A Visualized Multi-Dimensional Risk Detection System and Method for Transmission Lines
By performing offset analysis and transmission interference analysis on the UAV inspection status data, the data acquisition accuracy and transmission quality of power transmission line risk detection have been improved. This has solved the problems of insufficient image resolution and electromagnetic interference in UAV inspection, and enabled more accurate detection and visualization.
Patent Information
- Application Number
- CN202510436886.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-09
- Publication Date
- 2025-10-28
- Estimated Expiration
- 2045-04-09
Smart Images

Figure CN120373849B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of image data processing technology for power transmission lines, and in particular to a visualized multi-dimensional risk detection system and method for power transmission lines. Background Technology
[0002] Transmission lines are a crucial component of the power system, responsible for transmitting electrical energy from power plants to substations and end users. Their safe and stable operation is vital for ensuring power supply and maintaining the normal functioning of the social economy. However, transmission lines are typically widely distributed, long-distance, and exposed to the natural environment, making them susceptible to various factors such as natural disasters, external damage, and equipment aging. These factors can lead to line faults and even large-scale power outages. Therefore, risk detection of transmission lines is a key step in ensuring their safe operation. Through visualized, multi-dimensional risk detection of transmission lines, various potential threats can be effectively managed and predicted in the complex power system environment, ensuring the stable operation of the power grid, reducing accidents, and improving the overall security of the power system.
[0003] Existing multi-dimensional risk detection for power transmission lines collects various data, including temperature, vibration, meteorological data, and image data, using sensors, drones, and satellite remote sensing equipment. Deep learning algorithms (such as convolutional neural networks) are then used to analyze the image data, enabling rapid identification of line defects and faults. By combining real-time monitoring data with historical data, the risk level of the transmission line is dynamically assessed, allowing for the timely detection of potential fault risks. Furthermore, the visualization platform can provide decision-makers with real-time reports, early warning information, and maintenance recommendations, helping to develop more scientific maintenance and inspection plans. This visualized multi-dimensional risk detection of power transmission lines not only improves the safety, reliability, and operational efficiency of transmission lines but also promotes the intelligent and sustainable development of the power industry, holding profound significance in driving the digital and intelligent transformation of the power sector.
[0004] For example, the invention patent announcement CN118781095B discloses a method and system for monitoring localized heating in transmission lines, which includes: interpolating noise-reduced temperature data and enhanced thermal image data to obtain a target temperature matrix and a target thermal image matrix; fusing the temperature matrix and the thermal image matrix to obtain a fused temperature distribution matrix; performing threshold segmentation on the temperature distribution matrix to obtain localized high-temperature areas; locating and quantifying the localized high-temperature areas to obtain a set of heating location coordinates and a set of heating degree datasets; calculating a comprehensive heating index; determining the localized heating warning level based on the comprehensive heating index; matching the localized heating warning level with a pre-set transmission line BIM model to generate a visual warning model; and performing differentiated inspection scheme analysis on the visual warning model based on the localized heating warning level to generate a differentiated inspection and maintenance plan.
[0005] For example, the invention patent announcement CN116452594B discloses a method and system for visual monitoring and early warning of transmission line status, which includes: acquiring infrared images of the transmission line; obtaining the optimal Gaussian kernel size based on the gray-level variance and local variance of each superpixel region; obtaining the reference range and several first weight parameters for each blank cell, and obtaining several second weight parameters based on the gray-level value and position distribution of each pixel within the reference range; acquiring a guide image of the infrared image, obtaining the fill value of each blank cell based on the change in gray-level variance between the guide image and the infrared image, combined with the weight parameters, to obtain an upsampled image; obtaining the guide filter intensity parameter based on the difference in the local variance statistical histogram between the upsampled image and the infrared image; and obtaining a clear image through guide filtering to complete the visual monitoring of the transmission line status.
[0006] However, in the process of implementing the inventive technical solution in the embodiments of this application, it was found that the above-mentioned technology has at least the following technical problems:
[0007] During flight, drones may be affected by factors such as flight altitude and shooting angle, resulting in insufficient resolution or unsuitable perspective in the captured images, which in turn affects the clarity and detail capture of the images, and consequently affects the accuracy of the detection results.
[0008] Another factor to consider is that drones may encounter electromagnetic interference, radio frequency conflicts, or other external signal interference during flight, especially around power lines. Strong electromagnetic fields may affect the quality of data transmission, which in turn affects the final visualization, resulting in low data quality during the visualization of power line risk detection using drones. Summary of the Invention
[0009] This application provides a visualized multi-dimensional risk detection system and method for power transmission lines, which solves the problem of low data quality in the process of visualizing power transmission line risk detection through drone inspections in the prior art, and improves the data quality in the process of visualizing power transmission line risk detection through drone inspections.
[0010] This application provides a visualized multi-dimensional risk detection system for transmission lines, including: an inspection offset analysis module, a data acquisition interference analysis module, and a transmission interference analysis module. The inspection offset analysis module is used to acquire UAV inspection status data of a preset transmission line inspection area, and perform offset analysis between the UAV inspection status data and the preset inspection status data to obtain offset analysis results. The data acquisition interference analysis module is used to evaluate the accuracy of the risk detection data acquired during the inspection process based on the offset analysis results, and determine whether to perform inspection transmission interference analysis. If inspection transmission interference analysis is performed, the transmission quality of the risk detection data is detected and analyzed, and whether to perform risk detection data visualization.
[0011] Furthermore, the specific process for obtaining the offset analysis result by analyzing the degree of offset between the UAV inspection status data and the preset inspection status data is as follows: The UAV inspection offset within a preset time period is obtained; the UAV inspection offset is weighted and calculated with the corresponding offset analysis weight, and then combined with the inspection environment impact factor to obtain an environmental impact correction factor. The inspection offset correction factor is used to quantitatively evaluate the degree of offset between the UAV inspection status data and the preset inspection status data; if the inspection offset correction factor is within the preset offset threshold range obtained from the preset database, the offset analysis result for the corresponding preset time period is recorded as a normal offset to be corrected; if the inspection offset correction factor is not within the preset offset threshold range obtained from the preset database, the offset analysis result for the corresponding preset time period is recorded as an abnormal offset to be re-inspected.
