Methods, devices, electronic equipment and storage media for early warning of transmission line risks

By acquiring multi-dimensional data of transmission lines, determining electrical and non-electrical characteristics, and combining risk characteristic weights, early warning information is generated, solving the problem of low early warning accuracy in existing technologies and achieving more accurate early warning.

CN123117774APending Publication Date: 2026-11-17STEJT GRID ELEKTRIK PAUER INZHINIRING RISERCH INSTITYUT KO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611245616.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-08-17
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

In existing technologies, the early warning accuracy of transmission lines is low, and it is difficult to fully consider the combined influence of electrical and non-electrical parameters, resulting in inaccurate early warning information.

Method used

By acquiring multi-dimensional data of transmission lines, including electrical and non-electrical data, electrical and non-electrical characteristics are determined. Combined with preset risk characteristic weights, risk levels and integrated characteristics are determined, thereby generating early warning information.

Benefits of technology

It improves the accuracy of early warning information, comprehensively considers various factors affecting the safety of transmission lines, and enhances the precision and comprehensiveness of early warning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123117774A_ABST
    Figure CN123117774A_ABST
Patent Text Reader

Abstract

This invention relates to the field of power system operation and maintenance technology, and discloses a method, device, electronic equipment, and storage medium for early warning of transmission line risks. By acquiring multi-dimensional data of the transmission line, determining the electrical and non-electrical characteristics of the transmission line based on the electrical and non-electrical data represented by the multi-dimensional data, determining the risk level and integrated characteristics of the transmission line based on the electrical and non-electrical characteristics, and further determining the risk assessment result of the transmission line, early warning information of the transmission line is determined based on the risk assessment result. By collecting multi-dimensional non-electrical data and combining the non-electrical characteristics corresponding to the non-electrical data to determine the early warning information, the invention comprehensively considers various influencing factors on transmission line safety, thereby improving the accuracy of the early warning information.
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 technology, specifically to a method, device, electronic equipment, and storage medium for early warning of transmission line risks. Background Technology

[0002] In a power system, multiple transmission lines connect power-consuming equipment and power-generating equipment. To ensure the stable operation of the power system, it is necessary to maintain the transmission lines. In the early days, manual inspections were mainly carried out in conjunction with simple testing instruments to check the status of the lines. Due to limitations in manpower costs and the scope of work, the overall monitoring efficiency was low and it was easy to miss some cases.

[0003] In related technologies, various electrical sensors are deployed to acquire different electrical parameters in transmission lines. Based on these different electrical parameters, analysis is performed to determine whether an anomaly has occurred in the current transmission line. Different early warning information is matched by comparing the results with preset abnormal data thresholds. However, the factors influencing the abnormal information of transmission lines are diverse. If only the analysis of electrical parameters is used, the early warning of transmission lines caused by non-electrical parameter influencing factors is easily overlooked, affecting the accuracy of the early warning of transmission lines. Summary of the Invention

[0004] This application provides a method, device, electronic device, and storage medium for early warning of transmission line risks, in order to at least solve the problem of low accuracy in early warning of transmission lines in related technologies.

[0005] Firstly, this application provides a method for early warning of transmission line risks, including: Acquire multi-dimensional data of transmission lines; the multi-dimensional data includes at least electrical and non-electrical data. Based on multi-dimensional data, determine the electrical and non-electrical characteristics of the transmission line; The risk level of a transmission line is determined based on preset risk characteristic weights, electrical characteristics, and non-electrical characteristics of the transmission line. Based on the electrical and non-electrical characteristics of the transmission line, determine the integration characteristics of the transmission line; The risk assessment results are determined based on the risk level and integration characteristics of the transmission lines. Based on the risk assessment results, early warning information for transmission lines is determined.

[0006] In one optional implementation, the risk level of the transmission line is determined based on preset risk characteristic weights, electrical characteristics, and non-electrical characteristics of the transmission line, including: Determine at least one characteristic value based on the electrical and non-electrical characteristics of the transmission line; The overall risk score at the current moment is determined based on the preset risk feature weights and at least one feature normalization value. The risk level at the current moment is determined based on the comprehensive risk score at the current moment.

[0007] In one optional implementation, the comprehensive risk score for the current moment is determined based on preset risk feature weights and at least one feature value, including: The overall risk score at the current moment is determined based on the following formula:

[0008] in, The overall risk score at the current moment. Based on the preset feature weight coefficients of the k-th feature, Let be the eigenvalue of the k-th feature, and n be the total number of features.

[0009] In one optional implementation, the fusion characteristics of the transmission line are determined based on its electrical and non-electrical characteristics, including: Based on the electrical and non-electrical characteristics of the transmission line, determine the electrical and non-electrical characteristics with unified dimensions; Based on the dimensionally unified electrical features, non-electrical features, and a preset attention weight matrix, the association weights of electrical features and non-electrical features are determined. Based on the correlation weights and the unified electrical and non-electrical characteristics, the fusion characteristics of the transmission line are determined.

[0010] In one optional implementation, the transmission line communication connection includes an edge computing node and a cloud server to acquire multi-dimensional data of the transmission line, and further includes: The complexity of the multi-dimensional data is determined based on the preset complexity index and the multi-dimensional data of the transmission line; Obtain the computing load and network communication quality of edge computing nodes; Determine the computing capacity of edge computing nodes based on computing load and network communication quality; Based on the computing capacity of edge computing nodes and the complexity of multi-dimensional data, a preprocessing mode for multi-dimensional data is determined; among which, the preprocessing mode includes local processing, cloud processing, and hybrid processing.

[0011] In one optional implementation, a preprocessing mode for the multi-dimensional data is determined based on the comprehensive score of the edge computing node's computing power and the complexity of the multi-dimensional data; wherein the preprocessing mode includes local processing, cloud processing, and hybrid processing, including: If the complexity is no greater than the preset first complexity and the comprehensive score of computing power is greater than the preset first capability threshold, the preprocessing mode is determined to be local processing; where local processing means that multi-dimensional data is computed at edge computing nodes.

[0012] In one alternative implementation, the non-electrical data includes mechanical structure data, environmental impact data, and visual monitoring data. The mechanical structure data includes tower tilt values, conductor vibration values, and hardware stress values. The environmental impact data includes temperature, humidity, wind speed, icing status data, and precipitation. The visual monitoring data includes the appearance of the line and external intrusion targets.

