Line Wind Deviation and Galloping Early Warning System Combining Multi-Parallel Laser and Monocular Vision

Abstract

The present application provides a line wind deviation and galloping warning system combining multi-parallel line lasers and monocular vision, which relates to the technical field of wind deviation and galloping warning, and includes: a monitoring configuration optimization module for adjusting the galloping monitoring configuration result; a galloping capture module for capturing the galloping of the transmission line according to the multi-parallel line laser component and the monocular vision component; a galloping parameter analysis module for calculating multi-dimensional wind deviation and galloping parameters; a galloping risk assessment module for assessing the galloping risk of the transmission line; and a line galloping warning module for generating a wind deviation and galloping warning signal according to the line galloping risk coefficient. Through the present application, the technical problem in the prior art that the wind deviation and galloping warning system has poor adaptability to complex environments, affecting the accuracy of wind deviation and galloping warning, can be solved. By combining multi-parallel line laser and monocular vision technologies, accurate monitoring and risk assessment of the galloping of the transmission line are realized, and the accuracy of wind deviation and galloping warning is improved.

Description

Technical Field

[0001] This application relates to the technical field of wind-induced galloping warning, and particularly to a line wind-induced galloping warning system that combines multi-parallel line lasers and monocular vision. Background Art

[0002] When the transmission line is under strong wind or changing wind speed, vibration or galloping phenomena may occur. In severe cases, it may lead to faults such as line damage, tower tilt, or wire breakage, affecting the safety of power transmission. The transmission line wind-induced galloping warning system is a system used to monitor and prevent the galloping of transmission lines caused by wind force. It mainly monitors parameters such as wind speed, wind direction, line tension, and vibration frequency, timely identifies and warns of galloping phenomena, and takes preventive measures to reduce the risk of line faults. However, existing wind-induced galloping warning systems are easily interfered with under extreme weather conditions (such as storms, heavy rain, ice and snow, etc.) and complex terrains (such as mountains, plains, and rivers, etc.), resulting in unstable or invalid monitoring data, which limits the accuracy and timeliness of the warning system, especially in cases where quick response is required. Due to the complex and changeable natural environment, the warning system may lack robustness, and false alarms (false positives) or missed alarms may easily occur. False alarms increase the maintenance cost and burden, and missed alarms may lead to failures not being warned in time, affecting the actual prevention and control effect.

[0003] In summary, there is a technical problem in the prior art that due to the poor performance of the transmission line wind-induced galloping warning system in complex environments, false alarms and missed alarms occur, further affecting the accuracy of wind-induced galloping warning. Summary of the Invention

[0004] The purpose of this application is to provide a line wind-induced galloping warning system that combines multi-parallel line lasers and monocular vision, so as to solve the technical problem in the prior art that due to the poor performance of the transmission line wind-induced galloping warning system in complex environments, false alarms and missed alarms occur, further affecting the accuracy of wind-induced galloping warning.

[0005] In view of the above problems, the present application provides a line wind deviation and galloping warning system combining multi-parallel line lasers and monocular vision. Among them, the line wind deviation and galloping warning system combining multi-parallel line lasers and monocular vision includes: a monitoring configuration optimization module, which is used to adjust the galloping monitoring configuration result of the transmission line according to a predetermined future time zone to generate an optimized galloping monitoring configuration result; a galloping capture module, which is used to capture the galloping of the transmission line based on the predetermined future time zone and the optimized galloping monitoring configuration result according to the multi-parallel line laser component and the monocular vision component to obtain a line galloping capture result; a galloping parameter analysis module, which is used to calculate multi-dimensional wind deviation and galloping parameters according to the line galloping capture result to obtain a galloping parameter calculation result; a galloping risk assessment module, which is used to assess the galloping risk of the transmission line according to the wind deviation and galloping risk factors in combination with the galloping parameter calculation result to determine the line galloping risk coefficient; a line galloping warning module, which is used to generate a wind deviation and galloping warning signal based on the line galloping risk coefficient according to the line galloping risk threshold and the galloping risk classification warning device.

[0006] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0007] Through the monitoring configuration optimization module, which is used to adjust the galloping monitoring configuration result of the transmission line according to a predetermined future time zone to generate an optimized galloping monitoring configuration result; a galloping capture module, which is used to capture the galloping of the transmission line based on the predetermined future time zone and the optimized galloping monitoring configuration result according to the multi-parallel line laser component and the monocular vision component to obtain a line galloping capture result; a galloping parameter analysis module, which is used to calculate multi-dimensional wind deviation and galloping parameters according to the line galloping capture result to obtain a galloping parameter calculation result; a galloping risk assessment module, which is used to assess the galloping risk of the transmission line according to the wind deviation and galloping risk factors in combination with the galloping parameter calculation result to determine the line galloping risk coefficient; a line galloping warning module, which is used to generate a wind deviation and galloping warning signal based on the line galloping risk coefficient according to the line galloping risk threshold and the galloping risk classification warning device. That is to say, through the combination of multi-parallel line lasers and monocular vision, high-precision monitoring data is provided under various complex conditions, the risk of the transmission line is assessed, a wind deviation and galloping warning signal is generated, the accuracy of the wind deviation and galloping warning is improved, and the phenomena of missed reports and false reports are reduced.

[0008] The above description is only an overview of the technical solution of this application. In order to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. Moreover, in order to make the above and other purposes, features, and advantages of this application more obvious and understandable, the specific implementation manners of this application are specifically exemplified below. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of this application, nor is it used to limit the scope of this application. Other features of this application will become easily understandable through the following description of the specification. Brief Description of the Drawings

[0009] In order to more clearly illustrate the technical solutions in this application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0010] Figure 1 It is a schematic structural diagram of the line wind deviation and galloping warning system that combines multi-parallel line lasers and monocular vision in this application;

[0011] Figure 2 It is a schematic flowchart of determining the line galloping risk coefficient in the line wind deviation and galloping warning system that combines multi-parallel line lasers and monocular vision in this application.