[0012] Furthermore, the UAV inspection offset includes position offset, heading offset, flight altitude offset, and speed offset; the position offset represents the straight-line distance between the UAV inspection coordinates and the preset inspection coordinates; the heading offset represents the difference analysis result between the UAV inspection heading angle and the preset inspection heading angle; the flight altitude offset represents the difference analysis result between the UAV inspection relative altitude and the preset inspection relative altitude; the speed offset represents the difference analysis result between the UAV inspection speed and the preset inspection speed; the offset analysis weight includes position offset weight, heading offset weight, flight altitude offset weight, and speed offset weight; the inspection environment influence factor is used to correct the degree of influence of the inspection environment wind speed on the UAV inspection state offset analysis; the inspection offset correction factor represents the quantitative data of the degree of offset between the UAV inspection state data and the preset inspection state data, jointly quantified by the position offset, heading offset, flight altitude offset, and speed offset.
[0013] Furthermore, the specific steps for evaluating the accuracy of risk detection data collected during the inspection process by combining the offset analysis results are as follows: Quantitative data for the accuracy evaluation of risk detection data collected during the inspection process is obtained; the quantitative data for accuracy evaluation is weighted by performing a collection correction operation with the corresponding collection correction factor and the collection evaluation weight; then, the inspection deviation is corrected by combining the inspection offset correction factor to obtain the inspection collection evaluation value; the inspection collection evaluation value represents the quantitative data on the degree of influence of the inspection offset correction factor, the clarity of the collected image, the standard deviation of thermal imaging, and the point cloud density of the lidar on the accuracy evaluation of risk detection data collected during the inspection process.
[0014] Furthermore, the risk detection data includes image detection data, thermal imaging detection data, and lidar data; the accuracy evaluation quantification data includes the sharpness of the acquired image, the standard deviation of thermal imaging, and the lidar point cloud density; the acquisition correction factors include the acquisition illumination correction factor, the acquisition temperature correction factor, and the acquisition electromagnetic interference correction factor; the acquisition evaluation weights include the image acquisition evaluation weight, the thermal imaging acquisition evaluation weight, and the lidar acquisition evaluation weight; the inspection acquisition evaluation value is used to quantify the accuracy of the risk detection data acquired during the inspection process.
[0015] Furthermore, the specific process for determining whether to perform inspection transmission interference analysis is as follows: based on the preset inspection collection threshold range obtained from the preset database, determine whether the obtained inspection collection evaluation value is within the preset inspection collection threshold range; if the inspection collection evaluation value is within the preset inspection collection threshold range obtained from the preset database, then perform inspection transmission interference analysis and continuously monitor whether the inspection collection evaluation value is within the preset inspection collection threshold range; if the inspection collection evaluation value is not within the preset inspection collection threshold range obtained from the preset database, then do not perform inspection transmission interference analysis, and simultaneously remind the preset personnel to perform inspection collection data processing; the inspection collection data processing is used to perform image enhancement processing, thermal imaging data smoothing processing, and point cloud registration processing on the risk detection data.
[0016] Furthermore, the specific process of the inspection and data collection processing is as follows: A1, perform image enhancement processing on the image detection data, and determine whether the inspection and data collection evaluation value after image enhancement processing is within the preset inspection and data collection threshold range. If yes, stop the inspection and data collection processing and perform marking and transmission; otherwise, proceed to A2; A2, perform thermal imaging data smoothing processing on the thermal imaging detection data, and determine whether the inspection and data collection evaluation value after thermal imaging data smoothing processing is within the preset inspection and data collection threshold range. If yes, stop the inspection and data collection processing and perform marking and transmission; otherwise, proceed to A3; A3, perform point cloud registration processing on the lidar data, and mark and transmit the risk detection data after inspection and data collection processing; the marking and transmission is used to mark the risk detection data after inspection and data collection processing before transmission.
[0017] Furthermore, the specific steps for detecting and analyzing the transmission quality of risk detection data are as follows: Quantitative data on the transmission quality of risk detection data transmission is obtained, including the average transmission rate, transmission bit error rate, and signal strength at the receiving end; the results of the average transmission rate percentage analysis, the transmission bit error rate, and the signal strength at the receiving end are combined with the transmission electromagnetic interference correction factor to correct for environmental electromagnetic influence, and then weighted according to the corresponding transmission evaluation weights and corrected for inspection deviation using the inspection offset correction factor to obtain the inspection transmission evaluation value; the transmission evaluation weights include transmission rate evaluation weight, transmission accuracy evaluation weight, and transmission signal strength evaluation weight; the inspection transmission evaluation value represents the quantitative data on the degree of influence of the inspection offset correction factor, the average transmission rate, the transmission bit error rate, and the signal strength at the receiving end on the risk detection data transmission quality detection and analysis; the inspection transmission evaluation value is used to quantitatively analyze the transmission quality of risk detection data.
[0018] Furthermore, the specific process for determining whether to perform risk detection data visualization is as follows: based on the preset inspection transmission threshold range obtained from the preset database, determine whether the obtained inspection transmission evaluation value is within the preset inspection transmission threshold range; if the inspection transmission evaluation value is within the preset inspection transmission threshold range, then perform risk detection data visualization; if the inspection transmission evaluation value is not within the preset inspection transmission threshold range, then do not perform risk detection data visualization, and simultaneously remind preset personnel to optimize inspection transmission; the inspection transmission optimization includes inspection transmission data optimization and inspection transmission protocol optimization; the inspection transmission data optimization is used to reduce the amount of data transmitted during the inspection transmission process; the inspection transmission protocol optimization is used to perform transmission congestion control during the inspection transmission process.
