Range finding parameter optimization method and device suitable for monitoring external damage hidden danger of power transmission line

Abstract

The application discloses a ranging parameter optimization method and device suitable for monitoring external damage hidden dangers of a power transmission line, relates to the technical field of ranging parameter optimization, and comprises the following steps: acquiring risk target characteristic parameters, performing risk identification, and acquiring a target risk identification result; based on the target risk identification result, collecting N initial measurement results of the risk target and a to-be-monitored power transmission line, wherein N is greater than or equal to 3; based on the N initial measurement results, predicting the motion characteristics of the risk target, combining a comprehensive risk identification result, acquiring an optimization condition, optimizing the ranging parameter, and acquiring an optimized ranging parameter; and using the optimized ranging parameter to perform ranging for monitoring external damage hidden dangers of the power transmission line by using a host computer. The application solves the technical problem of poor adaptability of the ranging parameter optimization effect in the prior art.

Description

Technical Field

[0001] This invention relates to the field of ranging parameter optimization technology, specifically to a ranging parameter optimization method and device applicable to monitoring external damage hazards in transmission lines. Background Technology

[0002] Transmission lines, as the backbone of the power system, are crucial for safe and stable operation. However, these lines often traverse complex environments, facing serious threats from external forces such as construction machinery, oversized vehicles, and floating objects. Real-time, accurate distance monitoring is a core technological means for early warning and prevention of external damage risks. Currently, ranging technologies based on lasers, radar, or imagery are widely used in transmission line monitoring, determining the hazard level by continuously measuring the spatial distance between the target and the conductor. However, the ranging performance of existing monitoring systems heavily relies on preset ranging parameters. These parameters are often set based on general scenarios or historical experience, resulting in significant shortcomings. They lack refined perception and differentiation of the characteristics of the target itself and are usually based on static judgments using single or fixed-frequency ranging results, failing to fully consider the dynamic movement characteristics of the target. The ranging parameters cannot be adaptively adjusted, leading to monitoring delays or missed detections. Summary of the Invention

[0003] This application provides a method and apparatus for optimizing ranging parameters applicable to monitoring external damage hazards in transmission lines, which addresses the technical problem of poor adaptability of ranging parameter optimization effects in the prior art.

[0004] In view of the above problems, this application provides a method and device for optimizing ranging parameters applicable to monitoring external damage hazards in transmission lines.

[0005] Firstly, this application provides a method for optimizing ranging parameters applicable to monitoring external damage hazards in transmission lines, the method comprising:

[0006] Obtain the characteristic parameters of the risk target, perform risk identification, and obtain the target risk identification results;

[0007] Based on the target risk identification results, N preliminary measurement results of the risk target and the transmission line to be monitored are collected, where N is greater than or equal to 3;

[0008] Based on N preliminary test results, the motion characteristics of the risk target are predicted. Combined with the comprehensive risk identification results, optimization conditions are obtained, the ranging parameters are optimized, and optimized ranging parameters are obtained.

[0009] Optimized ranging parameters were adopted, and the main unit was used for ranging to monitor potential external damage to power transmission lines.

[0010] Secondly, this application provides a ranging parameter optimization device suitable for monitoring external damage hazards in transmission lines, including:

[0011] The risk target identification module is used to acquire risk target feature parameters, perform risk identification, and obtain target risk identification results.

[0012] The initial test result acquisition module is used to collect N initial test results of the risk target and the transmission line to be monitored based on the target risk identification results, wherein N is greater than or equal to 3;

[0013] The ranging parameter optimization module is used to predict the motion characteristics of the risk target based on N initial measurement results, combine the comprehensive risk identification results, obtain optimization conditions, optimize the ranging parameters, and obtain optimized ranging parameters.

[0014] The ranging parameter application module is used to perform ranging measurements by using optimized ranging parameters and a host computer for monitoring external damage hazards in power transmission lines.

[0015] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0016] This application proposes a method and device for optimizing ranging parameters suitable for monitoring external damage hazards in transmission lines. By integrating risk target feature identification, multi-time-series ranging data acquisition, dynamic motion trend prediction, and adaptive environmental perception, and using these to drive collaborative iterative optimization of ranging parameters, the method significantly improves the sensing accuracy, early warning timeliness, and overall resource utilization efficiency of the monitoring device for external damage hazards. Compared with traditional methods, the technical solution provided in this application significantly breaks through the limitations of static monitoring parameters or single adjustment strategies, achieving the technical effect of optimizing the adaptability of ranging parameters and improving the adaptability of monitoring conditions for external damage hazards in transmission lines. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating a method for optimizing ranging parameters for monitoring external damage hazards in transmission lines, as provided in an embodiment of this application.

[0019] Figure 2 This is a schematic diagram of the ranging parameter optimization device for monitoring external damage hazards in transmission lines, provided in an embodiment of this application.

[0020] The components represented by each number in the attached diagram are explained below:

[0021] Risk target identification module 100, initial test result acquisition module 200, ranging parameter optimization module 300, and ranging parameter application module 400. Detailed Implementation

[0022] This application provides a method and apparatus for optimizing ranging parameters suitable for monitoring external damage hazards in transmission lines, which addresses the technical problem of poor adaptability of ranging parameter optimization effects in existing technologies.