[0012] Description of the reference numerals: Monitoring configuration optimization module 11, galloping capture module 12, galloping parameter analysis module 13, galloping risk assessment module 14, line galloping warning module 15. Detailed Description of the Preferred Embodiments

[0013] This application provides a line wind deviation and galloping warning system that combines multi-parallel line lasers and monocular vision, and solves the technical problem in the prior art that due to the poor effect of the transmission line wind deviation and galloping warning system in complex environments, false alarms and missed alarms occur, further affecting the accuracy of the wind deviation and galloping warning. Through the combination of multi-parallel line lasers and monocular vision, high-precision monitoring data is provided under various complex conditions, the transmission line is risk-assessed, and a wind deviation and galloping warning signal is generated, improving the accuracy of the wind deviation and galloping warning and reducing the phenomena of missed alarms and false alarms.

[0014] Next, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described herein. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without making creative efforts belong to the scope of protection of the present application. Additionally, it should be noted that for the sake of description, only parts related to the present application are shown in the drawings rather than all of them.

[0015] For the embodiments, please refer to the attached Figure 1 drawings. The present application provides a line wind-induced galloping warning system combining multi-parallel line lasers and monocular vision. Among them, the line wind-induced galloping warning system combining multi-parallel line lasers and monocular vision includes:

[0016] A monitoring configuration optimization module 11, which is used to adjust the galloping monitoring configuration result of the transmission line according to a predetermined future time zone and generate an optimized galloping monitoring configuration result.

[0017] Specifically, according to the prediction of environmental conditions in the future time zone, the existing monitoring configuration is adjusted to optimize the monitoring effect. The predetermined future time zone refers to predicting the environmental conditions, such as wind speed, temperature, humidity, etc. within a certain period in the future based on weather forecasts, historical data, or other relevant information. The galloping monitoring configuration result includes the monitoring parameters of the multi-parallel line laser component and the monocular vision component, such as the power and emission angle of the laser emitter, the position and focal length of the camera, etc. According to the predicted environmental conditions, the multi-parallel line laser component and the monocular vision component of the existing monitoring configuration are adjusted accordingly, and the optimization results are integrated to obtain the optimized galloping monitoring configuration result. For example, the original laser monitoring configuration has a laser emission angle of 45 degrees and a line spacing of 1.0 meter. Since the wind speed of the transmission line in the predetermined future time zone is relatively high, which will cause more violent galloping, the laser emission angle is adjusted to 40 degrees and the line spacing is reduced to 0.8 meter to improve the resolution. The original vision monitoring configuration has a camera focal length of 75 mm and a frame rate of 25 fps. To capture faster galloping speeds, the camera focal length is adjusted to 50 mm and the frame rate is increased to 30 fps. By adjusting the configuration, the monitoring system can more accurately capture the galloping situation of the transmission line, better adapt to different environmental conditions, and improve the overall performance of the monitoring system.

[0018] A galloping capture module 12, which is used to capture the galloping of the transmission line based on the predetermined future time zone and the optimized galloping monitoring configuration result according to the multi-parallel line laser component and the monocular vision component, and obtain a line galloping capture result.

[0019] Specifically, based on future meteorological conditions (such as wind speed, wind direction, temperature, etc.) and historical galloping data of transmission lines, the optimization results of the galloping monitoring configuration are generated, including the emission parameters of the laser component (such as laser intensity, emission angle) and the monitoring parameters of the vision component (such as exposure time, resolution). According to the optimization results, the parameters of the multi-parallel line laser component are adjusted to ensure that the laser can effectively cover the transmission line and form a stable laser grid. At the same time, the monocular vision component is activated to perform real-time monitoring of the transmission line according to the optimized configuration parameters (such as frame rate, focal length), and capture images of the line under laser irradiation. K reference points are identified in the laser grid for tracking the galloping of the line; the line monitoring images captured by the monocular vision component are processed using a gamma enhancement function to improve the contrast and clarity of the images; based on the laser grid and the identified reference points, feature tracking is performed on the enhanced images, and the position changes of each reference point are recorded; the motion trajectories of each tracked reference point are fused and analyzed to obtain the galloping situation of the transmission line. For example, assuming that within the next 6 hours, the weather forecast predicts that there will be a strong wind with a wind speed of 15 m / s in the area where the transmission line is located, the emission frequency of the multi-parallel line laser component and the sampling rate of the monocular vision component are adjusted according to the prediction to adapt to the upcoming strong wind conditions. During the monitoring process, the laser component captures the vibration situation of the line under the action of strong wind, while the vision component records the actual motion trajectory of the line. By analyzing these data, the galloping situation of the line during this period is obtained, including the amplitude, frequency, and mode of galloping. Through the collaborative work of the multi-parallel line laser component and the monocular vision component, the galloping situation of the line is captured in real time, improving the adaptability and monitoring efficiency of the system, especially in complex weather conditions and night environments.

[0020] The galloping parameter analysis module 13 is used to calculate multi-dimensional wind deflection galloping parameters according to the line galloping capture result to obtain the galloping parameter calculation result.

[0021] Specifically, the captured results of line galloping obtained by the multi-parallel line laser component and the monocular vision component are analyzed and calculated from multiple angles and with multiple parameters to obtain detailed information on line galloping. The multi-dimensional wind-induced galloping parameter calculation includes wind deflection angle, galloping amplitude, vertical galloping amplitude, horizontal galloping amplitude, and elliptical tilt angle, etc. Among them, the wind deflection angle refers to the lateral deflection angle of the line under the action of wind, and is usually used to describe the offset degree of the line relative to the vertical line; the galloping amplitude refers to the maximum displacement of the line during galloping, which can be the displacement in the vertical or horizontal direction; the vertical galloping amplitude refers to the maximum displacement of the line in the vertical direction; the horizontal galloping amplitude refers to the maximum displacement of the line in the horizontal direction; the elliptical tilt angle refers to the tilt angle of the ellipse formed by the line galloping trajectory relative to the horizontal plane. The captured transmission line galloping images or laser point cloud data are preprocessed, including denoising, filtering, and image enhancement, etc., to improve the data quality. Key feature points of the transmission line are extracted from the processed data for tracking the galloping trajectory of the line and calculating the wind deflection angle, galloping amplitude, vertical galloping amplitude, horizontal galloping amplitude, and elliptical tilt angle, etc. By calculating the position change of the feature points, the angle at which the line deviates from the original position is determined to obtain the wind deflection angle; by analyzing the maximum displacement of the feature points, the overall galloping amplitude of the line is obtained; by separately analyzing the maximum displacement of the feature points in the vertical direction, the vertical galloping amplitude is obtained; by separately analyzing the maximum displacement of the feature points in the horizontal direction, the horizontal galloping amplitude is obtained; by fitting the galloping trajectory of the feature points, the tilt angle of the trajectory ellipse is calculated to obtain the elliptical tilt angle. For example, the maximum wind deflection angle of the line is 15 degrees, the maximum displacement of the line is 50 cm, the maximum displacement of the line in the vertical direction is 30 cm, the maximum displacement of the line in the horizontal direction is 40 cm, and the tilt angle of the ellipse formed by the line galloping trajectory relative to the horizontal plane is 10 degrees. Through multi-dimensional calculation, the quantitative analysis of line galloping is realized, which helps to diagnose whether there is excessive galloping or other abnormal behaviors in the line, so as to take corresponding maintenance or reinforcement measures.