[0013] Secondly, this application also provides a transmission line risk early warning device, comprising: The acquisition module is used to acquire multi-dimensional data of the transmission line; the multi-dimensional data includes at least electrical data and non-electrical data. The first determining module is used to determine the electrical and non-electrical characteristics of the transmission line based on multi-dimensional data; The second determination module is used to determine the risk level of the transmission line based on the preset risk characteristic weights, electrical characteristics and non-electrical characteristics of the transmission line; The third determining module is used to determine the fusion characteristics of the transmission line based on its electrical and non-electrical characteristics. The fourth determination module is used to determine the risk assessment results based on the risk level and integration characteristics of the transmission line. The early warning determination module is used to determine early warning information for transmission lines based on the risk assessment results.

[0014] In one alternative implementation, the second determining module is specifically used for: Based on the electrical and non-electrical characteristics of the transmission line, at least one characteristic value is determined; based on the preset risk characteristic weights and at least one characteristic normalization value, the comprehensive risk score at the current moment is determined; based on the comprehensive risk score at the current moment, the risk level at the current moment is determined.

[0015] In one alternative implementation, the second determining module is further configured to: The overall risk score at the current moment is determined based on the following formula:

[0016] in, The overall risk score at the current moment. Based on the preset feature weight coefficients of the k-th feature, Let be the eigenvalue of the k-th feature, and n be the total number of features.

[0017] In one alternative implementation, the third determining module is specifically used for: Based on the electrical and non-electrical characteristics of the transmission line, determine the electrical and non-electrical characteristics with unified dimensions; based on the unified electrical and non-electrical characteristics and the preset attention weight matrix, determine the association weights of the electrical and non-electrical characteristics; based on the association weights, the unified electrical and non-electrical characteristics, determine the fusion characteristics of the transmission line.

[0018] In one alternative implementation, the acquisition module is specifically used for: Based on preset complexity indicators and multi-dimensional data of transmission lines, the complexity of multi-dimensional data is determined; the computing load and network communication quality of edge computing nodes are obtained; the computing capacity of edge computing nodes is determined based on computing load and network communication quality; and the preprocessing mode of multi-dimensional data is determined based on the computing capacity of edge computing nodes and the complexity of multi-dimensional data. Among them, the preprocessing mode includes local processing, cloud processing and hybrid processing.

[0019] In one alternative implementation, the acquisition module is further configured to: If the complexity is no greater than the preset first complexity and the comprehensive score of computing power is greater than the preset first capability threshold, the preprocessing mode is determined to be local processing; where local processing means that multi-dimensional data is computed at edge computing nodes.

[0020] In one alternative implementation, the acquisition module further includes: Non-electrical data includes mechanical structure data, environmental impact data, and visual monitoring data. Mechanical structure data includes tower tilt values, conductor vibration values, and hardware stress values. Environmental impact data includes temperature, humidity, wind speed, icing status data, and precipitation. Visual monitoring data includes line appearance and external intrusion targets.

[0021] This application also provides an electronic device, including: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of any of the above-described transmission line risk warning methods.

[0022] Thirdly, this application also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements the steps of any of the above-mentioned transmission line risk warning methods.

[0023] Fourthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above-mentioned transmission line risk warning methods.

[0024] Fifthly, through this application, by acquiring multi-dimensional data of transmission lines, determining the electrical and non-electrical characteristics of transmission lines based on the electrical and non-electrical data characterized by the multi-dimensional data, determining the risk level and fusion characteristics of transmission lines based on the electrical and non-electrical characteristics, further determining the risk assessment results of transmission lines, and determining early warning information of transmission lines based on the risk assessment results, by collecting multi-dimensional non-electrical data and combining the non-electrical characteristics corresponding to the non-electrical data to determine early warning information, the accuracy of early warning information is improved by comprehensively considering various influencing factors on the safety of transmission lines. Attached Figure Description

[0025] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a schematic diagram of the structure of the transmission line risk early warning system on which the embodiments of this application are based; Figure 2 A flowchart illustrating the transmission line risk early warning method provided in this application embodiment; Figure 3 A flowchart illustrating an exemplary transmission line risk early warning method provided in this application embodiment; Figure 4 A schematic diagram of the structure of an exemplary transmission line risk early warning system provided in this application embodiment; Figure 5 This is a schematic diagram of the structure of the transmission line risk early warning device provided in the embodiments of this application; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0027] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0028] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. The terms "first," "second," etc., in this application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0029] In the field of power transmission line safety assurance, the development of safety risk identification technology has always resonated with the intelligentization process of the power industry. Early on, limited by technology, risk identification relied mainly on manual inspections and simple instrument measurements, which was not only inefficient but also prone to accuracy issues due to human negligence and environmental factors. With the increasing maturity of sensor technology, electrical parameters, mechanical structure data, and environmental monitoring information have gradually been incorporated into the monitoring scope. The widespread application of specialized monitoring equipment has continuously enriched the scale and types of data collection. Subsequently, the deep integration of data processing technologies with machine learning and deep learning algorithms has driven the transformation of risk identification models from traditional manual judgment to data-driven approaches. Multi-source data fusion, feature extraction, optimization, and evaluation model construction have become core directions for technological breakthroughs, with various targeted algorithms and models constantly emerging, continuously improving identification accuracy and efficiency.

[0030] Despite the advancements in technology from manual to intelligent methods, numerous challenges remain in the complex operating environment of power systems. Data acquisition often suffers from incomplete dimensional coverage; some solutions focus on acquiring only a single data type, failing to fully capture the comprehensive impact of electrical, mechanical, environmental, and visual factors on transmission lines. In data preprocessing, noise filtering and missing value completion lack stability, and invalid data and format differences can interfere with the accuracy of subsequent feature extraction. The semantic differences between different feature types are significant, and existing fusion technologies struggle to overcome domain barriers, failing to fully explore deep correlations between various features, resulting in insufficient comprehensiveness and accuracy in feature representation. In risk assessment, some solutions focus only on the quantitative classification of risk levels, lacking the ability to predict risk trends and accurately identify specific fault types, thus failing to meet the decision-making needs of actual operation and maintenance. Furthermore, model training often employs centralized data collection, posing potential risks of data privacy breaches and failing to adapt to the varying operating environments and structural differences of lines in different regions. The models lack adaptive adjustment capabilities, and dynamic iterative optimization is limited, requiring improvement in long-term stability and applicability.

