High-voltage line safety distance prediction method based on electric field intensity and probe speed change

Abstract

The invention discloses a high-voltage line safety distance prediction method based on electric field intensity and probe speed change, and relates to the technical field of electric field safety, and the safety distance prediction method comprises the steps of early-stage preparation, input parameter acquisition, data processing, prediction model construction, alarm and feedback, and later-stage maintenance. The method has the advantages that the actual distance between the probe and the high-voltage line can be predicted more accurately by integrating multivariate data such as the electric field intensity, the change trend of the electric field intensity and the movement speed and direction of the probe, training a prediction model in combination with a neural network algorithm and calculating a loss function value by using a formula; according to the method, false alarms and alarm distance errors caused by changes of environmental factors are reduced, the precision and reliability of high-voltage line safety distance prediction are improved, and alarm mechanisms of different levels can be triggered by comparing the prediction result output by the prediction model with the preset safety distance threshold value.

Description

Technical Field

[0001] The invention relates to the field of electric field safety technology, and in particular to a method for predicting the safe distance of a high-voltage line based on changes in electric field strength and probe speed. Background Art

[0002] The existing mainstream technology uses a preset electric field strength threshold for alarm. This method determines the distance between the probe and the high-voltage line by monitoring the changes in electric field strength. When the electric field strength exceeds the preset threshold, the alarm is triggered. However, since the electric field strength is affected by many factors, such as the voltage level of the high-voltage line, weather conditions, etc., the preset electric field strength threshold is difficult to accurately reflect the actual safety distance. Therefore, the false alarm rate of this method is high, and the error of the alarm distance is also large, which to a certain extent affects the normal progress of construction and the effectiveness of safety management. For this reason, we propose a high-voltage line safety distance prediction method based on changes in electric field strength and probe speed. Summary of the invention

[0003] The purpose of the present invention is to provide a method for predicting the safe distance of a high-voltage line based on changes in electric field strength and probe speed.

[0004] In order to solve the problems raised in the above background technology, the present invention provides the following technical solutions: a method for predicting the safe distance of a high-voltage line based on the change of electric field strength and probe speed, comprising the following steps:

[0005] Step 1: Preliminary preparation: set the initial safety distance threshold according to the high-voltage line voltage level and safety specifications stipulated by the industry, and set up safety warning signs around the work site;

[0006] Step 2: Input parameter acquisition to obtain the electric field strength data around the high-voltage line and the movement speed direction data of the probe;

[0007] Step 3: Data processing: pre-process the acquired data of electric field strength, electric field strength change and probe movement speed direction, convert the data into a format suitable for neural network algorithm processing, and extract key features that can be used to predict the distance between the probe and the high-voltage line;

[0008] Step 4: Build a prediction model, select a neural network algorithm, train the prediction model, and verify and evaluate the trained model;

[0009] Step 5: Alarm and feedback: According to the output results of the prediction model, the relationship between the distance between the probe and the high-voltage line and the safety distance threshold is judged. When the prediction results show that the distance between the probe and the high-voltage line is less than the preset safety distance threshold, the alarm mechanism is triggered;

[0010] Step 6: Post-maintenance: regularly calibrate and maintain the sensors, and update and optimize the prediction model based on operating conditions and data changes.

[0011] As a further solution of the present invention: in the step one, the initial safety distance threshold is set according to the voltage level of the high-voltage line. For a 110kV high-voltage line, the safety distance is set to 4m, and for a 220kV high-voltage line, the safety distance is set to 6m. The safety warning signs are yellow warning tapes, hazard warning stickers and LED flashing lights.

[0012] As a further solution of the present invention: In the step 2, the electric field strength data around the high-voltage line is obtained in a specific manner by using an electric field strength sensor to capture the electric field strength data around the high-voltage line in real time, and recording the changing trend of the electric field strength. The movement speed and direction data of the probe is obtained in a specific manner by using a speed sensor to obtain the movement speed and direction data of the probe in real time, and recording the movement trajectory of the probe.

[0013] As a further solution of the present invention: in the step three, the preprocessing includes data cleaning and data formatting. Data cleaning can remove outliers, missing values ​​and duplicate values ​​in the data. Data formatting uses a normalization method to convert the data into the same order of magnitude. The key features are extracted by using a feature selection algorithm to screen out features related to the predicted target, and new features are generated by combining the data of electric field strength, electric field strength change trend and probe movement speed direction obtained in step two.

