malfunctions or external interference are eliminated. A sliding window filtering algorithm is used to calculate the mean of the data within the window, and an anomaly threshold is determined based on the data within the sliding window. Data exceeding the threshold is identified as anomaly and removed. Simultaneous state data collected by adjacent nodes of the same type within the same time period are obtained, and a multi-factor regression model is constructed. The inputs to the multi-factor regression model include the data cosine similarity between the current node and adjacent nodes, spatial distance, electromagnetic environment similarity, and time synchronization error. The output is a correction coefficient k, and the correction formula is: (1); in, To correct the status data, For cleaning status data, This is the status data for the same period. The correction coefficient ranges from 0 to 1. If the data of adjacent nodes has high reliability (i.e., the correction coefficient k is close to 1), the corrected state data will refer more to the data of adjacent nodes. If the data of adjacent nodes has low reliability (i.e., the correction coefficient k is close to 0), the corrected state data will basically retain the value of the original cleaned state data.

[0092] Complexity Quantification and Offloading Decision: Standardized feature data undergoes multi-index complexity quantification, calculating feature entropy and temporal abrupt change detection indicators. These are then weighted and fused to generate a complexity score. Simultaneously, the resource occupancy status of edge computing nodes and the transmission quality parameters of the communication network are monitored to obtain current available computing power and network status information. Based on the complexity score, available computing power, and network status information, a comprehensive processing method is determined: for low-complexity data with sufficient edge computing power, subsequent processing is performed directly at the edge nodes; for high-complexity data or data requiring large-scale computation, the data is packaged, tagged, and uploaded to a cloud server via the communication network for in-depth analysis. Through this preprocessing, data is obtained that can be used for subsequent fusion diagnostics.

[0093] 2. Multi-dimensional weighted fusion: Multi-dimensional feature vector extraction: Extracting four-dimensional feature vectors from the data to be processed, namely electrical dimension feature vectors. , Wire dimension feature vector Environmental dimension feature vector and tower dimension feature vector .

[0094] Weighted fusion: Determine the weighting coefficients for each dimension based on the current operating conditions of the transmission line. For example, during thunderstorms, the environmental dimension weight is increased; during heavy-load operation, the electrical dimension weight is increased; and when the conductor temperature rises abnormally, the conductor dimension weight is increased, ensuring that the sum of all weights is 1. The feature vectors of each dimension are multiplied by their corresponding weight coefficients and then summed to obtain the fused features. : (2); This fusion feature retains key information from monitoring data across various dimensions and achieves adaptive representation of different operating conditions by adjusting weights.

[0095] 3. Digital Twin Model Construction and Comprehensive Diagnostic Analysis: Digital twin model construction: Based on the 3D point cloud data and design drawings of the transmission line, a geometric model is constructed; based on the material parameters (elastic modulus of conductors, yield strength of towers, insulation performance of insulators, etc.) and physical properties of the transmission line, a physical model is constructed; the geometric model and the physical model are merged, and real-time monitoring data is used to dynamically update the merged model to obtain the digital twin model.

[0096] Comprehensive diagnostic analysis: The fused features are input into the digital twin model, and finite element analysis is used to simulate physical states such as conductor stress, insulation aging, and icing growth in real time, generating a line health score. Simultaneously, the linear and nonlinear correlations between the feature parameters of each dimension in the fused features are quantitatively analyzed, using the Pearson correlation coefficient to quantify linear correlations. (3); Mutual information is used to quantify nonlinear correlations: (4); Generate multi-parameter coupled correlation information. Integrate the health score with the multi-parameter coupled correlation information to form the assessment and diagnostic results.

[0097] 4. Proactive protection and closed-loop operation and maintenance instructions: Active protection action triggering: Based on the assessment and diagnosis results, when a safety hazard is determined to exist in the transmission line, a protection command is issued to the autonomous operation system of the drone deployed in the transmission line channel. The drone then flies to the target area according to the preset route plan. For tree obstacles, the drone remotely cuts off branches that exceed the safe range using an airborne laser cutting device. For foreign objects hanging on the line, the drone grabs and removes the foreign objects using a robotic arm. For intrusions by unauthorized personnel or animals, the drone emits harmless sound waves to achieve non-contact removal.