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0024] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0025] Example 1, as Figure 1 As shown, this application provides a method for optimizing ranging parameters suitable for monitoring external damage hazards in transmission lines, wherein the method includes:

[0026] S10: Obtain the characteristic parameters of the risk target, perform risk identification, and obtain the target risk identification results.

[0027] In monitoring potential external damage to transmission lines, existing technologies typically treat all moving targets as potential threats of the same level, or issue alarms based solely on simple distance thresholds, lacking in-depth analysis and differentiated assessment of the target's own attributes.

[0028] Step S10 in the method provided in this application embodiment includes:

[0029] The risk target is obtained, and the risk target characteristic parameters of the risk target are collected. The risk target is a target that may affect the transmission line. The risk target characteristic parameters include the risk target type, the risk target size, and the risk target orientation.

[0030] The risk target feature parameters are input into the risk identifier to obtain the target risk identification result;

[0031] The construction of the risk identifier includes:

[0032] The sample risk target type, sample risk target size, and sample risk target location are obtained to form a sample target feature parameter set;

[0033] Based on the impact of the sample risk targets on transmission lines in the sample target feature parameter set, each group of sample target risk feature parameters in the sample target feature parameter set is labeled to obtain the risk parameter set;

[0034] A risk identifier is constructed based on machine learning. The target feature parameter set of the sample is used as input, and the risk parameter set is used as supervision. The risk identifier is trained until it converges.

[0035] In this embodiment of the application, risk target feature parameters are obtained, risk identification is performed, and target risk identification results are obtained.

[0036] Specifically, firstly, risk targets are acquired, and their characteristic parameters are collected. Risk targets are those that may affect the transmission line, and their characteristic parameters include the target type, size, and orientation. For example, when a moving object enters a preset warning area in the monitoring image, the moving object is identified as a risk target to be identified. Further, image processing tools such as the OpenCV library are used to analyze the target contours in the current frame image to collect risk target types such as "crane," "excavator," and "bird." The risk target size is estimated by calculating the pixel area occupied by the target contour in the image and combining it with the camera's calibration parameters. The risk target orientation is determined by calculating the angle between the center point of the target contour and the direction of the monitored line, i.e., an angle value representing the target's angle relative to the line direction.

[0037] Furthermore, a risk identifier is constructed.

[0038] First, the sample risk target type, sample risk target size, and sample risk target location are obtained to form a sample target feature parameter set. For example, historical monitoring data is used to obtain the sample risk target type, sample risk target size, and sample risk target location, and then integrated to obtain the sample target feature parameter set.

[0039] Furthermore, based on the impact of sample risk targets on transmission lines in the sample target feature parameter set, the risk feature parameters of each group of sample targets in the sample target feature parameter set are labeled to obtain a risk parameter set. For example, based on whether the risk target will ultimately lead to external damage to the transmission line and the severity of such damage, a risk score between 0 and 1 is assigned to each group of samples to obtain a risk parameter set.

[0040] Furthermore, a risk identifier is constructed based on machine learning. The risk identifier is trained until convergence using a set of sample target feature parameters as input and a set of risk parameters as supervision. For example, the risk identifier constructed based on machine learning has a simple three-layer feedforward neural network structure. The input layer has three nodes, corresponding to the risk target type, risk target size, and risk target location, respectively. The hidden layer has five nodes, using the ReLU activation function. The output layer has one node, using a linear activation function, to output a continuous risk score, i.e., the target risk identification result. The target risk identification result is a value between 0 and 1; a larger value indicates a higher potential risk to the transmission line. The set of sample target feature parameters and the set of risk parameters are divided into a validation set and a training set in a 2:8 ratio. The sample target feature parameters in the training set are used as input, and the corresponding risk parameters are used as supervision labels. Mean squared error is used as the loss function, and the Adam optimizer is used to iteratively train the risk identifier until the model's prediction error on the validation set no longer decreases significantly. If the prediction error decreases by less than or equal to 5%, the training is considered converged. After training is complete, the risk target feature parameters are input into the risk identifier to obtain the target risk identification results.

[0041] By acquiring and analyzing the characteristic parameters of risk targets and performing intelligent risk identification, preliminary screening and risk level quantification of targets within the monitoring area are achieved. Identifying target types effectively distinguishes between high-threat targets such as cranes and excavators and low-threat targets such as birds, thereby reducing false alarms at the source and optimizing resource allocation.

[0042] S20: Based on the target risk identification results, collect N preliminary measurement results of the risk target and the transmission line to be monitored, where N is greater than or equal to 3.

[0043] After initially identifying targets with a certain risk level, traditional monitoring methods typically rely on single ranging results or periodic ranging at a fixed frequency for distance monitoring and assessment. This static, single-point data acquisition method has significant limitations, as it may be affected by transient environmental interference or equipment noise, resulting in random errors.