[0022] The galloping risk assessment module 14 is used to perform a galloping risk assessment on the transmission line according to the wind-induced galloping risk factors and in combination with the calculation results of the galloping parameters to determine the line galloping risk coefficient.

[0023] Specifically, the galloping risk factors include instantaneous galloping risk, waiting galloping risk, and maintenance galloping risk. Among them, the instantaneous galloping risk refers to the situation where the galloping amplitude or frequency of the transmission line is too high at a certain moment, resulting in an increase in instantaneous risk; the waiting galloping risk means that the galloping phenomenon may accumulate over a period of time, increasing the likelihood of subsequent galloping risks, reflecting the potential galloping risks of the line under long-term exposure to wind forces; the maintenance galloping risk refers to the risk of damage to the transmission line or its auxiliary equipment caused by galloping, and the maintenance cost and resource requirements are also one of the considerations. Risk assessment is carried out on the calculation results of galloping parameters (such as wind deflection angle, galloping amplitude, vertical galloping amplitude, horizontal galloping amplitude, and elliptical tilt angle data) to quantify the impact of each parameter on the instantaneous risk, waiting risk, and maintenance risk. Initial weight settings are made for each galloping risk factor according to the actual situation, that is, initial weights are assigned according to the relative importance of the risk factors, and initial weights are assigned to each risk factor (instantaneous risk, waiting risk, maintenance risk) to obtain the first weight condition for galloping risk assessment.

[0024] Weights are assigned according to the relative importance of each risk coefficient in the overall risk assessment in the risk assessment results to obtain the second weight condition for galloping risk assessment. Central value calculations are performed on the first weight condition and the second weight condition to balance the weights of each risk factor, and the final comprehensive weight of the current galloping risk is calculated, which reflects the overall risk level of the current galloping phenomenon and comprehensively considers the influence of the calculation results of galloping parameters, instantaneous, waiting, and maintenance risks. According to the calculation results of galloping parameters and the final weight settings, the calculation results of galloping parameters, instantaneous risk, waiting risk, and maintenance risk are jointly weighted to determine the line galloping risk coefficient. Through the comprehensive assessment of various risk factors such as instantaneous galloping risk, waiting risk, and maintenance risk, combined with weight setting and weighted calculation, the line galloping risk coefficient is finally generated to accurately assess the galloping risk of the transmission line and adapt to complex environments and multi-dimensional risk scenarios.

[0025] The line galloping early warning module 15 is used to generate a wind deflection galloping early warning signal based on the line galloping risk coefficient, according to the line galloping risk threshold and the galloping risk grading early warning device.

[0026] Specifically, according to the design standards, environmental conditions, and safety requirements of the line, a line galloping risk threshold is preset in advance, which represents the maximum allowable galloping risk level and can be a fixed value or dynamically adjusted according to real-time conditions. It is judged whether the line galloping risk coefficient is greater than or equal to the line galloping risk threshold. If it is greater than or equal to the line galloping risk threshold, it means that the current galloping risk has reached a dangerous or critical level, which may pose a threat to the safe operation of the transmission line, trigger the galloping risk classification warning device, and generate a wind deviation galloping warning signal. Multiple thresholds are set according to different galloping risk levels, such as first-level warning, second-level warning, third-level warning, etc. The warning signal usually includes warning level, warning content, warning time, warning range, warning measures, etc. Once the warning signal is generated, it is notified to relevant operation and maintenance personnel and management personnel through appropriate communication channels (such as text messages, emails, on-site audible and visual alarms, etc.). The operation and maintenance personnel take corresponding preventive or emergency measures according to the warning signal, such as strengthening line monitoring, adjusting the line operation state, preparing maintenance resources, etc. If it is less than the line galloping risk threshold, it means that the line is within the safe range, no alarm is required, and it will continue to be monitored without taking any additional emergency measures. By judging whether the line galloping risk coefficient is greater than or equal to the line galloping risk threshold, high-risk states are automatically identified and the warning mechanism is triggered, which helps grid operation and maintenance personnel take necessary preventive measures in a timely manner, reduce the risk of line galloping, and thus ensure the safe operation of the power grid.

[0027] Further, the monitoring configuration optimization module 11 in the line wind deviation galloping warning system combining multi-parallel line lasers and monocular vision is further configured to:

[0028] The galloping monitoring configuration result includes the laser monitoring configuration result of the multi-parallel line laser component and the visual monitoring configuration result of the monocular vision component; based on the predetermined future time zone, environmental prediction of the transmission line is carried out to obtain a line environmental prediction result; based on the line environmental prediction result, wind deviation galloping characteristics prediction of the transmission line is carried out to obtain a line galloping prediction result; based on the line galloping prediction result, reward and punishment correction is carried out on the laser monitoring configuration result to generate an optimized laser monitoring configuration result; according to the line galloping prediction result, reward and punishment correction is carried out on the visual monitoring configuration result to generate an optimized visual monitoring configuration result; and the optimized laser monitoring configuration result and the optimized visual monitoring configuration result are added to the galloping monitoring configuration optimization result.