[0019] This application provides a visualized multi-dimensional risk detection method for transmission lines, including the following steps: S1, acquiring UAV inspection status data of a preset transmission line inspection area, and performing offset analysis between the UAV inspection status data and the preset inspection status data to obtain offset analysis results; S2, evaluating the accuracy of the risk detection data collected during the inspection process based on the offset analysis results, and determining whether to perform inspection transmission interference analysis; S3, if inspection transmission interference analysis is performed, detecting and analyzing the transmission quality of the risk detection data, and determining whether to perform risk detection data visualization.
[0020] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:
[0021] 1. By combining the offset analysis results to evaluate the accuracy of risk detection data collected during the inspection process, and determining whether to perform inspection transmission interference analysis, and then, if inspection transmission interference analysis is performed, the transmission quality of the risk detection data is detected and analyzed to determine whether to perform risk detection data visualization. This enables the offset analysis results to analyze and judge the accuracy of risk detection data collection and transmission quality during the inspection process, thereby improving the data quality in the process of visualizing transmission line risk detection through UAV inspection, and effectively solving the problem of low data quality in the existing technology of visualizing transmission line risk detection through UAV inspection.
[0022] 2. By acquiring quantitative data on the accuracy of risk detection data collected during the inspection process, and then performing a weighted calculation on the quantitative data and the corresponding collection correction factor, the inspection deviation is corrected to obtain the inspection collection evaluation value. This achieves the correction of the interference of the drone inspection deviation on the accuracy of risk detection data collected during the inspection process, and thus realizes a more accurate assessment of the accuracy of risk detection data collected during the inspection process.
[0023] 3. By acquiring quantitative data on the transmission quality of the risk detection data transmission process, the results of the average transmission rate ratio analysis, the transmission bit error rate, the signal strength at the transmission receiver, and the transmission electromagnetic interference correction factor are combined with the environmental electromagnetic influence correction results, and the corresponding transmission evaluation weights are weighted and the inspection deviation is corrected with the inspection offset correction factor to obtain the inspection transmission evaluation value. This realizes the correction of the interference of the UAV inspection offset on the risk detection data transmission quality, and thus achieves a more accurate evaluation of the risk detection data transmission quality. Attached Figure Description
[0024] Figure 1 A schematic diagram of the structure of a visualized multi-dimensional risk detection system for transmission lines provided in this application embodiment;
[0025] Figure 2 This is a flowchart illustrating a visualized multi-dimensional risk detection method for power transmission lines, provided as an embodiment of this application. Detailed Implementation
[0026] This application provides a visualized multi-dimensional risk detection system and method for transmission lines, solving the problem of low data quality in the existing technology of visualizing transmission line risk detection through drone inspections. It acquires drone inspection status data for a preset transmission line inspection area, analyzes the offset between the drone inspection status data and the preset inspection status data to obtain offset analysis results, and then evaluates the accuracy of the risk detection data collected during the inspection process based on the offset analysis results to determine whether to perform inspection transmission interference analysis. If inspection transmission interference analysis is performed, the transmission quality of the risk detection data is detected and analyzed. Finally, it determines whether to perform risk detection data visualization, thus improving the data quality in the process of visualizing transmission line risk detection through drone inspections.
[0027] The technical solution in this application embodiment aims to address the problem of low data quality during the visualization of transmission line risk detection through drone inspections. The overall approach is as follows:
[0028] By combining the offset analysis results to evaluate the accuracy of the risk detection data collected during the inspection process and to determine whether to perform inspection transmission interference analysis, the transmission quality of the risk detection data is then tested and analyzed to determine whether to perform risk detection data visualization. This achieves the effect of improving the data quality in the process of visualizing transmission line risk detection through UAV inspection.
[0029] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.
[0030] like Figure 1The diagram shown is a structural schematic of a visualized multi-dimensional risk detection system for transmission lines provided in this application embodiment. This visualized multi-dimensional risk detection system for transmission lines includes: an inspection offset analysis module, a data acquisition interference analysis module, and a transmission interference analysis module. The inspection offset analysis module acquires UAV inspection status data for a preset transmission line inspection area and performs offset analysis between the UAV inspection status data and the preset inspection status data to obtain offset analysis results. The data acquisition interference analysis module evaluates the accuracy of the risk detection data acquired during the inspection process based on the offset analysis results and determines whether to perform inspection transmission interference analysis. The transmission interference analysis module, if inspection transmission interference analysis is performed, detects and analyzes the transmission quality of the risk detection data and determines whether to visualize the risk detection data.
[0031] In this embodiment, traditional transmission line risk inspection usually requires personnel to work at high altitudes or near power facilities, which often faces problems such as high cost, low efficiency, and high risk. The introduction of drone inspection technology has greatly changed this situation.
[0032] Equipped with high-definition cameras and other sensors (such as thermal imagers and lidar), drones can acquire data in real time, providing a basis for subsequent analysis and decision-making. Furthermore, drones can quickly complete inspection tasks in adverse weather conditions and complex terrain. They can also traverse long distances, monitoring power transmission lines in multiple regions along pre-set flight paths, providing real-time remote monitoring and data transmission, reducing the delays and omissions associated with manual inspections.
[0033] During UAV inspections, data quality directly affects the reliability of transmission line risk detection and the accuracy of decision-making. In practical applications, the algorithm in this application considers the impact of the degree of offset during UAV inspections on the accuracy of risk detection data collection and transmission quality (for example, offset may lead to insufficient regional monitoring during UAV inspections, especially in high-risk areas (such as conductor intersections), where offset may result in these areas not being effectively scanned or monitored). This effectively improves inspection efficiency, reduces labor costs, and enhances inspection coverage.