[0098] Operation and maintenance command closed loop: After the active protection is executed, the drone transmits the operation images and data to the ground control unit in real time. After the operation is completed, it returns to the preset take-off and landing point and updates the line status database according to the execution results, forming a complete automated closed loop from monitoring, diagnosis, prediction to the issuance of active protection commands. This effectively reduces the safety risks of manual on-site operations, shortens the response time for handling hidden dangers, and ensures the safe and stable operation of transmission lines.

[0099] This embodiment provides a transmission line protection method that effectively solves the data reliability problem caused by single sensor measurement errors by collecting multi-dimensional status data and correcting the correlation between neighboring nodes. It weights and fuses the data and represents it as a unified fusion feature, overcoming the limitation that single-dimensional monitoring cannot fully reflect the line's operating status. Through simulation analysis and correlation quantification of the fusion feature using a digital twin model, it realizes the leap from single-point monitoring to multi-dimensional comprehensive diagnosis of the transmission line's operating status. Furthermore, based on the assessment and diagnosis results, it triggers remote clearing or non-contact removal operations, transforming the traditional operation and maintenance mode, which is mainly based on passive repair after a fault occurs, into an intelligent protection mode that combines proactive prevention and rapid response, realizing intelligent proactive protection of the transmission line throughout its entire life cycle.

[0100] This embodiment also provides a transmission line protection device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0101] This embodiment provides a power transmission line protection device, such as... Figure 5 As shown, it includes: The multi-dimensional status acquisition module 501 is used to acquire multi-dimensional status data of transmission lines.

[0102] The edge preprocessing module 502 is used to perform preprocessing on multi-dimensional state data to obtain data to be processed.

[0103] The feature fusion module 503 is used to perform multi-dimensional weighted fusion of the data to be processed to obtain fused features; The diagnostic analysis module 504 is used to construct a digital twin model, and to perform comprehensive diagnostic analysis on the fused features through the digital twin model to obtain evaluation and diagnostic result information. The active protection module 505 is used to trigger active protection actions based on the assessment and diagnostic results.

[0104] In some alternative implementations, the edge preprocessing module 502 includes: The data cleaning unit is used to identify and remove abnormal data from multi-dimensional state data to obtain cleaned state data.

[0105] The correction coefficient calculation unit is used to obtain the synchronous state data collected by the same type of acquisition nodes adjacent to the current acquisition node, and calculate the correction coefficient based on the multidimensional correlation characteristics between the cleaned state data and the synchronous state data.

[0106] The correction unit is used to correct the correlation between neighboring nodes in the cleaned state data according to the correction coefficient and the correction formula to obtain the corrected state data.

[0107] The normalization unit is used to normalize the corrected state data to obtain standardized feature data.

[0108] In some alternative implementations, the edge preprocessing module 502 includes: The data processing unit is used to perform multi-index complexity quantification on standardized feature data to obtain a complexity score; monitor resource occupancy status and generate current available computing power information; obtain transmission quality parameters of the communication network to obtain current network status information; and execute offloading decisions based on the complexity score, current available computing power information, and current network status information to obtain the data to be processed.

[0109] In some alternative implementations, the feature fusion module 503 includes: The feature fusion unit is used to extract multi-dimensional feature vectors from the data to be processed; the multi-dimensional feature vectors are weighted and fused to obtain fused features.

[0110] In some alternative implementations, the diagnostic analysis module 504 includes: The digital twin model building unit is used to construct a geometric model based on the three-dimensional point cloud data and design drawings of the transmission line; construct a physical model based on the material parameters and physical properties of the transmission line; and merge the geometric model and the physical model to obtain a digital twin model based on the pre-acquired real-time monitoring data and the merged model.