[0029] Specifically, multi-parallel line laser assemblies are installed at key points of the transmission line or areas prone to dancing, such as transmission towers, to ensure that the line of sight of the multi-parallel line laser assembly is not blocked by the tower structure or other obstacles. The multi-parallel line laser assembly is a multi-parallel line laser device in the prior art, which is used to emit multiple parallel laser lines, which form laser stripes on the surface of the transmission line. The multi-parallel line laser assembly is set and adjusted to achieve accurate monitoring of the transmission line, including the position, emission angle, power and other parameters of the multi-parallel line laser assembly, and the laser monitoring configuration results are determined. At the same time, a monocular camera (i.e., a monocular vision component) is installed near the multi-parallel line laser assembly to capture images of the scene and laser lines, determine the position, focal length, resolution, sensitivity and other parameters of the camera, and obtain the visual monitoring configuration results. Based on weather forecasts or other relevant factors, a monitoring time period is pre-set, that is, a future time zone is scheduled, and weather forecast data for the scheduled future time zone is obtained, including information such as wind speed, wind direction, temperature, humidity, etc. The environmental conditions of the transmission line in the future are predicted to obtain line environment prediction results, including key environmental parameters such as expected wind speed, wind direction, temperature, humidity, and precipitation probability in the future time zone.

[0030] Analyze historical dancing data, combine current and predicted environmental conditions, predict the dancing characteristics of the transmission line, such as dancing amplitude, frequency, etc., and obtain the line dancing prediction results. For example, if the forecast shows strong winds in the next few hours, it is predicted that the transmission line will have a large dancing amplitude and frequency. Reward and punishment correction is a method of adjusting the monitoring configuration according to the prediction results. If the prediction results are consistent with the actual monitoring results, the corresponding monitoring configuration is rewarded, that is, these configurations are maintained or enhanced; if the prediction results are inconsistent with the actual monitoring results, the corresponding monitoring configuration is punished, that is, these configurations are adjusted or weakened. According to the line dancing prediction results, the laser monitoring configuration results and the visual monitoring configuration results are adjusted, such as adjusting the power and emission frequency of the laser transmitter, or adjusting the position, focal length, image acquisition speed, etc. of the camera. Integrate the adjusted laser monitoring configuration optimization results and visual monitoring configuration optimization results to obtain the dancing monitoring configuration optimization results. For example, suppose that after the reward and punishment correction, the laser monitoring configuration optimization results show that the power of the laser transmitter needs to be increased from 100 watts to 150 watts, and the visual monitoring configuration optimization results show that the camera's image acquisition speed needs to be increased from 10 frames per second to 20 frames per second. The optimization results are added to the dancing monitoring configuration optimization results to update the overall monitoring strategy of the system. By adjusting the laser emission angle and spacing, as well as the camera focal length and frame rate, the monitoring system can more accurately capture the dancing of the transmission line. According to the reward and punishment correction algorithm, the monitoring system automatically adjusts the configuration according to different environmental conditions, improving the system's adaptability and operating efficiency.

[0031] Further, the dancing capture module 12 in the line wind deviation and dancing warning system combining multi-parallel-line laser and monocular vision is further configured to:

[0032] Based on the predetermined future time zone and the laser monitoring configuration optimization result, control the multi-parallel-line laser assembly to emit laser light to the transmission line, and establish a line laser grid; identify reference points for the line laser grid according to the transmission line to obtain K identified reference points, where K is a positive integer greater than 1; based on the predetermined future time zone and the vision monitoring configuration optimization result, synchronously control the monocular vision assembly to perform real-time monitoring on the transmission line to obtain a line monitoring image; perform enhancement processing on the line monitoring image according to the gamma enhancement function to obtain a line enhanced image; based on the line laser grid, perform feature tracking on the line enhanced image according to the K identified reference points to obtain a K-point feature tracking result; perform trajectory fusion based on the K-point feature tracking result to generate the line dancing capture result.

[0033] Specifically, analyze the environmental conditions in the predetermined future time zone, such as weather forecast, wind speed, temperature, etc., to predict the possible environmental changes that the transmission line may face in the next period of time. Use the optimized configuration result to control the multi-parallel-line laser assembly according to the environmental changes, adjust the parameters of the laser emitter, so that it can emit laser light according to the predicted environmental conditions, emit multiple parallel laser lines, and intersect on the surface of the transmission line to form a laser grid to achieve the monitoring of the transmission line. Laser emission is achieved by controlling the multi-parallel-line laser assembly to emit multiple parallel laser lines in the transmission line area, which can capture any tiny movement on the line, thereby achieving precise monitoring of line dancing. Identify K reference points in the established laser grid. Usually, based on specific feature points in the laser grid, such as the intersection points of laser lines, fixed points on the line, etc., they can be used as reference points for subsequent image processing.

[0034] According to the optimized configuration result, synchronously control the monocular vision assembly to perform real-time monitoring on the transmission line. The monocular vision assembly will continuously capture images of the line according to the optimized parameter settings to obtain a series of line monitoring images and capture the real-time state of the line. Use the gamma enhancement function to perform enhancement processing on the line monitoring image to improve the contrast and clarity of the image. Gamma enhancement is a commonly used image enhancement technology that changes the contrast and brightness of the image by adjusting the gamma value of the image. For each pixel, calculate the difference between its gray value and the average gray value, then multiply the difference by the gamma coefficient and perform rounding processing, and add the rounding result to the original gray value to obtain the enhanced gray value. Combine the pixel values after gamma enhancement processing to generate a line enhanced image.