[0034] Furthermore, the specific process for obtaining the offset analysis results by performing offset analysis on the UAV inspection status data and the preset inspection status data is as follows: Obtain the UAV inspection offset within a preset time period, including position offset, heading offset, flight altitude offset, and speed offset; Perform weighted calculations on the UAV inspection offset and corresponding offset analysis weights, and then combine this with the inspection environment impact factor to obtain the inspection offset correction factor; Judge the inspection offset correction factor based on the preset offset threshold range obtained from the preset database; If the inspection offset correction factor is within the preset offset threshold range obtained from the preset database (including the boundary values of the preset offset threshold range), then the offset analysis result for the corresponding preset time period is recorded as a normal offset to be corrected; If the inspection offset correction factor is not within the preset offset threshold range obtained from the preset database, then the offset analysis result for the corresponding preset time period is recorded as an abnormal offset to be re-inspected.
[0035] It is important to understand that the preset inspection status data refers to the drone inspection-related parameters that are set in advance to ensure the smooth and effective inspection before the drone inspection. These parameters include preset inspection coordinates (latitude and longitude coordinates), preset inspection heading angle, preset inspection relative altitude, and preset inspection speed.
[0036] In addition, the preset offset threshold range is set by professionals according to industry standards. For example, the preset offset threshold range is set to 1.0 to 2.0. The position offset, heading offset, flight altitude offset and speed offset are all de-unitized.
[0037] The position offset represents the straight-line distance between the UAV inspection coordinates and the preset inspection coordinates. The UAV inspection coordinates are obtained through a geographic information system, and the position offset is obtained using GIS tools (such as QGIS, Quantum Geographic Information System).
[0038] The heading offset represents the difference analysis result between the UAV inspection heading angle and the preset inspection heading angle; the UAV inspection heading angle is obtained through the heading sensor, and the units of the UAV inspection heading angle and the preset inspection heading angle are consistent, both being degrees.
[0039] The method for obtaining the heading offset is as follows:
[0040] XH=|θ W -θ Y |;
[0041] In the formula, XH represents the heading offset, and θ W θ represents the heading angle of the drone inspection. Y This indicates the preset inspection heading angle.
[0042] The flight altitude offset represents the difference analysis results between the drone inspection relative altitude and the preset inspection relative altitude. The drone inspection relative altitude represents the vertical distance between the drone and the power transmission line. The drone inspection relative altitude is obtained by laser radar scanning. The units of the drone inspection relative altitude and the preset inspection relative altitude are the same, both in meters.
[0043] The method for obtaining the flight altitude offset is as follows:
[0044] XG = |G W -G Y |;
[0045] In the formula, XG represents the flight altitude offset, and G... W Indicates the relative altitude of the drone inspection, G Y This indicates the preset relative height for inspection.
[0046] The speed offset represents the result of the difference analysis between the UAV inspection speed and the preset inspection speed. The UAV inspection speed is obtained through the UAV flight control system. The unit of the UAV inspection speed and the preset inspection speed is the same, which is kilometers per hour.
[0047] The method for obtaining the velocity offset is as follows:
[0048] XV=|V W -V Y |;
[0049] In the formula, XV represents the velocity offset, and V W V represents the inspection speed of the drone. Y This indicates the preset inspection speed.
[0050] The offset analysis weights include position offset weight, heading offset weight, flight altitude offset weight, and speed offset weight. The position offset weight, heading offset weight, flight altitude offset weight, and speed offset weight respectively describe the degree of influence of the position offset, heading offset, flight altitude offset, and speed offset on the inspection offset correction factor. For example, the position offset, heading offset, flight altitude offset, and speed offset are input into the database into a preset mapping set of position offset, heading offset, flight altitude offset, and speed offset and their corresponding weight factors to obtain the corresponding weights.
[0051] The inspection environment impact factor is used to correct the degree of influence of the inspection environment wind speed on the UAV inspection state deviation analysis. The value range is [0, 1]. For example, the real-time inspection environment wind speed (obtained by an anemometer) is input into the preset mapping set of inspection environment wind speed and inspection environment impact factor in the database to obtain the inspection environment impact factor.
[0052] When the offset analysis result is a normal offset that needs to be corrected, the accuracy of the risk detection data collected during the inspection process is evaluated; when the offset analysis result is an abnormal offset that needs to be re-inspected, a re-inspection command is sent to the drone. If the number of re-inspection commands sent reaches the preset number, multiple drones are used for inspection. The preset number is set by professionals and is generally five times.
[0053] The method for obtaining the inspection offset correction factor is as follows:
[0054]
[0055] In the formula, ξ XJP ξ represents the inspection offset correction factor within a preset time period. JF ξ represents the environmental impact factor of the inspection, n represents the inspection time within the preset time period, n = 1, 2, ..., N, and N represents the total number of inspection times within the preset time period. a ξ represents the position offset weight. b ξ represents the heading offset weight. c ξ represents the weight of the flight altitude offset. d XW represents the velocity offset weight. n XH represents the position offset at the nth inspection time within a preset time period. n XG represents the heading offset at the nth inspection time within a preset time period. n XV represents the flight altitude offset at the nth inspection time within a preset time period. n This represents the speed offset at the nth inspection moment within a preset time period.
[0056] It should be added that the inspection offset correction factor represents the quantitative data on the degree of deviation between the UAV inspection status data and the preset inspection status data, which is jointly quantified by the position offset, heading offset, flight altitude offset, and speed offset. The inspection offset correction factor includes multiple parameters, and these parameters are related to each other and do not exist independently. For example, position offset is usually related to factors such as heading, flight altitude, and speed. If the UAV's heading deviates, the position will often change accordingly. That is, as the heading offset increases, the position offset also increases. At the same time, flight altitude offset and speed offset are also related. Excessive speed may cause the position to exceed the predetermined trajectory, thereby affecting the UAV's heading and altitude.
[0057] The inspection offset correction factor is used to quantitatively evaluate the degree of deviation between the UAV inspection status data and the preset inspection status data. As the position offset, heading offset, flight altitude offset, and speed offset increase, the inspection offset correction factor also increases, making the correction and adjustment of the inspection data collection and transmission process more significant. Through quantitative methods, the degree of deviation between the UAV inspection status data and the preset inspection status data is numerically evaluated, thereby enabling further correction of the UAV inspection data collection and transmission risk detection data process.