[0044] Step S20 in the method provided in this application embodiment includes:

[0045] Determine whether the target risk identification result is greater than or equal to the low target risk threshold. If it is greater than or equal to the threshold, collect N preliminary test results of the risk target and the transmission line to be monitored. The N preliminary test results are collected by a secondary unit at a preset time interval, and the preset time interval is based on environmental parameters and the target risk identification result.

[0046] If the value is less than the target value, the host computer will collect a distance measurement result of the risk target and the transmission line to be monitored, which will be used as the distance measurement result for monitoring external damage hazards of the transmission line.

[0047] The acquisition of the low target risk threshold and the preset time interval includes:

[0048] Obtain environmental parameters, including weather parameters and lens cleanliness parameters;

[0049] Based on the environmental parameters, environmental risk identification results are obtained, and combined with a preset low target risk threshold, a low target risk threshold is obtained.

[0050] Based on the environmental risk identification results and the target risk identification results, a comprehensive risk identification result is calculated and obtained;

[0051] The preset time interval is obtained by combining the comprehensive risk identification results with the basic time interval.

[0052] In this embodiment of the application, based on the target risk identification results, N preliminary measurement results of the risk target and the transmission line to be monitored are collected, where N is greater than or equal to 3.

[0053] Specifically, first, obtain the low target risk threshold and the preset time interval.

[0054] Environmental parameters are acquired, including weather parameters and lens cleanliness parameters. Weather parameters are obtained by determining the weather conditions ("sunny," "light fog," "light rain," or "dense fog") based on weather station data, and quantifying the weather impact with a numerical value representing visibility or interference level. For example, sunny is 1, light fog is 0.7, and dense fog is 0.3. Lens cleanliness parameters are automatically assessed by analyzing the sharpness of images of fixed reference objects captured by the camera, resulting in a cleanliness score between 0 and 1, where 0 indicates blurriness and 1 indicates complete cleanliness. The environmental risk identification result is calculated as (weather parameters + lens cleanliness parameter) / 2, yielding an environmental risk identification result between 0 and 1. For example, a sunny day with a clean lens results in an environmental risk identification result of 1; a light fog with a slightly dirty lens results in a result of 0.75.

[0055] Further, based on the environmental parameters, an environmental risk identification result is obtained, and combined with a preset low target risk threshold, a low target risk threshold is obtained. The environmental risk identification result is multiplied by the preset low risk threshold to obtain the final dynamic low target risk threshold. Low target risk threshold = preset low target risk threshold × environmental risk identification result. For example, if the low target risk threshold is set to 0.2, and the environmental risk identification result is 0.75, the final low target risk threshold = 0.2 × 0.75 = 0.15.

[0056] Furthermore, based on the environmental risk identification results and the target risk identification results, a comprehensive risk identification result is calculated. For example, the comprehensive risk identification result = environmental risk identification result + target risk identification result, to comprehensively consider the risk situation.

[0057] Furthermore, a preset time interval is obtained by combining the comprehensive risk identification result with the basic time interval. The higher the comprehensive risk, the shorter the preset time interval. For example, the preset time interval = basic time interval / comprehensive risk identification result. For instance, if the comprehensive risk identification result is 1.21 and the basic time interval is 2 seconds, then the preset time interval = 2 / 1.21 = 1.65.

[0058] Furthermore, it is determined whether the target risk identification result is greater than or equal to the low target risk threshold. If it is, N preliminary measurement results for the risk target and the transmission line to be monitored are collected. These N preliminary measurement results are acquired using a secondary unit at preset time intervals, based on environmental parameters and the target risk identification result. When the target risk identification result is greater than or equal to the low target risk threshold, it indicates that the target risk is high and further monitoring is required. In this case, a secondary unit is used to collect multiple preliminary measurement results at preset time intervals. These preliminary measurement results are acquired using a low-power secondary unit for rapid scanning and ranging. N can be determined based on the importance of the line; for example, more preliminary measurement results are collected for lines of higher importance to improve the accuracy of subsequent trend prediction, while fewer preliminary measurement results are collected for lines of lower importance to improve efficiency and reduce power consumption.

[0059] Furthermore, if the risk threshold is less than the threshold value, the main unit collects a ranging result for both the risk target and the transmission line to be monitored, which serves as the ranging result for monitoring external damage hazards to the transmission line. If the target risk identification result is less than the low target risk threshold, the target is considered to have a low risk. In this case, the secondary unit is not activated for sampling; instead, the main unit, which has higher accuracy but also higher power consumption, performs a precise ranging measurement. This ranging result is used as the final output of this monitoring, thus saving energy consumption from multiple operations by the secondary unit in low-risk scenarios while optimizing the main unit's ranging parameters to ensure ranging efficiency for low-risk targets. The main unit can use the optimized ranging parameters from the previous cycle for ranging.

[0060] By determining whether to trigger the initial measurement results based on the target risk identification results, limited acquisition resources can be prioritized for high-risk targets for intensive and continuous observation, while basic monitoring is maintained for low-risk targets. This optimizes resource allocation and allows preliminary ranging results to be obtained with lower energy consumption.