[0035] Using K reference points in the line laser grid to perform feature tracking on the enhanced image, obtaining the position changes of the K reference points in the enhanced image, which reflects the galloping condition of the line, such as the swaying amplitude, frequency, etc. Feature tracking is an image processing technique used to track the changes of specific features over time in consecutive image frames. Fusing the tracking results of the K reference points to obtain the overall galloping capture result of the transmission line. Trajectory fusion is a data fusion technique used to combine information from multiple data sources to obtain more accurate and comprehensive results. For example, assume that monitoring is carried out on a 1000-meter-long transmission line, and one reference point is identified every 50 meters, with a total of 20 reference points identified (K = 20). The monitoring image is processed using an enhancement function with a gamma value of 1.5, and each reference point is tracked in 10 consecutive image frames. The tracking results of the 20 reference points are fused to generate a comprehensive capture result of the line galloping. By establishing a line laser grid to monitor the transmission line, identifying reference points improves the capture accuracy of the line galloping characteristics, gamma enhancement processing improves the image quality, feature tracking technology can capture the real-time dynamics of the line, and trajectory fusion technology integrates the information of multiple reference points to generate a comprehensive line galloping capture result, providing a basis for risk assessment and early warning.

[0036] Furthermore, the galloping capture module 12 in the line wind deflection and galloping early warning system combining multi-parallel line lasers and monocular vision is also used for:

[0037] The gamma enhancement function is: ; where represents the gray value at the (x, y) position in the enhanced line image, round represents rounding processing, represents the gray value at the (x, y) position in the line monitoring image, mean represents the average gray value of the line monitoring image, and γ represents the image enhancement gamma coefficient.

[0038] Specifically, the gamma enhancement function is used to perform enhancement processing on the monitoring image of the transmission line, and the expression is: ; the gray value of each pixel point in the original image is subtracted by the average gray value for gray normalization, so that the gray value distribution of the image is more uniform, thereby enhancing the contrast of the image. The obtained result is multiplied by the gamma coefficient and rounded, and the calculated gray value is converted to an integer. The rounded result is added to the original gray value to obtain the enhanced gray value, in order to retain some details of the original image while enhancing the contrast. Among them, represents the gray value at the (x, y) position in the enhanced line image; round represents rounding processing, that is, rounding the calculation result; Characterize the gray value at the (x, y) position in the line monitoring image; mean represents the average gray value of the line monitoring image; γ represents the image enhancement gamma coefficient, which is used to control the enhancement degree of the image. When the gamma value is greater than 1, the highlight part of the image will be enhanced, and the contrast will be increased. When the gamma value is less than 1, the dark part details of the image will be enhanced, and the contrast will be decreased. By adjusting the gray value of each pixel, the overall contrast of the image is enhanced, and certain original image information is retained, which is better for improving the quality of transmission line monitoring images, especially in the case of low light or insufficient contrast.

[0039] Further, as shown in the appendix Figure 2 The dancing risk assessment module 14 in the line wind deviation and dancing early warning system combining multi-parallel line lasers and monocular vision is further used for:

[0040] The wind deviation and dancing risk factors include instantaneous dancing risk, waiting dancing risk, and maintenance dancing risk; based on the wind deviation and dancing risk factors, risk assessment is performed on the calculation result of the dancing parameters to obtain a dancing risk assessment result; based on the wind deviation and dancing risk factors, initial weight settings are performed to determine the first weight condition for dancing risk assessment; according to the dancing risk assessment result, proportion calculation is performed to generate the second weight condition for dancing risk assessment; based on the first weight condition for dancing risk assessment and the second weight condition for dancing risk assessment, a central value calculation is performed to generate the third weight condition for dancing risk assessment; according to the third weight condition for dancing risk assessment, weighted calculation is performed on the dancing risk assessment result to generate the line dancing risk coefficient.

[0041] Further, the dancing risk assessment module 14 in the line wind deviation and dancing early warning system combining multi-parallel line lasers and monocular vision is further used for:

[0042] Based on the wind deviation and dancing risk factors, retrospective learning is performed to build multiple channels for dancing risk analysis, where the multiple channels for dancing risk analysis include an instantaneous dancing risk analysis channel, a waiting dancing risk analysis channel, and a maintenance dancing risk analysis channel; the calculation result of the dancing parameters is input into the instantaneous dancing risk analysis channel to obtain an instantaneous dancing risk coefficient; based on the calculation result of the dancing parameters, according to the waiting dancing risk analysis channel, a waiting dancing risk coefficient is obtained; based on the calculation result of the dancing parameters, according to the maintenance dancing risk analysis channel, a maintenance dancing risk coefficient is obtained; the instantaneous dancing risk coefficient, the waiting dancing risk coefficient, and the maintenance dancing risk coefficient are output as the dancing risk assessment result.

[0043] Specifically, the wind deviation and galloping risk factor is an index used to evaluate the safety risks of transmission lines under wind deviation and galloping conditions, including instantaneous galloping risk, waiting galloping risk, and maintenance galloping risk. Among them, the instantaneous galloping risk refers to the immediate risk of the transmission line during wind deviation and galloping, which may be related to factors such as galloping amplitude and speed; the waiting galloping risk refers to the possible risk accumulation or exacerbation in the future period after galloping occurs on the transmission line; the maintenance galloping risk refers to the risks that may be faced during the maintenance or repair of galloping faults, such as operation safety risks and power outage risks.

[0044] The wind deviation and galloping risk factor is used to conduct risk assessment on the calculation results of galloping parameters (such as wind deviation angle, galloping amplitude, vertical galloping amplitude, horizontal galloping amplitude, and elliptical tilt angle, etc.). Backtracking learning is a machine learning method that discovers potential risk patterns and correlations by analyzing historical data, so as to improve the prediction ability of future risks. According to risk factors such as instantaneous galloping risk, waiting galloping risk, and maintenance galloping risk, determine the types of risks that need to be analyzed, and establish an independent channel for each risk factor to analyze the safety risks of the line at the current moment, in the future period, and during long-term operation. In each channel, according to the calculation results of galloping parameters and the corresponding risk factors, calculate the galloping risk coefficient of the line, which reflects the safety risk level of the line at different time scales. The instantaneous galloping risk analysis channel specifically processes data related to the instantaneous galloping risk. Input the calculation results of galloping parameters (such as wind deviation angle, galloping amplitude, etc.) into this channel, analyze the relationship between historical galloping events and galloping parameters, and thus calculate the instantaneous galloping risk coefficient. The waiting galloping risk analysis channel focuses on the cumulative risks that may be caused by the failure to handle galloping in a timely manner after it occurs. Similarly, using the calculation results of galloping parameters, determine the coefficient of the waiting galloping risk by analyzing historical data, which reflects the risk level that may be faced in the future period. The maintenance galloping risk analysis channel evaluates the risks that may be encountered during maintenance or repair, analyzes historical maintenance records and galloping events, and calculates the maintenance galloping risk coefficient. Combine the risk coefficients output by the three channels (instantaneous galloping risk coefficient, waiting galloping risk coefficient, and maintenance galloping risk coefficient) to form the final galloping risk assessment result, which can be a comprehensive score or grade, or three independent risk coefficients, used to indicate the severity of different types of risks.