[0031] To address the aforementioned technical problems, this application provides a method, device, electronic device, and storage medium for early warning of transmission line risks. The method includes: acquiring multi-dimensional data of the transmission line; wherein the multi-dimensional data includes at least electrical data and non-electrical data; determining the electrical and non-electrical characteristics of the transmission line based on the multi-dimensional data; determining the risk level of the transmission line based on preset risk characteristic weights, the electrical and non-electrical characteristics of the transmission line; determining the integrated characteristics of the transmission line based on the electrical and non-electrical characteristics of the transmission line; determining the risk assessment result based on the risk level and the integrated characteristics of the transmission line; and determining early warning information for the transmission line based on the risk assessment result. The method provided by the above scheme improves the accuracy of early warning information by acquiring multi-dimensional data of transmission lines, determining the electrical and non-electrical characteristics of transmission lines based on the electrical and non-electrical data represented by the multi-dimensional data, determining the risk level and integrated characteristics of transmission lines based on the electrical and non-electrical characteristics, further determining the risk assessment results of transmission lines, and determining early warning information of transmission lines based on the risk assessment results. By collecting multi-dimensional non-electrical data and combining the non-electrical characteristics corresponding to the non-electrical data to determine early warning information, the method comprehensively considers various influencing factors of transmission line safety.

[0032] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0033] The specific application environment architecture or specific hardware architecture on which the transmission line risk early warning method depends is described here.

[0034] First, the structure of the transmission line risk early warning system upon which this application is based will be described: The transmission line risk early warning method, device, electronic equipment, and storage medium provided in this application are applicable to early warning of risks to transmission lines, such as... Figure 1 The diagram shown is a structural schematic of the transmission line risk early warning system based on the embodiments of this application. It mainly includes the transmission line to be predicted, a data acquisition device, and a transmission line risk early warning device. The data acquisition device is used to acquire multi-dimensional data of the transmission line, and the transmission line risk early warning device is used to provide early warning of the risks of the transmission line based on the transmission line risk early warning method provided in the embodiments of this application.

[0035] This application provides a method for early warning of transmission line risks, used to provide early warning of risks to transmission lines. It is applicable to overhead transmission lines of various voltage levels from 110kV to 1000kV, covering different geographical and operational scenarios such as mountainous areas, plains, and suburban areas. The execution subject of this application embodiment is an electronic device, such as a server, desktop computer, laptop computer, tablet computer, and other electronic devices that can be used for transmission line risk early warning.

[0036] like Figure 2 The diagram shown is a flowchart illustrating a transmission line risk early warning method provided in an embodiment of this application. The method includes: Step 201: Obtain multi-dimensional data of the transmission line.

[0037] Among them, multi-dimensional data includes at least electrical data and non-electrical data.

[0038] Specifically, the multi-dimensional status data includes electrical data and non-electrical data. Electrical data includes current, voltage, and partial discharge signals, while non-electrical data includes mechanical structure data, environmental impact data, and visual monitoring data. Mechanical structure data includes tower tilt values, conductor vibration values, and hardware stress values. Environmental impact data includes temperature, humidity, wind speed, icing status data, and precipitation. Visual monitoring data includes line appearance and external intrusion targets.

[0039] Accordingly, current data directly reflects the line load-bearing capacity, voltage data characterizes the stability of power supply, partial discharge signals indicate the presence of insulation defects, and electrical data characterizes the electrical operating status. Tower tilt values ​​characterize the overall stability of the towers, conductor vibration values ​​characterize the degree of conductor fatigue loss, hardware stress values ​​characterize the safety performance of connecting components, and mechanical structure data characterizes the safety of the line's mechanical structure. Temperature and humidity characterize the line's insulation performance, wind speed and icing conditions characterize potential hazards such as conductor galloping or icing, and precipitation characterizes the likelihood of tower foundation erosion. Line appearance characterizes line defects such as conductor corrosion and insulator damage, and external intrusion targets include objects that may threaten line safety, such as birds, drones, and construction machinery. Multi-dimensional data comprehensively reflects the main influencing factors facing line operation. By combining various multi-dimensional data, multiple influencing factors affecting transmission line safety are comprehensively considered.

[0040] Specifically, in one embodiment, during the data acquisition phase, data acquisition equipment is reasonably deployed around key components such as poles, conductors, and fittings, as well as around the line, to acquire four types of data according to differentiated frequencies.

[0041] The electrical sensor group includes current sensors, voltage sensors, and partial discharge sensors to collect electrical data. The data acquisition frequency is set to once per second. The current sensor has a measurement range of 0-2000A and an accuracy class of 0.2, accurately capturing changes in line current and is suitable for high-voltage, high-current scenarios. The voltage sensor has a measurement range of 0-10kV, a wide frequency response, strong anti-interference capability, and can stably acquire line voltage data. The partial discharge sensor has a detection range of up to 5 meters and can effectively capture partial discharge signals generated by insulation defects in the line.

[0042] The mechanical sensor group includes a tower tilt sensor, a vibration sensor, and a stress sensor to collect mechanical structure data. The mechanical data acquisition frequency is once per minute. The tower tilt sensor has a measurement range of ±15° and a resolution of 0.01°. It is installed at the waist of the tower to monitor the tower tilt status in real time. The vibration sensor has a sensitivity of 100mV / g and a frequency range of 1-1000Hz. It is fixed at the conductor suspension point to collect conductor vibration data. The stress sensor has a measurement range of 0-200MPa and an accuracy of ±1MPa. It is installed at the hardware connection to monitor the stress changes of the hardware.

[0043] The environmental sensor array includes temperature, humidity, wind speed and direction, icing, and precipitation sensors to collect environmental impact data. Data is collected every 5 minutes. The temperature sensor measures from -40℃ to 85℃ with an accuracy of ±0.5℃. The humidity sensor measures from 0-100%RH with an accuracy of ±2%RH. The wind speed and direction sensor measures wind speed from 0-60m / s and wind direction from 0-360°, offering high accuracy and eliminating mechanical wear. The precipitation sensor measures from 0-4mm / min with a resolution of 0.2mm. The icing sensor measures from 0-100mm with an accuracy of ±1mm and operates stably in low-temperature environments.

[0044] The visual acquisition device includes a visible light camera and an infrared imaging device to collect visual monitoring data. The visual data acquisition frequency is one frame every 10 minutes. The visible light camera has 8 megapixels and an infrared night vision range of up to 50 meters. It is installed on the top of the tower to capture images of the line's appearance. The infrared imaging device has a temperature measurement range of -20℃ to 150℃ and a resolution of 384×288. It can detect heat defects in the line and, in conjunction with the visible light camera, achieves all-weather visual monitoring, comprehensively capturing information about the line's appearance and external intrusion targets.