[0111] The diagnostic analysis unit is used to perform simulation analysis on the fused features through a digital twin model to generate a health score; to perform quantitative analysis on the correlation between multi-dimensional feature vectors in the fused features to generate multi-parameter coupled correlation information; and to use the health score and multi-parameter coupled correlation information as evaluation and diagnostic result information.

[0112] In some alternative implementations, the active protection module 505 includes: The active protection unit is used to perform at least one of the following operations based on the assessment and diagnosis results: remotely clearing tree obstructions and foreign objects along the transmission line; and non-contact removal of unauthorized personnel and animals along the transmission line.

[0113] The transmission line protection device provided in this embodiment of the invention can execute a transmission line protection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the various modules and units described above are the same as in the corresponding embodiments described above, and will not be repeated here.

[0114] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0115] The following is a detailed reference. Figure 6 This diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 601, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 602 or a program loaded from memory 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of the electronic device. The processor 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0116] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0117] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a memory 608, or installed from a ROM 602. When the computer program is executed by the processor 601, it performs the functions defined in a transmission line protection method according to an embodiment of the present invention.

[0118] Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0119] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, a power transmission line protection method shown in the above embodiments is implemented.

[0120] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0121] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for protecting transmission lines, characterized in that, The method includes: Collect multi-dimensional status data of the transmission line and perform data preprocessing on the multi-dimensional status data to obtain the data to be processed; The data to be processed is subjected to multi-dimensional weighted fusion to obtain fusion features; A geometric model is constructed based on the three-dimensional point cloud data and design drawings of the transmission line; a physical model is constructed based on the material parameters and physical properties of the transmission line; the geometric model and the physical model are fused together, and a digital twin model is constructed based on the pre-acquired real-time monitoring data and the fused model. The fused features are simulated and analyzed using the digital twin model to generate a health score; the correlation between multi-dimensional feature vectors in the fused features is quantitatively analyzed to generate multi-parameter coupled correlation information; the health score and the multi-parameter coupled correlation information are used as assessment and diagnostic result information. Active protection actions are triggered based on the assessment and diagnosis results. These active protection actions include at least one of the following: remotely clearing tree obstructions and foreign objects along the transmission line and non-contact removal of unauthorized personnel and animals along the transmission line.

2. The method according to claim 1, characterized in that, The data preprocessing of the multi-dimensional state data includes: Abnormal data is identified and removed from the multi-dimensional state data to obtain cleaned state data; Obtain concurrent state data collected by similar acquisition nodes adjacent to the current acquisition node, and calculate correction coefficients based on the multidimensional correlation characteristics between the cleaning state data and the concurrent state data; Based on the correction coefficient, the neighbor node correlation of the cleaning status data is corrected using the correction formula to obtain the corrected status data. The corrected state data is normalized to obtain standardized feature data.

3. The method according to claim 2, characterized in that, The corrected formula is: in, To correct the status data, For cleaning status data, The synchronous state data, The correction coefficient is denoted as .

4. The method according to claim 2, characterized in that, The preprocessing of the multi-dimensional state data also includes: The standardized feature data is subjected to multi-index complexity quantification to obtain a complexity score; Monitor resource usage status and generate current available computing power information; Obtain the transmission quality parameters of the communication network to get the current network status information; Based on the complexity score, current available computing power information, and current network status information, an offloading decision is made to obtain the data to be processed.

5. The method according to claim 1, characterized in that, The process of multi-dimensional weighted fusion of the data to be processed to obtain fusion features includes: Extract multi-dimensional feature vectors from the data to be processed; The multi-dimensional feature vectors are weighted and fused to obtain the fused features.