[0061] S30: Based on the N initial test results, predict the motion characteristics of the risk target, combine the comprehensive risk identification results, obtain optimization conditions, optimize the ranging parameters, and obtain optimized ranging parameters.

[0062] Existing transmission line monitoring devices typically compare distance information directly with a fixed threshold to trigger an alarm, or use preset ranging parameters for continuous monitoring. This approach cannot adapt to the ranging requirements of complex environments, resulting in insufficient performance in some high-risk, high-dynamic scenarios, while wasting monitoring resources in low-risk scenarios.

[0063] Step S30 in the method provided in this application embodiment includes:

[0064] Based on N preliminary test results, obtain the dispersion of the preliminary test results and the prediction results of the motion trend.

[0065] Among them, based on the N preliminary test results, the dispersion of the preliminary test results and the prediction results of the motion trend are obtained, including:

[0066] The ratio of the difference between the maximum and minimum values ​​of the N initial test results to the maximum value is used as the dispersion of the initial test results.

[0067] Based on N preliminary test results, motion trend prediction is performed to obtain motion trend prediction results, wherein the motion trend prediction is obtained using time series prediction.

[0068] Based on the dispersion of the initial test results, the motion trend weight is calculated and obtained, and the comprehensive risk weight is obtained by subtracting the motion trend weight from 1.

[0069] The risk parameters are obtained by weighting the motion trend prediction results and the comprehensive risk identification results using the motion trend weight and the comprehensive risk weight.

[0070] Based on the aforementioned risk parameters, optimization conditions are obtained, the ranging parameters are optimized, and optimized ranging parameters are obtained.

[0071] Specifically, based on the risk parameters, optimization conditions are obtained to optimize the ranging parameters, resulting in optimized ranging parameters, including:

[0072] Based on the risk parameters, an optimization step size is obtained, wherein the optimization step size is proportional to the risk parameters;

[0073] Using the optimized step size, the ranging parameters are iteratively optimized to obtain optimized ranging parameters;

[0074] The optimized ranging parameters are iteratively optimized using the optimized step size to obtain optimized ranging parameters, including:

[0075] Randomly generate a combination of ranging parameters as the current ranging parameters, wherein the ranging parameters include at least the transmit power, sampling frequency, and signal gain;

[0076] A fitness evaluation function is constructed, which is obtained by weighted calculation based on ranging accuracy and response time;

[0077] The ranging accuracy weight is corrected based on the environmental risk identification results, and the response time weight is corrected based on the target risk identification results. The correction accuracy weight and correction response time weight are then fused together to obtain the corrected weight.

[0078] Based on the correction accuracy weight and the correction response time weight, the ranging accuracy and the response time are weighted and calculated to obtain the fitness of the current ranging parameters;

[0079] The ranging parameters are iteratively optimized using the optimization step size until the fitness value meets the preset convergence condition or reaches the maximum number of iterations.

[0080] The ranging parameter with the highest fitness value during the iterative optimization process is output as the optimized ranging parameter.

[0081] In this embodiment of the application, based on N preliminary measurement results, the motion characteristics of the risk target are predicted, and combined with the comprehensive risk identification results, optimization conditions are obtained to optimize the ranging parameters and obtain optimized ranging parameters.

[0082] Specifically, firstly, based on N preliminary measurement results, the dispersion of the preliminary measurement results and the predicted motion trend are obtained. Specifically, the dispersion of the preliminary measurement results is calculated as the ratio of the difference between the maximum and minimum values ​​of the N preliminary measurement results to the maximum value. Preliminary measurement result dispersion = (maximum value - minimum value) / maximum value. A smaller dispersion indicates more concentrated and consistent results from multiple measurements; a larger dispersion indicates greater data fluctuation, potentially signifying violent target movement or significant measurement interference.

[0083] Furthermore, based on N initial measurement results, motion trend prediction is performed to obtain the motion trend prediction result, which is obtained using time-series prediction. Specifically, a linear regression model is used to fit the change in distance over time. This model is a single-layer neural network, and its output consists of two key trend values. The motion direction trend is represented by the slope of the regression line; a negative value indicates decreasing distance and the target is approaching, while a positive value indicates increasing distance and the target is moving away. The motion speed trend is represented by the magnitude of the slope, indicating the speed of approach or departure. For example, a motion trend prediction of -0.52 m / s based on N initial measurement results indicates that the target is approaching the track at a speed of approximately 0.52 m / s. The prediction results are mapped to characterize the risk value of the motion trend. For example, the maximum approaching speed and maximum departing speed are obtained from historical data to form a reference interval for mapping, and the prediction results are mapped to this reference interval to obtain the motion trend prediction result. For example, the motion trend prediction result = (predicted result - maximum departing speed) / (maximum approaching speed - maximum departing speed). The larger the predicted movement trend, the greater the tendency of the risk target to move toward the transmission line to be monitored, and the greater the risk.