[0045] The model of the data acquisition equipment is determined based on the characteristics of the multi-dimensional data and the application environment. Electrical sensors typically employ high-precision, anti-interference Hall effect current sensors, capacitive voltage sensors, and ultrasonic partial discharge sensors to adapt to the complex electromagnetic interference of high-voltage power transmission environments. Mechanical sensors are selected based on the required measurement range and accuracy, typically using dual-axis tilt sensors, piezoelectric vibration sensors, and fiber optic stress sensors, which possess strong resistance to harsh environments. Environmental sensors are chosen for their high stability and rapid response, adapting to various climatic conditions. The visual acquisition device is equipped with a 4K high-definition visible light camera and an uncooled infrared thermal imager. The visible light camera captures common external defects, while the infrared thermal imager detects hidden problems such as overheating, achieving all-weather, blind-spot-free visual monitoring coverage.

[0046] Accordingly, by setting a reasonable data collection frequency, the data can reflect the line status in real time, while avoiding the problem of high system computation caused by collecting a large amount of data.

[0047] Step 202: Determine the electrical and non-electrical characteristics of the transmission line based on multi-dimensional data.

[0048] For multi-dimensional data, firstly, an adaptive filtering algorithm is used to remove noisy data, interpolation is used to complete missing data, and an anomaly detection algorithm is used to remove invalid data. Electrical status data, mechanical structure data, environmental impact data, and visual monitoring data are each normalized and mapped to a preset numerical range. The adaptive filtering algorithm can be a Kalman filter, the interpolation method can be linear interpolation, and the anomaly detection algorithm can be an isolation forest algorithm. Finally, a quality assessment method is used to evaluate the quality of the multi-dimensional data, and multi-dimensional data with quality assessment scores below a preset quality threshold are filtered out.

[0049] Specifically, in one embodiment, the normalized value of the multi-dimensional data is determined based on the following formula:

[0050] in, This represents the normalized value of multi-dimensional data of type c. This represents multi-dimensional data of type c at the current moment. This represents the maximum value of multi-dimensional data of type c. This represents the minimum value of multi-dimensional data of type c. The maximum and minimum values ​​are the extreme values ​​within a preset reasonable range from the historical data of the route.

[0051] Correspondingly, Kalman filtering can dynamically track data change trends and accurately filter out noise data caused by sensor errors and external electromagnetic interference. Linear interpolation can smoothly supplement missing data caused by data transmission interruptions or temporary sensor malfunctions, ensuring the continuity of the data sequence. The Isolation Forest algorithm learns the distribution patterns of normal data and accurately identifies invalid data outside the normal operating range, such as numerical abrupt changes caused by sensor malfunctions. Normalization processing through format conversion maps data of different dimensions and numerical ranges to the 0-1 interval. This data preprocessing avoids the impact of large numerical differences on the accuracy of subsequent feature extraction and model calculation.

[0052] The multi-dimensional data includes both electrical and non-electrical features. Non-electrical features include mechanical, environmental, and visual features. Electrical feature extraction employs time-frequency analysis to extract the time-frequency domain features of partial discharge signals from the electrical data, spectrum analysis to extract the frequency features of harmonic components, and trend analysis to extract the variation trends of voltage and current. Mechanical feature extraction uses vibration analysis to extract the frequency features of tower tilt, modal analysis to extract the natural frequency features of conductor vibration, and stress analysis to extract the damage features of hardware. Environmental feature extraction uses time series analysis to extract the variation trends of environmental parameters, extreme value analysis to extract the peak features of extreme environmental events, and correlation analysis to extract the coupling and correlation features of environmental factors. Visual feature extraction uses convolutional neural networks to extract the depth feature vector of the line appearance, and target detection algorithms to extract the category and location features of external intrusion targets. The time-frequency analysis method can employ wavelet transform to decompose the partial discharge signals in the electrical data into wavelet coefficients of different scales, from which time-frequency domain features such as energy entropy and peak factor are extracted. Spectrum analysis can employ Fast Fourier Transform to decompose voltage and current signals in the frequency domain, extracting features such as the frequency and amplitude of harmonic components.

[0053] Correspondingly, wavelet transform accurately reflects the intensity and characteristics of partial discharge. After frequency domain decomposition of the voltage and current signals using Fourier transform, the presence of harmonic pollution in the line is characterized.

[0054] Step 203: Determine the risk level of the transmission line based on the preset risk characteristic weights, electrical characteristics and non-electrical characteristics of the transmission line.

[0055] Specifically, a comprehensive risk score is determined based on the electrical and non-electrical characteristics of the transmission line, and the risk level of the transmission line is determined based on the comprehensive risk score and the preset risk range.

[0056] Step 204: Determine the fusion characteristics of the transmission line based on its electrical and non-electrical characteristics.

[0057] Specifically, non-electrical features include mechanical features, environmental features, and visual features. These four types of features are mapped to a unified feature space through a preset mapping relationship to obtain the fused features of the transmission line.

[0058] Step 205: Determine the risk assessment results based on the risk level and fusion characteristics of the transmission lines.

[0059] Specifically, based on the fusion characteristics of transmission lines, the future changing trends of transmission lines are determined. These fusion characteristics are then input into a time series analysis model to obtain the future risk trends of the transmission lines. The time series analysis model can be an LSTM model.

[0060] For electrical characteristics, the mean rate of change of voltage and current is calculated using the sliding window method, and the future trend of electrical characteristics is determined based on the mean rate of change.

[0061] For mechanical characteristics, a Fourier transform is performed on the tower tilt value to obtain tilt frequency and amplitude characteristics. Based on these tilt frequency and amplitude characteristics, the future trend of the tower is determined, including whether the tower is loosening or experiencing foundation settlement. Acceleration signals of conductor vibration are collected, and a polynomial fitting method is used to determine the frequency characteristics of the conductor. Based on these frequency characteristics, the future trend of the conductor is determined, including whether the conductor vibration exceeds the safe range. Trend fitting and abrupt change detection are performed on the stress values ​​of the fittings to determine the damage characteristics of the stress data. Based on these damage characteristics, the future trend of the fittings is determined, including the degree of fatigue damage.

[0062] For environmental characteristics, peak data under extreme conditions are analyzed within a sliding window time to determine the peak size and duration. Based on the peak size and duration, the impact of extreme conditions on electrical and non-electrical characteristics is determined. Pearson correlation coefficients are calculated among the environmental data to determine the correlation characteristics between them. The peak size, duration, and correlation characteristics between environmental data under extreme conditions are then input into the ARIMA model to predict future environmental data.

[0063] For visual features, a convolutional neural network (CNN) is used to perform multi-layer convolution and pooling operations on the line appearance data to extract the depth feature vector of the line appearance. The CNN can be ResNet50. For object detection, a multi-scale feature fusion and bounding box regression are performed on the external intrusion target image to extract the category and location features of the external intrusion target. The object detection algorithm can be YOLOv8.