[0058] Furthermore, the specific steps for evaluating the accuracy of risk detection data collected during the inspection process based on the offset analysis results are as follows: obtain quantitative data for the accuracy evaluation of risk detection data collected during the inspection process; perform weighted calculations on the quantitative data for accuracy evaluation and the corresponding collection correction factor, and then combine the inspection offset correction factor to correct the inspection deviation and obtain the inspection collection evaluation value.
[0059] The method for obtaining the inspection and evaluation values is as follows:
[0060]
[0061] In the formula, XJC represents the inspection and evaluation value collected within a preset time period, ξ XJP δ1 represents the inspection offset correction factor within a preset time period, δ2 represents the image acquisition evaluation weight, δ3 represents the thermal imaging acquisition evaluation weight, and ξ represents the lidar acquisition evaluation weight. JG Indicates the illumination correction factor, ξ JW ξ represents the temperature correction factor for data acquisition. JD This represents the electromagnetic interference correction factor, where m represents the number of times risk detection data is collected during the inspection process, m = 1, 2, ..., M, and M represents the total number of times risk detection data is collected during the inspection process. TJQ m RJP represents the image clarity of the m-th risk detection data collection during the inspection process, JJD represents the standard deviation of thermal imaging, and JJD represents the point cloud density of the lidar.
[0062] It should be added that the risk detection data includes image detection data, thermal imaging detection data, and lidar data; image detection data is obtained through a high-resolution RGB camera on the drone, and thermal imaging detection data and lidar data are obtained through an infrared thermal imager and lidar sensor mounted on the drone.
[0063] The accuracy assessment quantification data includes the sharpness of the acquired image, the standard deviation of thermal imaging, and the point cloud density of the LiDAR. At the same time, the sharpness of the acquired image, the standard deviation of thermal imaging, and the point cloud density of the LiDAR have all undergone de-normalization processing. The sharpness of the acquired image is obtained by using gradient operators (such as Sobel and Canny edge detection), the standard deviation of thermal imaging is obtained by statistical analysis of thermal imaging detection data using libraries such as NumPy and OpenCV in Python, and the point cloud density of the LiDAR is obtained by using the PCL (Point Cloud Library) open source library tool.
[0064] The acquisition correction factors include acquisition illumination correction factors, acquisition temperature correction factors, and acquisition electromagnetic interference correction factors; wherein, the acquisition illumination correction factors, acquisition temperature correction factors, and acquisition electromagnetic interference correction factors all take values in the range of [0, 1]. For example, the corresponding acquisition illumination correction factors, acquisition temperature correction factors, and acquisition electromagnetic interference correction factors are obtained by inputting the real-time inspection acquisition illumination intensity (obtained through an illumination sensor), inspection acquisition temperature (obtained through a temperature sensor), and inspection acquisition electromagnetic interference intensity (obtained through an electromagnetic field detector) into a preset mapping set of real-time inspection acquisition illumination intensity, inspection acquisition temperature correction factor, and inspection acquisition electromagnetic interference intensity and their corresponding acquisition illumination correction factors, temperature correction factors, and electromagnetic interference correction factors into the database.
[0065] The acquisition evaluation weights include image acquisition evaluation weights, thermal imaging acquisition evaluation weights, and lidar acquisition evaluation weights; among them, the image acquisition evaluation weights, thermal imaging acquisition evaluation weights, and lidar acquisition evaluation weights all take values in the range of [0, 1] and their sum is 1. For example, the real-time acquired image sharpness, thermal imaging standard deviation, and lidar point cloud density are input into the database into a preset mapping set of acquired image sharpness, thermal imaging standard deviation, and lidar point cloud density and their respective weight factors to obtain the corresponding weights.
[0066] It is important to understand that the inspection and acquisition evaluation value represents the quantitative data on the impact of the inspection offset correction factor, the clarity of the acquired image, the standard deviation of thermal imaging, and the density of the lidar point cloud on the accuracy assessment of the risk detection data acquired during the inspection process. The inspection and acquisition evaluation value includes multiple parameters used to quantitatively assess the accuracy of the risk detection data acquired during the inspection process. As the clarity of the acquired image and the density of the lidar point cloud increase, the inspection and acquisition evaluation value also increases as the standard deviation of thermal imaging decreases.
[0067] Furthermore, the parameters in the inspection and evaluation values are interconnected and not independent. For example, higher LiDAR point cloud density typically provides more spatial information, which helps improve image clarity and the quality of thermal imaging data. High-density point cloud data can help improve object recognition accuracy in images, thereby improving image clarity. Simultaneously, LiDAR data density can help identify abnormal temperature distributions in thermal imaging, reducing the standard deviation of thermal imaging data. Moreover, the inspection offset correction factor corrects for the degree of inspection offset in image clarity, thermal imaging standard deviation, and LiDAR point cloud density. Therefore, this algorithm, through quantification, achieves a more accurate assessment of the accuracy of risk detection data collected during the inspection process.
[0068] Furthermore, the specific process for determining whether to perform inspection transmission interference analysis is as follows: Based on the preset inspection collection threshold range obtained from the preset database, determine whether the obtained inspection collection evaluation value is within the preset inspection collection threshold range; if the inspection collection evaluation value is within the preset inspection collection threshold range obtained from the preset database, then perform inspection transmission interference analysis and continuously monitor whether the inspection collection evaluation value is within the preset inspection collection threshold range (excluding the boundary values of the preset inspection collection threshold range); if the inspection collection evaluation value is not within the preset inspection collection threshold range obtained from the preset database, then do not perform inspection transmission interference analysis, and simultaneously remind the preset personnel to perform inspection collection data processing; inspection collection data processing is used to perform image enhancement processing, thermal imaging data smoothing processing, and point cloud registration processing on risk detection data.
[0069] In this embodiment, the preset inspection and collection threshold range is set by professionals according to the standards in the field. For example, the preset inspection and collection threshold range is set to 2.0 to 3.0. Among them, the inspection transmission interference analysis is to transmit risk detection data through satellite communication and to detect and analyze the transmission quality of risk detection data.