[0045] Allocate initial weights according to the relative importance of risk factors, assign corresponding weights to different risk factors, and determine the first weight condition for galloping risk assessment, which reflects the relative importance of different risk factors to the line safety risk. For example, if the instantaneous risk is considered the most important, then a higher weight is assigned. According to the galloping risk assessment results, calculate the contribution ratio of each risk factor in the overall risk assessment. Calculate the proportion according to the galloping risk assessment results to generate the second weight condition for galloping risk assessment. Specifically, through expert scoring, historical data analysis or machine learning algorithms, divide each risk coefficient by the sum of all risk coefficients to obtain the importance of each risk coefficient in the overall risk assessment. For example, the galloping instantaneous risk coefficient is 0.8, the galloping waiting risk coefficient is 0.6, and the galloping maintenance risk coefficient is 0.4. Calculate the proportion of each coefficient to determine the importance of each risk coefficient in the overall risk assessment. The proportion of instantaneous risk: 0.8 / (0.8 + 0.6 + 0.4) is approximately equal to 0.4, the proportion of waiting risk: 0.6 / (0.8 + 0.6 + 0.4) is approximately equal to 0.3, and the proportion of maintenance risk: 0.4 / (0.8 + 0.6 + 0.4) is approximately equal to 0.2.

[0046] On the basis of the first weight condition and the second weight condition, calculate the third weight condition through statistical methods (such as mean, median, etc.), which takes a more comprehensive and balanced consideration of the weights of different risk factors. It not only considers the relative importance of risk factors (the first weight condition), but also considers the contribution ratio in the overall risk assessment (the second weight condition). According to the third weight condition, weight each risk factor in the galloping risk assessment results. Multiply the assessment result of each risk factor by its corresponding third weight condition, and then add the products to obtain a total risk coefficient, that is, the line galloping risk coefficient, which is used to represent the current risk level of the transmission line. The higher the line galloping risk coefficient, the greater the risk of line galloping, and corresponding warning measures need to be taken. Through weight setting and weighted calculation, a comprehensive line galloping risk coefficient is obtained, which comprehensively reflects the safety state of the line.

[0047] Furthermore, the galloping risk assessment module 14 in the line wind deflection and galloping warning system combining multi-parallel line lasers and monocular vision is further used for:

[0048] Based on the wind deviation galloping risk factors, conduct a retrospective analysis of the galloping risk assessment of the transmission line to obtain a calculation sample set of galloping parameters, an instantaneous risk sample set of galloping, a waiting risk sample set of galloping, and a maintenance risk sample set of galloping; use the calculation sample set of galloping parameters as input data and the instantaneous risk sample set of galloping as output data to perform deep learning on the residual neural network and build the instantaneous risk analysis channel of galloping; conduct deep learning based on the calculation sample set of galloping parameters and the waiting risk sample set of galloping to establish the waiting risk analysis channel of galloping; conduct deep learning based on the calculation sample set of galloping parameters and the maintenance risk sample set of galloping to generate the maintenance risk analysis channel of galloping; connect the instantaneous risk analysis channel of galloping, the waiting risk analysis channel of galloping, and the maintenance risk analysis channel of galloping as parallel nodes to generate the multi-channel galloping risk analysis.

[0049] Specifically, review and analyze the galloping risk assessment records of the transmission line over a past period, including the calculation results of galloping parameters, risk assessment results, and relevant environmental parameters (such as wind speed, wind direction, etc.). Through retrospective analysis, generate four different sample sets: the calculation sample set of galloping parameters contains the calculation results of historical galloping parameters; the instantaneous risk sample set of galloping contains the results of historical instantaneous risk assessments; the waiting risk sample set of galloping contains the results of historical waiting risk assessments; the maintenance risk sample set of galloping contains the results of historical maintenance risk assessments.

[0050] Use the calculation sample set of galloping parameters, including wind deviation angle, galloping amplitude, vertical galloping amplitude, horizontal galloping amplitude, and elliptical tilt angle data, as input data, and the instantaneous risk sample set of galloping as output data to perform deep learning training on the residual neural network to establish a prediction model for the instantaneous risk of galloping. Deep learning is a machine learning method that learns high-level features and complex patterns in data through a multi-layer neural network model. The residual neural network (ResNet) is a deep learning architecture that can effectively reduce the vanishing gradient problem in deep networks and is particularly suitable for processing complex data relationships. In the galloping monitoring system, ResNet is used to learn the complex mapping relationship between the input galloping parameters (such as wind speed, wind direction, line vibration amplitude, etc.) and the output instantaneous risk. By training the residual neural network, establish a dedicated channel for analyzing and predicting the instantaneous risk of the line, which can process the input galloping parameters and output the corresponding instantaneous risk prediction results.

[0051] Similarly, a risk analysis channel for dancing waiting risk is established through deep learning technology to process the input dancing parameters and output the corresponding waiting risk prediction results; through deep learning technology, a risk analysis channel for dancing maintenance risk is generated to process the input dancing parameters, but the output is the prediction result of maintenance risk. Each risk analysis channel is an independent node, running in parallel and each processing a specific type of risk. The instantaneous risk analysis channel focuses on predicting risks in a short period of time, the waiting risk analysis channel focuses on risks in a slightly longer period of time, while the maintenance risk analysis channel focuses on evaluating risks during maintenance activities, including the difficulty, cost of maintenance operations, and risks that may occur during maintenance. Each channel can independently process the risk type associated with it. The trained channels are connected in parallel to ensure that the channels can receive input data simultaneously and produce outputs. The output results of each channel are comprehensively analyzed to obtain a comprehensive risk assessment. Through deep learning, complex risk patterns are learned from historical data to improve the accuracy of risk assessment. Through parallel channels, different types of risks are considered simultaneously to obtain a more comprehensive risk assessment result, generating a multi-channel dancing risk analysis to provide a comprehensive risk assessment view to help power grid operation and maintenance personnel better understand the risks of the line at different time scales.