[0064] The risk assessment results are determined based on the risk level of the transmission line and the future risk trends corresponding to each characteristic.

[0065] Accordingly, by processing visual features through convolutional neural networks, a depth feature vector of the line's appearance is obtained, which can accurately identify subtle appearance defects. Target detection algorithms provide a basis for timely removal or remedial measures.

[0066] Step 206: Based on the risk assessment results, determine the early warning information for the transmission lines.

[0067] Specifically, a deep learning algorithm combining CNN and BiLSTM is used to determine the fault risk type based on the future risk trends corresponding to each feature and the risk level of the transmission line. CNN extracts the spatial information of the features, while BiLSTM determines the temporal correlation of the data. The fault risk types include at least common fault types such as conductor damage, insulator aging, tower tilting, and external intrusion. Based on the fault risk type, early warning information for the transmission line is generated.

[0068] The early warning information includes three levels: low risk is alerted via system message push, medium risk is notified to relevant personnel via SMS, and high risk is simultaneously triggered by SMS and telephone alerts and linked to the operation and maintenance dispatch center to ensure that the early warning information is delivered to relevant personnel in a timely manner.

[0069] Correspondingly, by predicting future environmental data, the changing trends of the future environment are characterized, providing data reference for the generation of early warning information. Based on the changing trends of the future environment, potential faults in transmission lines are identified, thus realizing early warning for transmission lines.

[0070] Based on the above embodiments, as an implementable approach, in one embodiment, the fusion characteristics of the transmission line are determined according to its electrical and non-electrical characteristics, including: Step 2031: Determine at least one characteristic value based on the electrical and non-electrical characteristics of the transmission line; Step 2032: Determine the comprehensive risk score at the current moment based on the preset risk feature weights and at least one feature normalization value; Step 2033: Determine the risk level at the current moment based on the comprehensive risk score at the current moment.

[0071] Specifically, in one embodiment, the overall risk score at the current moment can be determined based on the following formula:

[0072] in, The overall risk score at the current moment. Based on the preset feature weight coefficients of the k-th feature, Let k be the eigenvalue of the k-th feature. The total number of features.

[0073] Specifically, Determined through expert experience and the importance of features, Based on the electrical and non-electrical characteristics of the transmission line, at least one normalized value is determined as a characteristic value. This is used in transmission line risk early warning applications. You can take 20.

[0074] Based on the overall risk score, the risk level is determined as low when the overall risk score is in the first risk range (0, 0.3), medium when the overall risk score is in the second risk range (0.3, 0.7), and high when the overall risk score is in the third risk range (0.7, 1). The risk ranges are determined based on historical fault data and operational experience.

[0075] Accordingly, the current risk level of the transmission line was determined by the risk range.

[0076] Based on the above embodiments, as an implementable approach, in one embodiment, the fusion characteristics of the transmission line are determined according to its electrical and non-electrical characteristics, including: Step 2041: Determine the electrical and non-electrical characteristics with unified dimensions based on the electrical and non-electrical characteristics of the transmission line; Step 2042: Determine the association weights of electrical features and non-electrical features based on the dimensionally unified electrical features, non-electrical features, and the preset attention weight matrix; Step 2043: Determine the fusion characteristics of the transmission line based on the association weights, unified electrical and non-electrical characteristics.

[0077] Specifically, non-electrical features include mechanical features, environmental features, and visual features. These four types of features are mapped to a unified 512-dimensional feature space through a linear transformation matrix based on a preset mapping relationship.

[0078] Based on dimensionally unified electrical and non-electrical features, eight attention heads are set up. Each attention head is used to capture the correlation patterns between different types of features. By calculating the similarity matrix between features, the correlation weights of electrical and non-electrical features are dynamically assigned. Features closely related to line safety risks are assigned high weight values, while irrelevant or secondary features are assigned low weight values. According to the correlation weights, the electrical and non-electrical features are weighted to obtain the weighted electrical and non-electrical features. Then, residual connections are performed on the weighted features, and the input features are directly added to the weighted features to generate a fused feature vector.

[0079] Accordingly, by setting appropriate dimensionality values, the core information of each feature can be fully preserved while avoiding excessive computational burden due to high dimensionality. Residual connections alleviate the gradient vanishing problem during deep network training, ensuring the complete transmission of feature information. The fused feature vector integrates key information from four types of features, comprehensively and accurately representing the overall safety status of the transmission line, providing a data foundation for risk assessment.

[0080] Based on the above embodiments, as one implementable approach, in one embodiment, the transmission line is communicatively connected to an edge computing node and a cloud server to acquire multi-dimensional data of the transmission line, including: Step 2011: Determine the complexity of the multi-dimensional data based on the preset complexity index and the multi-dimensional data of the transmission line; Step 2012: Obtain the computing load and network communication quality of the edge computing nodes; Step 2013: Determine the computing capacity of the edge computing nodes based on the computing load and network communication quality; Step 2014: Determine the preprocessing mode of multi-dimensional data based on the computing capacity of the edge computing nodes and the complexity of the multi-dimensional data; the preprocessing mode includes local processing, cloud processing and hybrid processing.

[0081] Specifically, the complexity of the multi-dimensional data is determined based on the multi-dimensional data of the transmission lines and preset complexity indicators. The data is divided according to the regions of the transmission lines, with each edge computing node responsible for processing the line data of a specific region. Computational load is characterized by CPU utilization and memory utilization. Network communication quality is characterized by network bandwidth, network latency, and packet loss rate. The data for computational load and network communication quality are normalized and weighted to obtain the computational capacity of the edge computing nodes.

[0082] Specifically, in one embodiment, when the complexity is not greater than a preset first complexity threshold and the computing capacity is greater than a preset first capacity threshold, the preprocessing mode is determined to be local processing; wherein, local processing represents multi-dimensional data being computed at edge computing nodes.

[0083] Specifically, multiple multi-dimensional data are normalized and weighted to obtain the complexity of the multi-dimensional data.

[0084] If the complexity is no greater than a preset first complexity threshold and the computational capacity is greater than a preset first capacity threshold, the preprocessing mode is determined to be local processing.

[0085] If the complexity is greater than a preset first complexity threshold and the computing capacity is less than or equal to a preset first capacity threshold, the preprocessing mode is determined to be cloud processing, where cloud processing means that multi-dimensional data is computed on a cloud server.

[0086] In other cases, based on preset multi-dimensional anomaly indicators, abnormal and non-abnormal data are identified in the multi-dimensional data. Abnormal data is sent to the cloud server for processing, while non-abnormal data is processed at the edge computing node.