[0070] It should be added that the specific process for processing the inspection and data collection data is as follows: A1, perform image enhancement processing on the image detection data, and determine whether the inspection and data collection evaluation value after image enhancement processing is within the preset inspection and data collection threshold range. If yes, stop the inspection and data collection data processing and perform marking and transmission; otherwise, proceed to A2; A2, perform thermal imaging data smoothing processing on the thermal imaging detection data, and determine whether the inspection and data collection evaluation value after thermal imaging data smoothing processing is within the preset inspection and data collection threshold range. If yes, stop the inspection and data collection data processing and perform marking and transmission; otherwise, proceed to A3; A3, perform point cloud registration processing on the lidar data, and mark and transmit the risk detection data after inspection and data collection data processing; marking and transmission is used to mark the risk detection data after inspection and data collection data processing before transmission.
[0071] Specifically, image enhancement is achieved through histogram equalization, which uses OpenCV for equalization; thermal imaging data smoothing is achieved through mean filtering, which uses the blur() function in OpenCV for mean filtering; point cloud registration is achieved through the ICP (Iterative Closest Point) algorithm, which uses the Open3D library to align the LiDAR data to a common coordinate system; and tag transmission is performed using the scapy library in Python.
[0072] By combining the preset inspection and data collection threshold range to determine whether to perform inspection and data collection processing, a more accurate judgment of the accuracy of risk detection data collected during the inspection process is achieved, thereby improving the reliability of data collected during UAV inspections of power transmission lines.
[0073] Furthermore, the specific steps for detecting and analyzing the transmission quality of risk detection data are as follows: Quantitative data on the transmission quality of risk detection data is obtained, including the average transmission rate, bit error rate, and signal strength at the receiving end. The results of the average transmission rate percentage analysis, bit error rate, and signal strength at the receiving end are combined with the results of environmental electromagnetic interference correction factors, weighted by the corresponding transmission evaluation weights, and corrected for inspection deviation by the inspection offset correction factor to obtain the inspection transmission evaluation value. The transmission evaluation weights include transmission rate evaluation weight, transmission accuracy evaluation weight, and transmission signal strength evaluation weight.
[0074] The method for obtaining the inspection transmission evaluation value is as follows:
[0075]
[0076] In the formula, XJS represents the inspection transmission evaluation value within a preset time period, and ξ XJP This represents the inspection offset correction factor within a preset time period, where ξ1 represents the transmission rate evaluation weight, ξ2 represents the transmission accuracy evaluation weight, and ξ3 represents the transmission signal strength evaluation weight. Indicates the average transmission rate during inspection. The reference minimum transmission rate is represented by ξ, BER represents the bit error rate, and ξ represents the bit error rate. CD Indicates the transmission electromagnetic interference correction factor. This indicates the signal strength at the transmitting and receiving end.
[0077] In this embodiment, the average transmission rate is obtained by using network performance monitoring tools (such as Wireshark, NetFlow, iPerf), the bit error rate is obtained by using signal quality testing instruments (such as BERT, Bit Error Rate Tester), and the signal strength at the receiving end is obtained by using a wireless signal analyzer (such as a network spectrum analyzer). The reference minimum transmission rate is the minimum value of the summation and averaging of the collected historical average transmission rates. The units of the average transmission rate and the reference minimum transmission rate are the same, both being bits per second. The unit of the signal strength at the receiving end is decibels and milliwatts, and the signal strength at the receiving end is de-normalized before calculation.
[0078] The transmission electromagnetic interference correction factor is used to correct the impact of the electromagnetic interference intensity during the inspection transmission process on the quality detection and analysis of risk detection data transmission. For example, the transmission electromagnetic interference correction factor is obtained by inputting the electromagnetic interference intensity of the real-time inspection transmission process (obtained by an electromagnetic field detector) into a preset mapping set of electromagnetic interference intensity and transmission electromagnetic interference correction factor in the database.
[0079] The transmission rate assessment weight, transmission accuracy assessment weight, and transmission signal strength assessment weight respectively describe the degree of influence of the average inspection transmission rate, transmission bit error rate, and transmission receiver signal strength on the risk detection data transmission quality detection and analysis. For example, the real-time inspection average transmission rate, transmission bit error rate, and transmission receiver signal strength are input into the database into a preset mapping set of inspection average transmission rate, transmission bit error rate, transmission receiver signal strength, and their respective weight factors to obtain the corresponding weights.
[0080] It is important to understand that the inspection transmission evaluation value represents the quantitative data on the combined impact of the inspection offset correction factor, the average inspection transmission rate, the transmission bit error rate, and the signal strength at the transmission receiver on the risk detection data transmission quality detection and analysis. This algorithm comprehensively considers multiple parameters to obtain the inspection transmission evaluation value. As the average inspection transmission rate and the signal strength at the transmission receiver increase, the inspection transmission evaluation value increases accordingly. As the transmission bit error rate decreases, the inspection transmission evaluation value also increases accordingly.
[0081] It is also necessary to consider that the inspection transmission evaluation value is used to quantitatively analyze the transmission quality of risk detection data. The various parameters included are interconnected and not independent. For example, signal strength is usually a key factor affecting transmission rate. Strong signals help increase transmission rate, while weak signals may lead to a decrease in rate. At the same time, good signal transmission reduces bit errors; that is, as the signal strength at the receiving end increases, the transmission bit error rate decreases. Furthermore, the inspection offset correction factor corrects for the average inspection transmission rate, the signal strength at the receiving end, and the transmission bit error rate according to the corresponding inspection offset. In summary, through the quantitative analysis of the risk detection data transmission quality, a more accurate assessment of the risk detection data transmission quality is achieved.