[0084] Furthermore, based on the dispersion of the initial test results, the motion trend weight is calculated, and the comprehensive risk weight is obtained by subtracting the motion trend weight from 1. The smaller the dispersion of the initial test results, the more stable the data, the higher the reliability of the motion trend prediction, and the greater its weight. For example, the motion trend weight = 0.5 + (dispersion equilibrium point - actual dispersion) × scaling factor. The scaling factor is used to control the sensitivity of the weight's impact on dispersion changes, and can be set to 2.5 for example. For instance, if the dispersion equilibrium point is set to 0.1, the actual dispersion is 0.0419, and the scaling factor is 2.5, then the motion trend weight = 0.5 + (0.1 - 0.0419) × 2.5 = 0.65. Since the dispersion of the initial test results is lower than the equilibrium point, the motion trend prediction is considered relatively reliable, therefore its weight is 0.65. Correspondingly, the comprehensive risk weight = 1 - 0.65 = 0.35.

[0085] Furthermore, by employing motion trend weights and comprehensive risk weights, the motion trend prediction results and comprehensive risk identification results are weighted and calculated to obtain risk parameters. Risk parameter = Motion trend weight × Motion trend prediction result + Comprehensive risk weight × Comprehensive risk identification result. The obtained risk parameters quantify the risk parameters of the risk objective under multiple factors, providing a reference basis for subsequent optimization strategies.

[0086] Furthermore, based on the risk parameters, optimization conditions are obtained, and the ranging parameters are optimized to obtain the optimized ranging parameters.

[0087] Specifically, an optimization step size is obtained based on the risk parameter, where the optimization step size is directly proportional to the risk parameter. For example, if the scaling factor is set to 0.05, then the optimization step size = 0.05 × the risk parameter. For instance, if the risk parameter is 0.9, then the optimization step size = 0.05 × 0.9 = 0.045, meaning that the original parameter is adjusted by 0.045 each time for optimization.

[0088] Furthermore, a random combination of ranging parameters is generated as the current ranging parameters, wherein the ranging parameters include at least the transmit power, sampling frequency, and signal gain. For example, a random set of current ranging parameters is generated as [transmit power: 40mW, sampling frequency: 30Hz, signal gain: 8 times].

[0089] Furthermore, a fitness evaluation function is constructed, which is obtained by weighted calculation based on ranging accuracy and response time.

[0090] Specifically, the ranging accuracy weight is corrected based on the environmental risk identification result, and the response time weight is corrected based on the target risk identification result. These two weights are then fused to obtain the corrected accuracy weight and corrected response time weight. For example, the ranging accuracy weight is corrected based on the environmental risk identification result; that is, the higher the environmental risk and the greater the environmental interference, the less meaningful it is to pursue absolute accuracy, therefore its weight should be reduced. Corrected accuracy weight = Basic accuracy weight × (1 - Environmental risk identification result). For example, if the ranging accuracy weight is 0.7 and the environmental risk identification result is 0.56, then the corrected accuracy weight = 0.7 × (1 - 0.56) = 0.308. The response time weight is corrected based on the target risk identification result; that is, the higher the target risk, the higher the requirement for rapid response, therefore the response time weight should be increased. Corrected response time weight = Basic response time weight × Target risk identification result. Assuming the basic response time weight is 0.3, then the corrected response time weight = 0.3 × 0.65 = 0.195. To make the total weight sum to 1, these two corrected weights are normalized. Correction accuracy weight = 0.308 / (0.308 + 0.195) = 0.612, correction response time weight = 0.195 / (0.308 + 0.195) = 0.388.

[0091] Furthermore, based on the correction accuracy weight and correction response time weight, the ranging accuracy and response time are weighted and calculated to obtain the fitness of the current ranging parameters. Fitness = Correction Accuracy Weight × Ranging Accuracy + Correction Response Time Weight × Response Time. The ranging accuracy and response time are obtained based on historical similar ranging parameters of the current model, for example, based on historical operating results of ranging parameters whose deviation from the current ranging parameters is less than 2%. If no similar ranging parameters are available, the current ranging parameters are used for actual testing.

[0092] Furthermore, the ranging parameters are iteratively optimized using an optimized step size until the fitness value meets a preset convergence condition or reaches the maximum number of iterations. Using the current parameters as a baseline, a new set of transmission parameters is obtained using the optimized step size, and its fitness is calculated. If the new fitness is higher, this set of parameters is retained as the current best; otherwise, fine-tuning in other directions is attempted. This iteration is repeated until the preset maximum number of iterations is reached or a preset convergence condition is met, such as the fitness reaching a maximum fitness threshold. The maximum fitness threshold can be obtained based on the ranging accuracy and response time under ideal conditions.

[0093] Furthermore, the ranging parameter with the highest fitness value during the iterative optimization process is output as the optimized ranging parameter.

[0094] Intelligent optimization of ranging parameters enhances risk prediction capabilities and the dynamic adaptation of monitoring resources. First, by analyzing initial measurement results and predicting target movement trends, distance monitoring is upgraded to behavior and trajectory prediction, improving the foresight and accuracy of risk warnings. Second, the predicted movement trends are combined with comprehensive risk identification results that integrate target attributes and environmental factors to quantify current risk parameters and generate optimization conditions. Finally, based on these optimization conditions, key ranging parameters such as transmission power and sampling frequency are iteratively optimized to find the optimal performance balance point for the current specific risk scenario. This results in ranging parameters that best match the current risk state, achieving a globally synergistic optimization of monitoring accuracy, timeliness, and system efficiency.