[0052] Furthermore, the line dancing early warning module 15 in the line wind deviation and dancing early warning system combining multi-parallel line lasers and monocular vision is further configured to:

[0053] Determine whether the line dancing risk coefficient is greater than or equal to the line dancing risk threshold; if the line dancing risk coefficient is greater than or equal to the line dancing risk threshold, activate the dancing risk classification early warning device; input the line dancing risk coefficient into the dancing risk classification early warning device to obtain the wind deviation and dancing early warning signal.

[0054] Specifically, according to the design standards, environmental conditions, and safety requirements of the line, a line galloping risk threshold is preset, and the calculated line galloping risk coefficient is compared with the set line galloping risk threshold. If the line galloping risk coefficient is greater than or equal to the line galloping risk threshold, it is considered that the line is in a high-risk state, and early warning measures need to be taken to activate the galloping risk classification and early warning device, which can be automatically completed through software instructions or manually activated after manual confirmation. The line galloping risk coefficient is input into the activated galloping risk classification and early warning device to generate a corresponding wind deflection and galloping early warning signal. For example, when the galloping risk coefficient is close to but does not exceed the threshold, it reminds the operation and maintenance personnel to closely monitor the galloping condition; when the galloping risk coefficient is greater than or equal to the first threshold but lower than the highest threshold, it is recommended to take some countermeasures, such as increasing the line monitoring frequency or adjusting the equipment parameters; when the galloping risk coefficient is greater than or equal to the highest threshold, it is recommended to immediately take emergency measures, such as stopping the line operation or performing emergency maintenance.

[0055] The early warning signal usually includes the early warning level (such as level 1 early warning, level 2 early warning, level 3 early warning, etc.), the early warning content (such as the line may experience galloping, the recommended measures, etc.), the early warning time (the specific time when the early warning signal is issued), and the early warning range (the affected line section). Through appropriate communication channels (such as text messages, emails, on-site audible and visual alarms, etc.), relevant operation and maintenance personnel and management personnel are notified to remind them of possible dangerous situations, or to trigger automated protection measures, such as adjusting the line tension, starting vibration dampers, and even stopping the line operation in extreme cases. After the early warning is issued, it enters the continuous monitoring mode, and through further calculation of galloping parameters and real-time data analysis, the risk assessment result is dynamically adjusted. If the galloping risk coefficient continues to rise, the alarm level can be increased or more severe measures can be taken; if the galloping risk coefficient decreases, the alarm can be cancelled and the normal operation can be restored. By automatically issuing an early warning signal when the detected line galloping risk exceeds the safety threshold, it reminds the power grid operation and maintenance personnel to take necessary preventive measures, which helps to respond to potential safety risks in a timely manner, thus ensuring the safe operation of the power grid.

[0056] In summary, the line wind deflection and galloping early warning system combining multi-parallel line lasers and monocular vision provided by this application has the following technical effects:

[0057] Through the monitoring configuration optimization module, which is used to adjust the galloping monitoring configuration result of the transmission line according to a predetermined future time zone to generate an optimized galloping monitoring configuration result; a galloping capture module, which is used to capture the galloping of the transmission line based on the predetermined future time zone and the optimized galloping monitoring configuration result by using a multi-parallel line laser component and a monocular vision component to obtain a line galloping capture result; a galloping parameter analysis module, which is used to calculate multi-dimensional wind deviation galloping parameters according to the line galloping capture result to obtain a galloping parameter calculation result; a galloping risk assessment module, which is used to assess the galloping risk of the transmission line according to the wind deviation galloping risk factor and in combination with the galloping parameter calculation result to determine the line galloping risk coefficient; a line galloping early warning module, which is used to generate a wind deviation galloping early warning signal based on the line galloping risk coefficient according to the line galloping risk threshold and the galloping risk grading early warning device. That is to say, through the combination of multi-parallel line lasers and monocular vision, high-precision monitoring data is provided under various complex conditions to assess the risk of the transmission line, generate a wind deviation galloping early warning signal, improve the accuracy of the wind deviation galloping early warning, and reduce the phenomena of missed reports and false alarms.

[0058] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0059] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is also intended to include these changes and modifications.

Claims

1. A line wind deviation and galloping warning system combining multi-parallel line lasers and monocular vision, characterized in that Including: A monitoring configuration optimization module, which is used to adjust the galloping monitoring configuration result of a transmission line according to a predetermined future time zone and generate an optimized galloping monitoring configuration result; A galloping capture module, which is used to capture the galloping of the transmission line based on the predetermined future time zone and the optimized galloping monitoring configuration result by using a multi-parallel line laser component and a monocular vision component, and obtain a line galloping capture result; A galloping parameter analysis module, which is used to calculate multi-dimensional wind deviation galloping parameters according to the line galloping capture result and obtain a galloping parameter calculation result; A galloping risk assessment module, which is used to assess the galloping risk of the transmission line according to the wind deviation galloping risk factor and in combination with the galloping parameter calculation result, and determine the line galloping risk coefficient; A line galloping early warning module, which is used to generate a wind deviation galloping early warning signal based on the line galloping risk coefficient according to a line galloping risk threshold and a galloping risk grading early warning device; The galloping capture module is used to capture the galloping of the transmission line based on the predetermined future time zone and the optimized galloping monitoring configuration result by using a multi-parallel line laser component and a monocular vision component, and obtain a line galloping capture result, including: Based on the predetermined future time zone and the optimized laser monitoring configuration result, control the multi-parallel line laser component to emit laser to the transmission line and establish a line laser grid; Identify reference points for the line laser grid according to the transmission line to obtain K identified reference points, where K is a positive integer greater than 1; Based on the predetermined future time zone and the optimized vision monitoring configuration result, synchronously control the monocular vision component to perform real-time monitoring on the transmission line to obtain a line monitoring image. The predetermined future time zone refers to the environmental conditions predicted in a future period according to weather forecasts and historical data; Enhance the line monitoring image according to the gamma enhancement function to obtain a line enhanced image; Based on the line laser grid, perform feature tracking on the line enhanced image according to the K identified reference points to obtain a K-point feature tracking result; Generate the line galloping capture result based on the K-point feature tracking result through trajectory fusion.