[0082] Furthermore, the specific process for determining whether to perform risk detection data visualization is as follows: Based on the preset inspection transmission threshold range obtained from the preset database, determine whether the obtained inspection transmission evaluation value is within the preset inspection transmission threshold range (excluding the boundary values of the preset inspection transmission threshold range); if the inspection transmission evaluation value is within the preset inspection transmission threshold range, then perform risk detection data visualization; if the inspection transmission evaluation value is not within the preset inspection transmission threshold range, then do not perform risk detection data visualization, and simultaneously remind the preset personnel to optimize the inspection transmission; inspection transmission optimization includes inspection transmission data optimization and inspection transmission protocol optimization; inspection transmission data optimization is used to reduce the amount of data transmitted during the inspection transmission process; inspection transmission protocol optimization is used to control transmission congestion during the inspection transmission process.
[0083] In this embodiment, the preset inspection transmission threshold range is set by professionals according to industry standards. For example, the preset inspection transmission threshold range is set to 1.0 to 3.0. Among them, risk detection data visualization refers to the visualization processing of risk detection data through visualization tools. Specifically, image detection data is visualized through image processing libraries (such as matplotlib and OpenCV in Python), thermal imaging detection data is visualized through visualization tools (such as heatmaps), and LiDAR data is visualized through visualization tools (such as PCL and Point Cloud Library).
[0084] The optimization of inspection transmission data involves compressing risk detection data transmitted during the inspection process using data compression algorithms (such as ZIP), thereby reducing the volume of risk detection data and the amount of data transmitted during the inspection process. The optimization of the inspection transmission protocol is achieved by using an adaptive congestion avoidance algorithm to dynamically adjust the data transmission rate in real time based on the network congestion status. By combining the preset inspection transmission threshold range for visual judgment of risk detection data, a more accurate judgment of the quality of risk detection data transmission is achieved, thus improving the reliability of data transmission during UAV inspections of power transmission lines.
[0085] like Figure 2 The diagram shows a flowchart of a visualized multi-dimensional risk detection method for transmission lines provided in this application embodiment. The method includes the following steps: S1, acquiring UAV inspection status data of a preset transmission line inspection area, and performing offset analysis between the UAV inspection status data and the preset inspection status data to obtain offset analysis results; S2, evaluating the accuracy of the risk detection data collected during the inspection process based on the offset analysis results, and determining whether to perform inspection transmission interference analysis; S3, if inspection transmission interference analysis is performed, detecting and analyzing the transmission quality of the risk detection data, and determining whether to perform risk detection data visualization.
[0086] In this embodiment, by analyzing the degree of deviation of the UAV inspection and evaluating the dual interference during the process of collecting and transmitting risk detection data based on the deviation analysis results, the reliability of data in the process of risk detection of transmission lines through UAV inspection is improved, thereby improving the data quality in the process of visualizing risk detection of transmission lines through UAV inspection.
[0087] In summary, this application embodiment evaluates the accuracy of risk detection data collected during the inspection process by combining the offset analysis results, and determines whether to perform inspection transmission interference analysis. If inspection transmission interference analysis is performed, the transmission quality of the risk detection data is detected and analyzed to determine whether to perform risk detection data visualization. This enables the offset analysis results to analyze and judge the accuracy of risk detection data collection and transmission quality during the inspection process, thereby improving the data quality in the process of visualizing transmission line risk detection through UAV inspection. This effectively solves the problem of low data quality in the prior art when visualizing transmission line risk detection through UAV inspection.
[0088] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0089] This invention is described with reference to flowchart illustrations and / or block diagrams of systems, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0090] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.
[0091] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0092] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.
[0093] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.
Claims
1. A visualized multi-dimensional risk detection system for transmission lines, characterized in that, include: Inspection offset analysis module, data acquisition interference analysis module, and transmission interference analysis module; The inspection offset analysis module is used to obtain the UAV inspection status data of the preset transmission line inspection area, and to perform offset analysis between the UAV inspection status data and the preset inspection status data to obtain the offset analysis result. The specific process for analyzing the offset between the UAV inspection status data and the preset inspection status data to obtain the offset analysis result is as follows: Obtain the drone inspection offset within a preset time period; After weighting the UAV inspection offset and the corresponding offset analysis weight, it is combined with the inspection environment impact factor to obtain the inspection offset correction factor. The inspection offset correction factor is used to quantitatively evaluate the degree of offset between the UAV inspection status data and the preset inspection status data. If the inspection offset correction factor is within the preset offset threshold obtained from the preset database, the offset analysis result for the corresponding preset time period will be recorded as a normal offset to be corrected. If the inspection offset correction factor is not within the preset offset threshold obtained from the preset database, the offset analysis result for the corresponding preset time period will be recorded as an abnormal offset to be re-inspected. The UAV inspection offset includes position offset, heading offset, flight altitude offset, and speed offset; The position offset represents the straight-line distance between the UAV inspection coordinates and the preset inspection coordinates; The heading offset represents the result of the difference analysis between the UAV inspection heading angle and the preset inspection heading angle; The flight altitude offset represents the analysis result of the difference between the relative altitude of the UAV inspection and the preset relative altitude of the inspection. The speed offset represents the result of the difference analysis between the UAV inspection speed and the preset inspection speed; The offset analysis weights include position offset weights, heading offset weights, flight altitude offset weights, and speed offset weights; The inspection environment impact factor is used to correct the degree of influence of wind speed in the inspection environment on the UAV inspection state deviation analysis. The inspection offset correction factor represents the quantitative data on the degree of deviation between the UAV inspection status data and the preset inspection status data, which is jointly quantified by the position offset, heading offset, flight altitude offset, and speed offset. The data acquisition interference analysis module is used to evaluate the accuracy of the risk detection data acquired during the inspection process by combining the offset analysis results, and to determine whether to perform inspection transmission interference analysis. The transmission interference analysis module is used to detect and analyze the transmission quality of risk detection data if inspection transmission interference analysis is performed, and to determine whether to perform risk detection data visualization.