[0087] Accordingly, the preprocessing mode is dynamically determined based on the computational volume of multi-dimensional data and the computational capacity of edge computing nodes. This avoids the problem of high processing latency at edge computing nodes caused by the computational volume of multi-dimensional data exceeding the computational capacity. Furthermore, by using a hybrid processing approach, computational resources are rationally allocated, thereby improving computational efficiency.

[0088] Specifically, in one embodiment, the edge computing node realizes risk prediction of the transmission line through a risk warning model, wherein the risk warning model realizes risk warning of the transmission line based on the steps of any of the above-mentioned transmission line risk warning methods.

[0089] Edge computing nodes train models based on multi-dimensional data within their corresponding range, obtain local gradient parameters for that edge computing node, and then send the local gradient parameters to the central node.

[0090] For example, 10 edge computing nodes can be set up to cover areas with different geographical environments and network structures. During the model training phase, each edge computing node trains the model based on locally collected data, using mini-batch gradient descent with a batch size of 32 and 10 training epochs. Only local gradient parameters are calculated during training. The data is encrypted using homomorphic encryption technology before being uploaded to the central node, thus avoiding security risks associated with centralized data storage.

[0091] The central node receives encrypted local gradient parameters sent by multiple edge computing nodes. After decrypting the encrypted local gradient parameters, it obtains the local gradient parameters corresponding to each edge computing node. Based on the local gradient parameters, it determines the global gradient parameters and sends the global gradient parameters to each edge computing node.

[0092] The global gradient parameters are determined based on the following formula:

[0093] in, Represents the global gradient parameters. This represents the total number of edge computing nodes. Indicates the first Local gradient parameters of each edge computing node.

[0094] Edge computing nodes receive global gradient parameters and update local gradient parameters based on the global gradient parameters and corresponding local electrical and non-electrical characteristics, such as the current line's operating environment parameters (temperature, humidity, wind speed, etc.) and structural characteristics (tower type, conductor type, etc.). This allows edge computing nodes to train models based on the updated local gradient parameters, improving the accuracy of risk warnings in specific scenarios and enabling dynamic optimization and upgrading of the model.

[0095] For example, such as Figure 3 The diagram shown illustrates an exemplary transmission line risk early warning method provided in this application. It involves real-time collection of multi-dimensional data, including electrical and non-electrical data. The multi-dimensional data undergoes preprocessing, including cleaning, quality assessment, and normalization. Based on the preprocessed multi-dimensional data, electrical and non-electrical characteristics are determined. Based on these characteristics, the integrated characteristics of the transmission line are determined. The risk level is determined based on the multi-dimensional data. Based on the integrated characteristics of the transmission line, the future risk trend is determined. Based on the risk level and future risk trend, a risk assessment result is determined. Based on the risk assessment result, early warning information is determined and fed back to the user. The model parameters of the edge computing nodes are optimized based on operational data.

[0096] Correspondingly, training using local data through edge computing nodes avoids privacy leaks caused by centralized data management, and multi-node joint training is achieved by having a central node responsible for model updates, thus improving the model's adaptability.

[0097] For example, such as Figure 4 The diagram shown is a schematic representation of an exemplary transmission line risk early warning system provided in this application embodiment. The transmission line risk early warning system includes a multi-source data acquisition module, a data preprocessing module, a multi-dimensional feature extraction module, a multi-modal fusion module, a risk assessment module, an early warning decision module, and a model optimization module.

[0098] The multi-source data acquisition module collects multi-dimensional data, and various types of sensors are deployed at multiple key monitoring points on the transmission line. Based on the environmental characteristics of the transmission line, the type and deployment location of the sensors are determined to ensure that all kinds of data related to the operation of the line can be collected in an all-round way, and the collected multi-dimensional data is sent to the data preprocessing module.

[0099] The data preprocessing module is deployed on edge computing nodes or cloud processors. It receives multi-dimensional data transmitted from multi-source data acquisition modules, completes tasks such as data cleaning, normalization, and quality assessment, transforms the original multi-dimensional data into standardized data, improves the processing efficiency of subsequent modules, and sends the preprocessed data to the multi-dimensional feature extraction module.

[0100] The multi-dimensional feature extraction module is deployed on a cloud server to extract features corresponding to data in each dimension. The multi-modal fusion module is deployed on a cloud server to receive various features output by the multi-dimensional feature extraction module, complete feature fusion through a specific algorithm, generate a fused feature vector reflecting the line status, and send the fused feature vector to the risk assessment module.

[0101] The risk assessment module determines the risk level and future risk trend of transmission lines based on fused feature vectors, and outputs comprehensive risk assessment results based on the risk level and future risk trend.

[0102] The early warning decision-making module includes a tiered early warning module, a solution generation module, and a visualization module. The tiered early warning module determines the fault type based on risk assessment results and generates corresponding early warning information. The solution generation module generates standardized handling procedures based on a preset knowledge base and early warning information. The visualization module displays the risk status to users through a map interface, dashboard interface, and trend curve interface, enabling users to take appropriate actions based on the early warning information. The preset knowledge base of the solution generation module stores standard handling procedures for various risk scenarios, covering personnel allocation, equipment preparation, operating procedures, safety precautions, etc. It automatically matches the optimal handling solution based on the risk identification results, directly guiding on-site operation and maintenance work. The map interface of the visualization module integrates a GIS system, intuitively marking the line location, risk point distribution, and severity. The dashboard interface centrally displays key information such as core monitoring indicators, risk scores, and fault types. The trend curve interface presents the changing trends of risk levels and key parameters over time, enabling operation and maintenance personnel to quickly grasp the line safety status.

[0103] The model optimization module collects the running data of each module, uses a federated learning framework to train and update multi-node models, and pushes the optimized parameters to the relevant modules, thereby improving the system's performance.

[0104] The transmission line risk early warning method provided in this application includes: acquiring multi-dimensional data of the transmission line; wherein the multi-dimensional data includes at least electrical data and non-electrical data; determining the electrical and non-electrical characteristics of the transmission line based on the multi-dimensional data; determining the risk level of the transmission line based on preset risk feature weights, the electrical and non-electrical characteristics of the transmission line; determining the integrated characteristics of the transmission line based on the electrical and non-electrical characteristics of the transmission line; determining the risk assessment result based on the risk level and the integrated characteristics of the transmission line; and determining the early warning information of the transmission line based on the risk assessment result. The method provided above, by acquiring multi-dimensional data of the transmission line, determining the electrical and non-electrical characteristics of the transmission line based on the electrical and non-electrical data represented by the multi-dimensional data, determining the risk level and integrated characteristics of the transmission line based on the electrical and non-electrical characteristics, further determining the risk assessment result of the transmission line, and determining the early warning information of the transmission line based on the risk assessment result, and by collecting non-electrical multi-dimensional data and combining it with the non-electrical characteristics corresponding to the non-electrical data to determine the early warning information, comprehensively considers multiple influencing factors on transmission line safety, thus improving the accuracy of the early warning information.