[0095] S40: The ranging method uses optimized ranging parameters and a main unit to monitor potential external damage to power transmission lines.

[0096] In this embodiment, optimized ranging parameters are used, and a host computer is employed for ranging monitoring of external damage hazards in transmission lines. This transforms the ranging behavior of the host computer from a fixed mode to on-demand optimized execution, enabling precise ranging at any given moment using the most suitable working mode for dealing with identified risk targets and their predicted movement.

[0097] Example 2, as Figure 2 As shown, based on the same inventive concept as the ranging parameter optimization method for monitoring external damage hazards of transmission lines provided in Embodiment 1, this embodiment of the invention also provides a ranging parameter optimization device for monitoring external damage hazards of transmission lines, including:

[0098] The risk target identification module 100 is used to acquire risk target feature parameters, perform risk identification, and obtain target risk identification results.

[0099] The preliminary test result acquisition module 200 is used to collect N preliminary test results of the risk target and the transmission line to be monitored based on the target risk identification results, wherein N is greater than or equal to 3;

[0100] The ranging parameter optimization module 300 is used to predict the motion characteristics of the risk target based on N initial measurement results, combine the comprehensive risk identification results, obtain optimization conditions, optimize the ranging parameters, and obtain optimized ranging parameters.

[0101] The ranging parameter application module 400 is used to perform ranging measurements by using optimized ranging parameters and a host computer to monitor potential external damage to power transmission lines.

[0102] In one embodiment, the risk target identification module 100 is further configured to:

[0103] The risk target is obtained, and the risk target characteristic parameters of the risk target are collected. The risk target is a target that may affect the transmission line. The risk target characteristic parameters include the risk target type, the risk target size, and the risk target orientation.

[0104] The risk target feature parameters are input into the risk identifier to obtain the target risk identification result;

[0105] The construction of the risk identifier includes:

[0106] The sample risk target type, sample risk target size, and sample risk target location are obtained to form a sample target feature parameter set;

[0107] Based on the impact of the sample risk targets on transmission lines in the sample target feature parameter set, each group of sample target risk feature parameters in the sample target feature parameter set is labeled to obtain the risk parameter set;

[0108] A risk identifier is constructed based on machine learning. The target feature parameter set of the sample is used as input, and the risk parameter set is used as supervision. The risk identifier is trained until it converges.

[0109] In one embodiment, the initial test result acquisition module 200 is further configured to:

[0110] Determine whether the target risk identification result is greater than or equal to the low target risk threshold. If it is greater than or equal to the threshold, collect N preliminary test results of the risk target and the transmission line to be monitored. The N preliminary test results are collected by a secondary unit at a preset time interval, and the preset time interval is based on environmental parameters and the target risk identification result.

[0111] If the value is less than the target value, the host computer will collect a distance measurement result of the risk target and the transmission line to be monitored, which will be used as the distance measurement result for monitoring external damage hazards of the transmission line.

[0112] The acquisition of the low target risk threshold and the preset time interval includes:

[0113] Obtain environmental parameters, including weather parameters and lens cleanliness parameters;

[0114] Based on the environmental parameters, environmental risk identification results are obtained, and combined with a preset low target risk threshold, a low target risk threshold is obtained.

[0115] Based on the environmental risk identification results and the target risk identification results, a comprehensive risk identification result is calculated and obtained;

[0116] The preset time interval is obtained by combining the comprehensive risk identification results with the basic time interval.

[0117] In this embodiment of the application, based on the target risk identification results, N preliminary measurement results of the risk target and the transmission line to be monitored are collected, where N is greater than or equal to 3.

[0118] In one embodiment, the ranging parameter optimization module 300 is further configured to:

[0119] Based on N preliminary test results, obtain the dispersion of the preliminary test results and the prediction results of the motion trend.

[0120] Among them, based on the N preliminary test results, the dispersion of the preliminary test results and the prediction results of the motion trend are obtained, including:

[0121] The ratio of the difference between the maximum and minimum values ​​of the N initial test results to the maximum value is used as the dispersion of the initial test results.

[0122] Based on N preliminary test results, motion trend prediction is performed to obtain motion trend prediction results, wherein the motion trend prediction is obtained using time series prediction.

[0123] Based on the dispersion of the initial test results, the motion trend weight is calculated and obtained, and the comprehensive risk weight is obtained by subtracting the motion trend weight from 1.

[0124] The risk parameters are obtained by weighting the motion trend prediction results and the comprehensive risk identification results using the motion trend weight and the comprehensive risk weight.

[0125] Based on the aforementioned risk parameters, optimization conditions are obtained, the ranging parameters are optimized, and optimized ranging parameters are obtained.