2. The visualized multi-dimensional risk detection system for transmission lines as described in claim 1, characterized in that, The specific steps for evaluating the accuracy of risk detection data collected during the inspection process by combining the offset analysis results are as follows: Quantitative data for accuracy assessment of risk detection data collected during the inspection process; The results of the accuracy assessment quantification data and the corresponding acquisition correction factor are weighted and calculated with the acquisition assessment weight, and then the inspection deviation is corrected by the inspection offset correction factor to obtain the inspection acquisition assessment value. The inspection and acquisition evaluation value represents the quantitative data on the impact of the inspection offset correction factor, the clarity of the acquired image, the standard deviation of thermal imaging, and the point cloud density of lidar on the accuracy assessment of the risk detection data acquired during the inspection process.
3. The visualized multi-dimensional risk detection system for transmission lines as described in claim 2, characterized in that, The risk detection data includes image detection data, thermal imaging detection data, and lidar data; The accuracy assessment quantification data includes the sharpness of the acquired images, the standard deviation of thermal imaging, and the point cloud density of the lidar. The acquisition correction factors include acquisition illumination correction factors, acquisition temperature correction factors, and acquisition electromagnetic interference correction factors. The acquisition and evaluation weights include image acquisition evaluation weights, thermal imaging acquisition evaluation weights, and lidar acquisition evaluation weights. The inspection and evaluation values are used to quantitatively assess the accuracy of risk detection data collected during the inspection process.
4. The visualized multi-dimensional risk detection system for transmission lines as described in claim 2, characterized in that, The specific process for determining whether to perform inspection transmission interference analysis is as follows: Based on the preset inspection collection threshold range obtained from the preset database, determine whether the obtained inspection collection evaluation value is within the preset inspection collection threshold range. If the inspection and evaluation value is within the preset inspection and evaluation threshold range obtained from the preset database, then the inspection transmission interference analysis is performed, and the inspection and evaluation value is continuously monitored to see if it is within the preset inspection and evaluation threshold range. If the inspection and collection evaluation value is not within the range of the preset inspection and collection threshold obtained from the preset database, the inspection transmission interference analysis will not be performed, and the preset personnel will be reminded to process the inspection and collection data. The inspection data processing is used to perform image enhancement, thermal imaging data smoothing, and point cloud registration on the risk detection data.
5. The visualized multi-dimensional risk detection system for transmission lines as described in claim 4, characterized in that, The specific process for processing the inspection data is as follows: A1: Perform image enhancement processing on the image detection data, and determine whether the inspection and collection evaluation value after image enhancement processing is within the preset inspection and collection threshold range. If yes, stop the inspection and collection data processing and perform tag transmission; otherwise, execute A2. A2: Perform thermal imaging data smoothing on the thermal imaging detection data, and determine whether the inspection and collection evaluation value after thermal imaging data smoothing is within the preset inspection and collection threshold range. If it is, stop the inspection and collection data processing and mark and transmit it; otherwise, execute A3. A3 performs point cloud registration processing on lidar data and marks and transmits the risk detection data after processing the inspection data. The tagging transmission is used to tag the risk detection data after the inspection and data collection data processing is performed before transmission.
6. The visualized multi-dimensional risk detection system for transmission lines as described in claim 1, characterized in that, The specific steps for detecting and analyzing the transmission quality of risk detection data are as follows: The transmission quality quantification data of the risk detection data transmission process is obtained, including the average transmission rate, transmission bit error rate, and transmission receiver signal strength. The inspection transmission evaluation value is obtained by combining the results of the average rate ratio analysis of the inspection transmission, the transmission bit error rate, the signal strength of the transmission receiver and the result of environmental electromagnetic influence correction by the transmission electromagnetic interference correction factor, the weighting operation of the corresponding transmission evaluation weight, and the inspection deviation correction by the inspection offset correction factor. The transmission evaluation weights include transmission rate evaluation weights, transmission accuracy evaluation weights, and transmission signal strength evaluation weights. The inspection transmission evaluation value represents the quantitative data on the impact of the inspection offset correction factor, the average inspection transmission rate, the transmission bit error rate, and the signal strength at the transmission receiver on the quality detection and analysis of risk detection data transmission. The inspection transmission evaluation value is used to quantitatively analyze the transmission quality of risk detection data.
7. The visualized multi-dimensional risk detection system for transmission lines as described in claim 6, characterized in that, The specific process for determining whether to perform risk detection data visualization is as follows: Based on the preset inspection transmission threshold range obtained from the preset database, determine whether the obtained inspection transmission evaluation value is within the preset inspection transmission threshold range. If the inspection transmission evaluation value is within the preset inspection transmission threshold range, then perform risk detection data visualization; If the inspection transmission evaluation value is not within the preset inspection transmission threshold range, the risk detection data visualization will not be executed, and the preset personnel will be reminded to optimize the inspection transmission. The inspection transmission optimization includes inspection transmission data optimization and inspection transmission protocol optimization. The inspection data transmission optimization is used to reduce the amount of data transmitted during the inspection transmission process; The inspection transmission protocol optimization is used to control transmission congestion during the inspection transmission process.
8. A method applied to the visualized multi-dimensional risk detection system for transmission lines as described in any one of claims 1-7, characterized in that, Includes the following steps: S1. Obtain the drone inspection status data of the preset power transmission line inspection area, and perform offset analysis between the drone inspection status data and the preset inspection status data to obtain the offset analysis results. S2, Combine the offset analysis results to evaluate the accuracy of the risk detection data collected during the inspection process and determine whether to perform inspection transmission interference analysis; S3. If the inspection transmission interference analysis is performed, the transmission quality of the risk detection data will be detected and analyzed to determine whether to perform risk detection data visualization.
Citation Information
Patent Citations
A Visual Monitoring and Early Warning Method and System for Transmission Line Status
CN116452594B
A method and system for monitoring local heating of transmission lines
CN118781095B
Inspection unmanned aerial vehicle communication enhancement method, system and device
CN106506121A
Intelligent inspection management system and method for intelligent photovoltaic power station
CN118801815A