6. A power transmission line protection system, characterized in that, A transmission line protection method according to any one of claims 1 to 5, the system comprising: The data acquisition unit is installed on the transmission line side to collect multi-dimensional status data of the transmission line; An edge computing node, connected to the data collector, is used to perform data preprocessing on the multi-dimensional state data to obtain data to be processed. A cloud server, which communicates with the edge computing node, is used to perform multi-dimensional weighted fusion of the data to be processed to obtain fusion features; a digital twin model is constructed, and the fusion features are comprehensively diagnosed and analyzed through the digital twin model to obtain evaluation and diagnostic results information; An actuator is used to trigger active protection actions based on the assessment and diagnostic results.

7. A transmission line protection device, characterized in that, The device includes: A multi-dimensional status acquisition module is used to acquire multi-dimensional status data of the transmission line; An edge preprocessing module is used to perform data preprocessing on the multi-dimensional state data to obtain data to be processed. The feature fusion module is used to perform multi-dimensional weighted fusion on the data to be processed to obtain fused features; The diagnostic analysis module is used to construct a digital twin model, and to perform comprehensive diagnostic analysis on the fused features through the digital twin model to obtain evaluation and diagnostic result information; The active protection module is used to trigger active protection actions based on the assessment and diagnostic results.

8. The apparatus according to claim 7, characterized in that, The edge preprocessing module includes: The data cleaning unit is used to identify and remove abnormal data from the multi-dimensional state data to obtain cleaned state data. The correction coefficient calculation unit is used to obtain the synchronous state data collected by the same type of acquisition nodes adjacent to the current acquisition node, and calculate the correction coefficient based on the multidimensional correlation characteristics between the cleaning state data and the synchronous state data. The correction unit is used to correct the neighbor node correlation of the cleaning status data according to the correction coefficient and the correction formula to obtain the corrected status data. The normalization unit is used to normalize the corrected state data to obtain standardized feature data.

9. The apparatus according to claim 8, characterized in that, The corrected formula is: in, To correct the status data, For cleaning status data, The synchronous state data, The correction coefficient is denoted as .

10. The apparatus according to claim 8, characterized in that, The edge preprocessing module further includes: The data to be processed calculation unit is used to perform multi-index complexity quantification on the standardized feature data to obtain a complexity score; monitor resource occupancy status and generate current available computing power information; obtain transmission quality parameters of the communication network to obtain current network status information; and perform offloading decisions based on the complexity score, current available computing power information and current network status information to obtain the data to be processed.

11. The apparatus according to claim 7, characterized in that, The feature fusion module includes: The feature fusion unit is used to extract multi-dimensional feature vectors from the data to be processed; and to perform weighted fusion on the multi-dimensional feature vectors to obtain fused features.

12. The apparatus according to claim 7, characterized in that, The diagnostic analysis module includes: The diagnostic analysis unit is used to perform simulation analysis on the fused features through the digital twin model to generate a health score; to perform quantitative analysis on the correlation between multi-dimensional feature vectors in the fused features to generate multi-parameter coupled correlation information; and to use the health score and the multi-parameter coupled correlation information as evaluation and diagnostic result information.

13. The apparatus according to claim 12, characterized in that, The device further includes: The digital twin model building unit is used to construct a geometric model based on the three-dimensional point cloud data and design drawings of the transmission line; construct a physical model based on the material parameters and physical properties of the transmission line; fuse the geometric model and the physical model, and obtain a digital twin model based on the pre-acquired real-time monitoring data and the fused model.

14. The apparatus according to claim 7, characterized in that, The active protection module includes: The active protection unit is used to perform at least one of the following operations based on the assessment and diagnosis results: remotely clearing tree obstructions and foreign objects along the transmission line; and non-contact removal of unauthorized personnel and animals along the transmission line.

15. An electronic device, characterized in that, include: The system includes a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the steps of a power transmission line protection method according to any one of claims 1 to 5.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the steps of a power transmission line protection method according to any one of claims 1 to 5.

17. A computer program product, characterized in that, It includes computer instructions for causing a computer to perform the steps of a power transmission line protection method according to any one of claims 1 to 5.