[0126] Specifically, based on the risk parameters, optimization conditions are obtained to optimize the ranging parameters, resulting in optimized ranging parameters, including:

[0127] Based on the risk parameters, an optimization step size is obtained, wherein the optimization step size is proportional to the risk parameters;

[0128] Using the optimized step size, the ranging parameters are iteratively optimized to obtain optimized ranging parameters;

[0129] The optimized ranging parameters are iteratively optimized using the optimized step size to obtain optimized ranging parameters, including:

[0130] Randomly generate a combination of ranging parameters as the current ranging parameters, wherein the ranging parameters include at least the transmit power, sampling frequency, and signal gain;

[0131] A fitness evaluation function is constructed, which is obtained by weighted calculation based on ranging accuracy and response time;

[0132] The ranging accuracy weight is corrected based on the environmental risk identification results, and the response time weight is corrected based on the target risk identification results. The correction accuracy weight and correction response time weight are then fused together to obtain the corrected weight.

[0133] Based on the correction accuracy weight and the correction response time weight, the ranging accuracy and the response time are weighted and calculated to obtain the fitness of the current ranging parameters;

[0134] The ranging parameters are iteratively optimized using the optimization step size until the fitness value meets the preset convergence condition or reaches the maximum number of iterations.

[0135] The ranging parameter with the highest fitness value during the iterative optimization process is output as the optimized ranging parameter.

[0136] In summary, the embodiments of this application have at least the following technical effects:

[0137] This application proposes a method and device for optimizing ranging parameters suitable for monitoring external damage hazards in transmission lines. By integrating risk target feature identification, multi-time-series ranging data acquisition, dynamic motion trend prediction, and adaptive environmental perception, and using these to drive collaborative iterative optimization of ranging parameters, the method significantly improves the sensing accuracy, early warning timeliness, and overall resource utilization efficiency of the monitoring device for external damage hazards. Specifically, firstly, through intelligent identification of the type, size, and orientation of risk targets, refined classification and initial risk assessment of potential threats are achieved, laying the foundation for subsequent differentiated monitoring strategies. This effectively avoids the unnecessary consumption of monitoring resources on low-risk targets and enhances the early identification capability of risk targets. Furthermore, by introducing multiple ranging results based on time series, not only can the dispersion of the ranging data be calculated to reflect the stability of the current monitoring, but more importantly, it can predict the movement trend and speed changes of risk targets, thereby enabling proactive prediction of movement risks. Furthermore, by integrating target risk and environmental risk into a comprehensive risk identification result, and dynamically adjusting monitoring thresholds and data acquisition intervals accordingly, the reliability and timeliness of basic monitoring data under different operating conditions are ensured. Finally, based on the risk parameters obtained by fusing motion trends and comprehensive risk weights, the optimization step size is adaptively determined, and key ranging parameters such as transmission power, sampling frequency, and signal gain are iteratively optimized. This process is guided by a risk-corrected fitness evaluation function, ultimately intelligently finding the optimal parameter combination that balances ranging accuracy, response speed, and energy consumption in a specific scenario. Compared to traditional methods, the technical solution provided in this application significantly breaks through the limitations of static monitoring parameters or single adjustment strategies, achieving the technical effect of optimizing the adaptability of ranging parameters and improving the adaptability of monitoring operating conditions for external damage hazards in transmission lines.

[0138] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0139] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0140] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A method for optimizing ranging parameters applicable to monitoring external damage hazards in transmission lines, characterized in that, include: Obtain the characteristic parameters of the risk target, perform risk identification, and obtain the target risk identification results; Based on the target risk identification results, N preliminary measurement results of the risk target and the transmission line to be monitored are collected, where N is greater than or equal to 3; Based on N preliminary measurement results, the motion characteristics of the risk target are predicted. Combined with the comprehensive risk identification results, optimization conditions are obtained to optimize the ranging parameters, including: Based on N preliminary test results, obtain the dispersion of the preliminary test results and the prediction results of the motion trend. Based on the dispersion of the initial test results, the motion trend weight is calculated and obtained, and the comprehensive risk weight is obtained by subtracting the motion trend weight from 1. The risk parameters are obtained by weighting the motion trend prediction results and the comprehensive risk identification results using the motion trend weight and the comprehensive risk weight. Based on the aforementioned risk parameters, optimization conditions are obtained to optimize the ranging parameters, resulting in optimized ranging parameters, including: Based on the risk parameters, an optimization step size is obtained, wherein the optimization step size is proportional to the risk parameters; Using the aforementioned optimization step size, the ranging parameters are iteratively optimized to obtain optimized ranging parameters, including: Randomly generate a combination of ranging parameters as the current ranging parameters, wherein the ranging parameters include at least the transmit power, sampling frequency, and signal gain; A fitness evaluation function is constructed, which is obtained by weighted calculation based on ranging accuracy and response time; The ranging accuracy weight is corrected based on the environmental risk identification results, and the response time weight is corrected based on the target risk identification results. The correction accuracy weight and correction response time weight are then fused together to obtain the corrected weight. Based on the correction accuracy weight and the correction response time weight, the ranging accuracy and the response time are weighted and calculated to obtain the fitness of the current ranging parameters; The ranging parameters are iteratively optimized using the optimization step size until the fitness value meets the preset convergence condition or reaches the maximum number of iterations. The ranging parameter with the highest fitness value during the iterative optimization process is output as the optimized ranging parameter. Optimized ranging parameters were adopted, and the main unit was used for ranging to monitor potential external damage to power transmission lines.