[0105] Furthermore, current data directly reflects the line load-bearing capacity, voltage data characterizes the stability of power supply, partial discharge signals indicate the presence of insulation defects, and electrical data characterizes the electrical operating status. Tower tilt values ​​characterize the overall stability of the towers, conductor vibration values ​​characterize the degree of conductor fatigue loss, hardware stress values ​​characterize the safety performance of connecting components, and mechanical structure data characterizes the safety of the line's mechanical structure. Temperature and humidity characterize the line's insulation performance, wind speed and icing conditions characterize potential hazards such as conductor galloping or icing, and precipitation characterizes the likelihood of tower foundation erosion. Line appearance characterizes line defects such as conductor corrosion and insulator damage, and external intrusion targets include objects that may threaten line safety, such as birds, drones, and construction machinery. This multi-dimensional data comprehensively reflects the main influencing factors facing line operation. By setting a reasonable acquisition frequency, the data ensures real-time reflection of the line status while avoiding the problem of high system computational load caused by collecting large amounts of data. Kalman filtering dynamically tracks data trends and accurately filters out noise data caused by sensor errors and external electromagnetic interference. Linear interpolation can be used to smoothly supplement missing data caused by data transmission interruption or temporary sensor failure, based on valid data before and after the missing data, thus ensuring the continuity of the data sequence.

[0106] By employing the Isolation Forest algorithm, the distribution patterns of normal data are learned to accurately identify invalid data exceeding normal operating ranges, such as numerical abrupt changes caused by sensor malfunctions. Normalization processing through format conversion maps data of different dimensions and numerical ranges to the 0-1 interval. This data preprocessing avoids the impact of large numerical differences on the accuracy of subsequent feature extraction and model calculations. Wavelet transform accurately reflects the intensity and characteristics of partial discharge. Fourier transform is used to perform frequency domain decomposition of voltage and current signals, characterizing the presence of harmonic pollution problems in the line. Convolutional neural networks process visual features to obtain a depth feature vector of the line's appearance, enabling precise identification of subtle appearance defects. Target detection algorithms provide a basis for timely removal or disposal measures. Predicted future environmental data characterizes future environmental trends, providing data reference for generating early warning information. Based on these trends, potential faults in transmission lines are identified, achieving early warning for transmission lines. Risk intervals determine the current risk level of the transmission line. By reasonably setting dimensional values, the core information of each feature is fully preserved while avoiding excessive computational burden due to high dimensionality. Residual connections mitigate the vanishing gradient problem in deep network training, ensuring the complete transmission of feature information. Fusion feature vectors integrate key information from four types of features, comprehensively and accurately representing the overall safety status of transmission lines and providing a data foundation for risk assessment. The preprocessing mode is dynamically determined based on the computational load of multi-dimensional data and the computational capacity of edge computing nodes, avoiding the problem of high processing latency at edge computing nodes due to the computational load exceeding the computational capacity. Furthermore, a hybrid processing approach rationally allocates computational resources, improving computational efficiency. Training with local data at edge computing nodes avoids privacy leaks caused by centralized data management. Model updates by a central node enable multi-node collaborative training, improving model adaptability.

[0107] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method.

[0108] An embodiment of this application also provides a transmission line risk early warning device for executing the transmission line risk early warning method provided in the above embodiments.

[0109] like Figure 5 The diagram shown is a structural schematic of the transmission line risk early warning device provided in this embodiment of the application. The transmission line risk early warning device 50 includes: an acquisition module 501, a first determination module 502, a second determination module 503, a third determination module 504, a fourth determination module 505, and an early warning determination module 506.

[0110] The system comprises the following modules: an acquisition module for acquiring multi-dimensional data of the transmission line, including at least electrical and non-electrical data; a first determination module for determining the electrical and non-electrical characteristics of the transmission line based on the multi-dimensional data; a second determination module for determining the risk level of the transmission line based on preset risk characteristic weights, the electrical and non-electrical characteristics of the transmission line; a third determination module for determining the integrated characteristics of the transmission line based on the electrical and non-electrical characteristics of the transmission line; a fourth determination module for determining the risk assessment result based on the risk level and the integrated characteristics of the transmission line; and an early warning determination module for determining early warning information for the transmission line based on the risk assessment result.

[0111] Specifically, in one embodiment, the second determining module is specifically used for: Based on the electrical and non-electrical characteristics of the transmission line, at least one characteristic value is determined; based on the preset risk characteristic weights and at least one characteristic normalization value, the comprehensive risk score at the current moment is determined; based on the comprehensive risk score at the current moment, the risk level at the current moment is determined.

[0112] Specifically, in one embodiment, the second determining module is further configured to: The overall risk score at the current moment is determined based on the following formula:

[0113] in, The overall risk score at the current moment. Based on the preset feature weight coefficients of the k-th feature, Let be the eigenvalue of the k-th feature, and n be the total number of features.

[0114] Specifically, in one embodiment, the third determining module is specifically used for: Based on the electrical and non-electrical characteristics of the transmission line, determine the electrical and non-electrical characteristics with unified dimensions; based on the unified electrical and non-electrical characteristics and the preset attention weight matrix, determine the association weights of the electrical and non-electrical characteristics; based on the association weights, the unified electrical and non-electrical characteristics, determine the fusion characteristics of the transmission line.

[0115] Specifically, in one embodiment, the acquisition module is specifically used for: Based on preset complexity indicators and multi-dimensional data of transmission lines, the complexity of multi-dimensional data is determined; the computing load and network communication quality of edge computing nodes are obtained; the computing capacity of edge computing nodes is determined based on computing load and network communication quality; and the preprocessing mode of multi-dimensional data is determined based on the computing capacity of edge computing nodes and the complexity of multi-dimensional data. Among them, the preprocessing mode includes local processing, cloud processing and hybrid processing.

[0116] Specifically, in one embodiment, the acquisition module is further configured to: If the complexity is no greater than the preset first complexity and the comprehensive score of computing power is greater than the preset first capability threshold, the preprocessing mode is determined to be local processing; where local processing means that multi-dimensional data is computed at edge computing nodes.