[0014] As a further solution of the present invention: in the step four, the neural network algorithm adopts a convolutional neural network, and the corresponding input layer, hidden layer and output layer are configured according to the input characteristics of the electric field strength, the trend of the change of the electric field strength and the direction of the probe movement speed. The specific method of training the prediction model is to divide the training data set into multiple batches with the same number of samples, calculate the loss function value on the batch, calculate the gradient through the back propagation algorithm, update the weight and bias according to the calculated gradient at a learning rate of 0.001, monitor the performance of the model on the verification data set, and when the verification performance begins to decline, terminate the training process in advance to avoid further overfitting of the model.

[0015] As a further solution of the present invention: in step 4, the specific formula for calculating the loss function value on the batch is as follows:

[0016]

[0017] Among them, y i Represents the true value of the i-th sample, y' i represents the predicted value of the i-th sample, n represents the number of samples, (y i -y' i )2 represents the square of the error between the predicted value and the true value, α represents the regularization parameter, m represents the number of features, j represents the index for traversing features, and ω j represents the weight corresponding to the j-th feature, S represents the loss function. The smaller the value of S, the smaller the average gap between the predicted value and the true value of the model, and the better the performance of the model.

[0018] As a further solution of the present invention: in the fifth step, the specific way of alarm is that the prediction model continuously monitors the distance between the probe and the high-voltage line in real time, compares the prediction result with a preset safety distance threshold, and triggers the corresponding alarm mechanism according to the result. The alarm mechanism is divided into three levels: general warning, danger warning, and high-risk warning. Set X as the safety distance threshold, X is the safety distance threshold in the first step, L is the distance shown by the prediction result. When 0.8X < L ≤ X, trigger a general warning. When 0.5X < L ≤ 0.8X, trigger a danger warning. When L ≤ 0.5X, trigger a high-risk warning.

[0019] As a further solution of the present invention: in the fifth step, the general warning method is that the LED flashing light emits yellow flashing light, flashing 2 times per second. The danger warning method is that the LED flashing light emits orange flashing light, flashing 3 times per second and giving a voice prompt. The high-risk warning method is that the LED flashing light emits red flashing light, flashing 5 times per second, automatically cutting off the power supply and equipment related to the high-voltage line, and sending a distress signal to the emergency rescue department.

[0020] As a further solution of the present invention: the specific way of the later maintenance is to set a quarterly basic calibration period for the high-precision sensors in the environment, set a semi-annual basic calibration period for the sensors with relatively low frequency and relatively stable environmental conditions, and dynamically judge the calibration time of the sensors through a formula. The specific formula is as follows:

[0021]

[0022] Among them, Q t is the basic calibration period, Q v is the influence factor of the high-voltage line voltage level, H1 is the temperature influence factor, H2 is the humidity influence factor, H3 is the electromagnetic field interference influence factor, K1, K2, and K3 are the weight coefficients of the three environmental influence factors, and K1:K2:K3 = 2:3:5. The above Q v , H1, H2, and H3 are obtained based on a large number of historical data experiments. C is the sensor accuracy requirement coefficient, F is the time since the last calibration. After operating in extreme weather or harsh environments, conduct an additional environmental adaptability inspection on the sensors, continuously collect sensor data during the operation process and analyze the data, and formulate a model update strategy according to the data analysis results.

[0023] By adopting the above technical solution, compared with the prior art, the beneficial effects of the present invention are:

[0024] 1. The present invention integrates multivariate data such as electric field strength, electric field strength change trend, and the movement speed and direction of the probe, and combines the neural network algorithm to train the prediction model and use the formula to calculate the loss function value. It can more accurately predict the actual distance between the probe and the high-voltage line, reduce false alarms and warning distance errors caused by changes in environmental factors, and improve the accuracy and reliability of high-voltage line safety distance prediction;

[0025] 2. The present invention can trigger different levels of warning mechanisms, including general warning, danger warning and high-risk warning, by comparing the prediction results output by the prediction model with the preset safety distance threshold. When the prediction results reach the high-risk warning level, measures can be taken quickly to avoid accidents according to the preset response strategy. The design of this hierarchical warning and automatic response mechanism enhances the safety awareness of operators, and can also respond quickly in emergency situations to reduce the probability of accidents.

[0026] 3. The present invention dynamically determines the calibration time of the sensor through a formula according to the high-voltage line voltage level, environmental conditions and sensor accuracy requirements. This mechanism ensures the high accuracy and reliability of the sensor under different environmental conditions. In addition, by regularly collecting and analyzing sensor data during the operation process, it helps to timely discover and correct potential errors, and can also guide the formulation of model update strategies, thereby preventing performance degradation due to sensor aging or model obsolescence, providing a lasting and stable safety guarantee for high-voltage line operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A schematic diagram of the steps of a safety distance prediction method in an embodiment of the present invention;

[0028] Figure 2 Schematic diagram of the structure of the prediction model in the embodiment of the present invention. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] Embodiment 1:

[0031] Please see attached Figure 1The present invention provides a method for predicting the safe distance of a high-voltage line based on the change of electric field strength and probe speed, comprising the following steps:

[0032] Step 1: Preliminary preparation: set the initial safety distance threshold according to the high-voltage line voltage level and safety specifications stipulated by the industry, and set up safety warning signs around the work site;

[0033] Step 2: Input parameter acquisition to obtain the electric field strength data around the high-voltage line and the movement speed direction data of the probe;

[0034] Step 3: Data processing: pre-process the acquired data of electric field strength, electric field strength change and probe movement speed direction, convert the data into a format suitable for neural network algorithm processing, and extract key features that can be used to predict the distance between the probe and the high-voltage line;

[0035] Step 4: Build a prediction model, select a neural network algorithm, train the prediction model, and verify and evaluate the trained model;

[0036] Step 5: Alarm and feedback: According to the output results of the prediction model, the relationship between the distance between the probe and the high-voltage line and the safety distance threshold is judged. When the prediction results show that the distance between the probe and the high-voltage line is less than the preset safety distance threshold, the alarm mechanism is triggered;

[0037] Step 6: Post-maintenance: regularly calibrate and maintain the sensors, and update and optimize the prediction model according to the operation status and data changes;

[0038] In step 1, the initial safety distance threshold is set according to the voltage level of the high-voltage line. For 110kV high-voltage lines, the safety distance is set to 4m, and for 220kV high-voltage lines, the safety distance is set to 6m. The safety warning signs are yellow warning tape, hazard warning stickers, and LED flashing lights;

[0039] In step 2, the electric field strength data around the high-voltage line is obtained by using an electric field strength sensor to capture the electric field strength data around the high-voltage line in real time, recording the change trend of the electric field strength, and obtaining the movement speed and direction data of the probe. The specific method is to obtain the movement speed and direction data of the probe in real time through a speed sensor and record the movement trajectory of the probe;

[0040] In step three, preprocessing includes data cleaning and data formatting. Data cleaning can remove outliers, missing values ​​and duplicate values ​​in the data. Data formatting uses normalization method to convert the data into the same order of magnitude. The key features are extracted by using feature selection algorithm to screen out features related to the predicted target, and combine the data of electric field strength, electric field strength change trend and probe movement speed direction obtained in step two to generate new features.

[0041] Specific workflow: At a high-voltage transmission line construction site, we adopted the high-voltage line safety distance prediction method of the present invention. First, an electric field strength sensor and a speed sensor were installed to collect the electric field strength data around the high-voltage line and the movement speed direction data of the probe, respectively. Within a week, a large amount of data under different weather conditions (sunny, cloudy, light rain) was collected, including electric field strength values ​​ranging from 1kV / m to 5kV / m, and probe movement speeds varying from 0.5m / s to 2m / s;

[0042] After preprocessing these data, the neural network algorithm is used to train the model. After multiple iterations of training, the average prediction error of the final model on the test set is 0.3m. Compared with the traditional method based only on a single electric field strength, the prediction error is reduced by about 40%. For example, in an actual test, the traditional method predicts that the distance between the probe and the high-voltage line is 3.5m, while the actual distance is 3.2m, with an error of 0.3m. The distance predicted by the method of the present invention is 3.18m, with an error of only 0.02m, which significantly improves the prediction accuracy.

[0043] During the testing phase, we selected 100 different test scenarios, each of which included different environmental factors and probe motion states. By comparing the predicted results with the actual distance, we found that the model's prediction error was reduced by an average of 20%, and the false alarm rate also dropped significantly. Especially under complex environmental conditions, such as strong winds and heavy rains, the model's prediction accuracy remained at a high level.

[0044] Furthermore, by integrating multivariate data such as electric field strength, electric field strength change trend, and probe movement speed and direction, and combining the neural network algorithm to train the prediction model and use the formula to calculate the loss function value, the actual distance between the probe and the high-voltage line can be predicted more accurately, reducing false alarms and warning distance errors caused by changes in environmental factors, and improving the accuracy and reliability of high-voltage line safety distance prediction.