2. The method for optimizing ranging parameters for monitoring external damage hazards in transmission lines according to claim 1, characterized in that, Obtain the characteristic parameters of the risk target, perform risk identification, and obtain the target risk identification results, including: The risk target is obtained, and the risk target characteristic parameters of the risk target are collected. The risk target is a target that may affect the transmission line. The risk target characteristic parameters include the risk target type, the risk target size, and the risk target orientation. Input the risk target feature parameters into the risk identifier to obtain the target risk identification result.

3. The method for optimizing ranging parameters for monitoring external damage hazards in transmission lines according to claim 2, characterized in that, The construction of the risk identifier includes: The sample risk target type, sample risk target size, and sample risk target location are obtained to form a sample target feature parameter set; Based on the impact of the sample risk targets on transmission lines in the sample target feature parameter set, each group of sample target risk feature parameters in the sample target feature parameter set is labeled to obtain the risk parameter set; A risk identifier is constructed based on machine learning. The target feature parameter set of the sample is used as input, and the risk parameter set is used as supervision. The risk identifier is trained until it converges.

4. The method for optimizing ranging parameters for monitoring external damage hazards in transmission lines according to claim 1, characterized in that, Based on the target risk identification results, N preliminary measurement results are collected for the risk target and the transmission line to be monitored, where N is greater than or equal to 3, including: Determine whether the target risk identification result is greater than or equal to the low target risk threshold. If it is greater than or equal to the threshold, collect N preliminary test results of the risk target and the transmission line to be monitored. The N preliminary test results are collected by a secondary unit at a preset time interval, and the preset time interval is based on environmental parameters and the target risk identification result. If the distance is less than the target distance, the host computer will collect a distance measurement result of the risk target and the transmission line to be monitored, which will be used as the distance measurement result for monitoring external damage hazards of the transmission line.

5. The method for optimizing ranging parameters for monitoring external damage hazards in transmission lines according to claim 4, characterized in that, The acquisition of the low target risk threshold and the preset time interval includes: Obtain environmental parameters, including weather parameters and lens cleanliness parameters; Based on the environmental parameters, environmental risk identification results are obtained, and combined with a preset low target risk threshold, a low target risk threshold is obtained. Based on the environmental risk identification results and the target risk identification results, a comprehensive risk identification result is calculated and obtained; The preset time interval is obtained by combining the comprehensive risk identification results with the basic time interval.

6. The method for optimizing ranging parameters for monitoring external damage hazards in transmission lines according to claim 1, characterized in that, Based on N preliminary test results, the dispersion of the preliminary test results and the prediction results of the motion trend are obtained, including: The ratio of the difference between the maximum and minimum values ​​of the N initial test results to the maximum value is used as the dispersion of the initial test results. Based on N preliminary test results, motion trend prediction is performed to obtain motion trend prediction results, wherein the motion trend prediction is obtained using time series prediction.

7. A ranging parameter optimization device suitable for monitoring external damage hazards in transmission lines, characterized in that, The apparatus for implementing the ranging parameter optimization method for monitoring external damage hazards in transmission lines according to any one of claims 1-6, the apparatus comprising: The risk target identification module is used to acquire risk target feature parameters, perform risk identification, and obtain target risk identification results. The initial test result acquisition module is used to collect N initial test results of the risk target and the transmission line to be monitored based on the target risk identification results, wherein N is greater than or equal to 3; The ranging parameter optimization module is used to predict the motion characteristics of the risk target based on N initial measurement results, combine them with the comprehensive risk identification results, obtain optimization conditions, and optimize the ranging parameters to obtain optimized ranging parameters, including: Based on the risk parameters, an optimization step size is obtained, wherein the optimization step size is proportional to the risk parameters; Using the aforementioned optimization step size, the ranging parameters are iteratively optimized to obtain optimized ranging parameters, including: Randomly generate a combination of ranging parameters as the current ranging parameters, wherein the ranging parameters include at least the transmit power, sampling frequency, and signal gain; A fitness evaluation function is constructed, which is obtained by weighted calculation based on ranging accuracy and response time; The ranging accuracy weight is corrected based on the environmental risk identification results, and the response time weight is corrected based on the target risk identification results. The correction accuracy weight and correction response time weight are then fused together to obtain the corrected weight. Based on the correction accuracy weight and the correction response time weight, the ranging accuracy and the response time are weighted and calculated to obtain the fitness of the current ranging parameters; The ranging parameters are iteratively optimized using the optimization step size until the fitness value meets the preset convergence condition or reaches the maximum number of iterations. The ranging parameter with the highest fitness value during the iterative optimization process is output as the optimized ranging parameter. The ranging parameter application module is used to perform ranging measurements by using optimized ranging parameters and a host computer for monitoring external damage hazards in power transmission lines.

Images