[0117] Specifically, in one embodiment, the acquisition module further includes: Non-electrical data includes mechanical structure data, environmental impact data, and visual monitoring data. Mechanical structure data includes tower tilt values, conductor vibration values, and hardware stress values. Environmental impact data includes temperature, humidity, wind speed, icing status data, and precipitation. Visual monitoring data includes line appearance and external intrusion targets.

[0118] For a description of the features in the embodiment corresponding to the transmission line risk early warning device, please refer to the relevant description of the embodiment corresponding to the transmission line risk early warning method, which will not be repeated here.

[0119] Embodiments of this application also provide an electronic device, such as... Figure 6 The diagram shown is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, including a processor 10 and a memory 20. The memory 20 stores a computer program, and the processor 10 is configured to run the computer program to execute the steps in any of the above-described embodiments of the transmission line risk warning method.

[0120] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above embodiments of the transmission line risk warning method when it is run.

[0121] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0122] The embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above embodiments of the transmission line risk warning method.

[0123] Embodiments of this application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in any of the above embodiments of the transmission line risk warning method.

[0124] Any of the components, modules, units, parts, methods, and operations described herein can be implemented using software, firmware, hardware (e.g., fixed logic circuitry), manual processing, or any combination thereof. Alternatively or additionally, any functionality described herein can be executed at least in part by one or more hardware logic components, such as, but not limited to, a central processing unit (CPU), a field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), an application-specific standard product (ASSP), a system-on-a-chip (SoC), a complex programmable logic device (CPLD), a microprocessor (MCU), etc. The terms "system," "computing device," or "apparatus" as used herein encompass various means, devices, and machines for processing data, including, for example, one or more programmable processors, computers, SoCs, or combinations thereof. The apparatus may also include code that creates an execution environment for the computer program in question, such as code constituting processor firmware, a protocol stack, a database management system, an operating system, a cross-platform runtime environment, a virtual machine, or one or more combinations thereof. The aforementioned computer program (also known as a program, software, software application, app, script, or code) can be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, and can be deployed in any form, including as a standalone program or as a module, component, subroutine, object, or other unit suitable for a computing environment.

[0125] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0126] The above provides a detailed description of a transmission line risk early warning method, device, electronic equipment, and storage medium provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only intended to help understand the method and core ideas of this application. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. A method for early warning of risks in power transmission lines, characterized in that, The method includes: Acquire multi-dimensional data of transmission lines; wherein the multi-dimensional data includes at least electrical data and non-electrical data; Based on the multi-dimensional data, the electrical and non-electrical characteristics of the transmission line are determined; The risk level of the transmission line is determined based on preset risk characteristic weights and the electrical and non-electrical characteristics of the transmission line. Based on the electrical and non-electrical characteristics of the transmission line, the integration characteristics of the transmission line are determined; The risk assessment results are determined based on the risk level of the transmission line and the fusion characteristics of the transmission line; Based on the risk assessment results, early warning information for the transmission line is determined.

2. The transmission line risk early warning method according to claim 1, characterized in that, The step of determining the risk level of the transmission line based on preset risk characteristic weights and the electrical and non-electrical characteristics of the transmission line includes: Based on the electrical and non-electrical characteristics of the transmission line, at least one characteristic value is determined; The current risk score is determined based on the preset risk feature weights and at least one feature normalization value. The risk level at the current moment is determined based on the comprehensive risk score at the current moment.

3. The transmission line risk early warning method according to claim 2, characterized in that, The step of determining the comprehensive risk score at the current moment based on the preset risk feature weights and at least one feature value includes: The overall risk score at the current moment is determined based on the following formula: in, The overall risk score at the current moment. Based on the preset feature weight coefficients of the k-th feature, Let be the eigenvalue of the k-th feature, and n be the total number of features.

4. The transmission line risk early warning method according to claim 1, characterized in that, Determining the combined characteristics of the transmission line based on its electrical and non-electrical characteristics includes: Based on the electrical and non-electrical characteristics of the transmission line, determine the electrical and non-electrical characteristics with unified dimensions; Based on the dimensionally unified electrical features, non-electrical features, and a preset attention weight matrix, the association weights of the electrical features and non-electrical features are determined; The fusion characteristics of the transmission line are determined based on the associated weights, unified electrical and non-electrical characteristics.

5. The transmission line risk early warning method according to claim 1, wherein the transmission line is communicatively connected to an edge computing node and a cloud server, characterized in that, The acquisition of multi-dimensional data of transmission lines also includes: The complexity of the multi-dimensional data is determined based on a preset complexity index and multi-dimensional data of the transmission line. Obtain the computing load and network communication quality of edge computing nodes; The computing capacity of the edge computing node is determined based on the computing load and network communication quality. Based on the computing capacity of the edge computing node and the complexity of the multi-dimensional data, a preprocessing mode for the multi-dimensional data is determined; wherein, the preprocessing mode includes local processing, cloud processing, and hybrid processing.

6. The transmission line risk early warning method according to claim 5, characterized in that, The preprocessing mode for the multi-dimensional data is determined based on the comprehensive score of the computing power of the edge computing nodes and the complexity of the multi-dimensional data; wherein the preprocessing mode includes local processing, cloud processing, and hybrid processing, including: If the complexity is not greater than a preset first complexity and the comprehensive score of computing power is greater than a preset first capability threshold, the preprocessing mode is determined to be local processing; wherein, local processing indicates that the multi-dimensional data is calculated at the edge computing node.

7. The transmission line risk early warning method according to claim 1, characterized in that, The non-electrical data includes mechanical structure data, environmental impact data, and visual monitoring data. The mechanical structure data includes tower tilt values, conductor vibration values, and hardware stress values. The environmental impact data includes temperature, humidity, wind speed, icing status data, and precipitation. The visual monitoring data includes the appearance of the line and external intrusion targets.

8. A transmission line risk early warning device, characterized in that, The device includes: The acquisition module is used to acquire multi-dimensional data of the transmission line; wherein the multi-dimensional data includes at least electrical data and non-electrical data; The first determining module is used to determine the electrical and non-electrical characteristics of the transmission line based on the multi-dimensional data. The second determining module is used to determine the risk level of the transmission line based on preset risk feature weights and the electrical and non-electrical characteristics of the transmission line; The third determining module is used to determine the fusion characteristics of the transmission line based on its electrical and non-electrical characteristics. The fourth determining module is used to determine the risk assessment result based on the risk level of the transmission line and the fusion characteristics of the transmission line; The early warning module is used to determine early warning information for the transmission line based on the risk assessment results.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the transmission line risk warning method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, it implements the steps of the transmission line risk warning method as described in any one of claims 1 to 7.