2. The line wind deviation and galloping warning system combining multi-parallel line lasers and monocular vision according to claim 1, characterized in that, The monitoring configuration optimization module is used to adjust the galloping monitoring configuration result of a transmission line according to a predetermined future time zone and generate an optimized galloping monitoring configuration result, including: The galloping monitoring configuration result includes the laser monitoring configuration result of the multi-parallel line laser component and the vision monitoring configuration result of the monocular vision component; Perform environmental prediction on the transmission line based on the predetermined future time zone to obtain a line environmental prediction result; Perform wind deviation galloping feature prediction on the transmission line based on the line environmental prediction result to obtain a line galloping prediction result; Perform reward and punishment correction on the laser monitoring configuration result based on the line galloping prediction result to generate an optimized laser monitoring configuration result; Perform reward and punishment correction on the visual monitoring configuration result according to the predicted result of line galloping to generate an optimized result of visual monitoring configuration; Add the optimized result of laser monitoring configuration and the optimized result of visual monitoring configuration to the optimized result of galloping monitoring configuration.

3. The line wind deviation and galloping warning system combining multi-parallel line lasers and monocular vision according to claim 1, characterized in that The gamma enhancement function is: ； where g(x, y) represents the gray value at the position (x, y) in the line enhanced image, round represents rounding processing, f(x, y) represents the gray value at the position (x, y) in the line monitoring image, mean represents the average gray value of the line monitoring image, and γ represents the gamma coefficient of image enhancement.

4. The line wind deviation and galloping warning system combining multi-parallel line lasers and monocular vision according to claim 1, characterized in that The galloping risk assessment module is used to perform galloping risk assessment on the transmission line according to the wind deviation galloping risk factors and in combination with the calculated result of the galloping parameters to determine the line galloping risk coefficient, including: The wind deviation galloping risk factors include instantaneous galloping risk, waiting galloping risk, and maintenance galloping risk; Perform risk assessment on the calculated result of the galloping parameters based on the wind deviation galloping risk factors to obtain a galloping risk assessment result; Set the initial weight based on the wind deviation galloping risk factors to determine the first weight condition for galloping risk assessment; Calculate the proportion according to the galloping risk assessment result to generate the second weight condition for galloping risk assessment; Perform a central value calculation based on the first weight condition for galloping risk assessment and the second weight condition for galloping risk assessment to generate the third weight condition for galloping risk assessment; Perform a weighted calculation on the galloping risk assessment result according to the third weight condition for galloping risk assessment to generate the line galloping risk coefficient.

5. The line wind deviation and galloping warning system combining multi-parallel line lasers and monocular vision according to claim 4, characterized in that, Perform risk assessment on the calculated result of the galloping parameters based on the wind deviation galloping risk factors to obtain a galloping risk assessment result, including: Perform backtracking learning based on the wind deviation galloping risk factors to build a multi-channel for galloping risk analysis, where the multi-channel for galloping risk analysis includes an instantaneous galloping risk analysis channel, a waiting galloping risk analysis channel, and a maintenance galloping risk analysis channel; Input the calculated result of the galloping parameters into the instantaneous galloping risk analysis channel to obtain an instantaneous galloping risk coefficient; Based on the calculated result of the galloping parameters, obtain a waiting galloping risk coefficient according to the waiting galloping risk analysis channel; Based on the calculated result of the galloping parameters, obtain a maintenance galloping risk coefficient according to the maintenance galloping risk analysis channel; Output the instantaneous galloping risk coefficient, the waiting galloping risk coefficient, and the maintenance galloping risk coefficient as the galloping risk assessment result.

6. The line wind deviation and galloping warning system combining multi-parallel line lasers and monocular vision according to claim 5, characterized in that, Perform backtracking learning based on the wind deviation galloping risk factors to build a multi-channel for galloping risk analysis, where the multi-channel for galloping risk analysis includes an instantaneous galloping risk analysis channel, a waiting galloping risk analysis channel, and a maintenance galloping risk analysis channel, including: Perform a retrospective record of galloping risk assessment on the transmission line according to the wind deviation galloping risk factors to obtain a sample set of galloping parameter calculations, a sample set of instantaneous galloping risks, a sample set of waiting galloping risks, and a sample set of maintenance galloping risks; Taking the sample set calculated from the galloping parameters as input data and the instantaneous galloping risk sample set as output data, perform deep learning on the residual neural network to build the instantaneous galloping risk analysis channel; Perform deep learning based on the sample set calculated from the galloping parameters and the waiting galloping risk sample set to establish the waiting galloping risk analysis channel; Perform deep learning based on the sample set calculated from the galloping parameters and the maintenance galloping risk sample set to generate the maintenance galloping risk analysis channel; Connect the instantaneous galloping risk analysis channel, the waiting galloping risk analysis channel, and the maintenance galloping risk analysis channel as parallel nodes to generate the multi-channel galloping risk analysis.

7. The line wind deviation and galloping warning system combining multi-parallel line lasers and monocular vision according to claim 1, characterized in that, The line galloping early warning module is used to generate a wind deviation galloping early warning signal based on the line galloping risk coefficient, according to the line galloping risk threshold and the galloping risk classification early warning device, including: Judge whether the line galloping risk coefficient is greater than or equal to the line galloping risk threshold; If the line galloping risk coefficient is greater than or equal to the line galloping risk threshold, activate the galloping risk classification early warning device; Input the line galloping risk coefficient into the galloping risk classification early warning device to obtain the wind deviation galloping early warning signal.

Images