[0045] Embodiment 2:

[0046] Based on the first embodiment, please refer to the attached Figure 1, in step 4, the neural network algorithm uses a convolutional neural network. For the input features of electric field strength, the change trend of electric field strength, and the direction of the probe movement speed, corresponding input layers, hidden layers, and output layers are configured. The specific method for training the prediction model is to divide the training data set into multiple batches with the same number of samples, calculate the loss function value on this batch, calculate the gradient through the backpropagation algorithm, and according to the calculated gradient, update the weights and biases at a learning rate of 0.001. Monitor the performance of the model on the validation data set. When the validation performance starts to decline, terminate the training process in advance to avoid further overfitting of the model. In step 4, the specific formula for calculating the loss function value on this batch is as follows:

[0047]

[0048] where y i represents the true value of the i-th sample, y’ i represents the predicted value of the i-th sample, n represents the number of samples, (y i -y’ i ) 2 represents the square of the error between the predicted value and the true value, α represents the regularization parameter, m represents the number of features, j represents the index for traversing the features, ω j represents the weight corresponding to the j-th feature, S represents the loss function, and the smaller the value of S, the smaller the average gap between the predicted value and the true value of the model, and the better the performance of the model;

[0049] In step 5, the specific method for giving an alarm is that the prediction model continuously monitors the distance between the probe and the high-voltage line in real time, compares the prediction result with a preset safety distance threshold, and triggers the corresponding alarm mechanism according to the result. The alarm mechanism is divided into three levels: general warning, danger warning, and high-risk warning. Set X as the safety distance threshold, X is the safety distance threshold in step 1, L is the distance shown in the prediction result. When 0.8X < L ≤ X, trigger a general warning. When 0.5X < L ≤ 0.8X, trigger a danger warning. When L ≤ 0.5X, trigger a high-risk warning;

[0050] In step 5, the general warning method is that the LED flashing light emits yellow flashing light, flashing 2 times per second. The danger warning method is that the LED flashing light emits orange flashing light, flashing 3 times per second, and a voice prompt is given. The high-risk warning method is that the LED flashing light emits red flashing light, flashing 5 times per second, automatically cuts off the power supply and equipment related to the high-voltage line, and sends a distress signal to the emergency rescue department.

[0051] Specific workflow: At another high-voltage line maintenance operation site, the alarm mechanism of the present invention is set. When the prediction result shows that the distance between the probe and the high-voltage line is less than the preset safety distance threshold, the alarm mechanism is triggered. In actual operation, the preset safety distance threshold is set according to the voltage level of the high-voltage line. For example, for a 110kV high-voltage line, the safety distance is set to 4m;

[0052] During an operation, the probe gradually approached the high-voltage line. When the predicted result showed that the distance was between 3.2m and 4m, a normal warning was triggered, and the LED flashing light emitted a yellow flashing light, flashing twice per second, reminding the staff to pay attention to the safe distance. As the probe continued to approach, when the distance was between 2m and 3.2m, a danger warning was triggered, the LED flashing light emitted an orange flashing light, flashing 3 times per second, and a voice prompt was given. Finally, when the distance was less than 2m, a high-risk warning was triggered, the LED flashing light emitted a red flashing light, flashing 5 times per second, automatically cutting off the power supply and equipment related to the high-voltage line, and sending a distress signal to the emergency rescue department. Through this hierarchical alarm and automatic response mechanism, the safety awareness of operators is greatly enhanced, and the probability of accidents is effectively reduced.

[0053] Furthermore, by comparing the prediction results output by the prediction model with the preset safety distance threshold, different levels of warning mechanisms can be triggered, including general warning, danger warning and high-risk warning. When the prediction results reach the high-risk warning level, measures can be taken quickly to avoid accidents according to the preset response strategy. The design of this hierarchical alarm and automatic response mechanism enhances the safety awareness of operators, and can also respond quickly in emergency situations to reduce the probability of accidents.

[0054] Embodiment three:

[0055] Based on the second embodiment, please refer to the attached Figure 1 The specific method of later maintenance is to set a quarter as the basic calibration cycle for high-precision sensors in the environment, and set a half-year basic calibration cycle for sensors with low frequency and relatively stable environmental conditions, and dynamically determine the sensor calibration time through the formula. The specific formula is as follows:

[0056]

[0057] Among them, Q t is the basic calibration cycle, Q v is the high voltage line voltage level influencing factor, H1 is the temperature influencing factor, H2 is the humidity influencing factor, H3 is the electromagnetic field interference influencing factor, K1, K2 and K3 are the weight coefficients of the three environmental influencing factors, and K1:K2:K3=2:3:5, the above Q vThe values ​​of H1, H2, and H3 are obtained based on a large amount of historical data experiments. C is the sensor accuracy requirement coefficient, and F is the time since the last calibration. After operating in extreme weather or harsh environments, additional environmental adaptability checks are performed on the sensors. Sensor data during the operation is continuously collected and analyzed. Based on the data analysis results, a model update strategy is formulated.

[0058] Specific workflow: In the long-term high-voltage line monitoring project, we strictly follow the maintenance mechanism of the present invention. For high-precision sensors in the environment, a quarterly calibration cycle is set as the basic calibration cycle. According to the formula Dynamically determine the calibration time;

[0059] For sensors with low frequency and relatively stable environmental conditions, set a half-year basic calibration cycle, and use the above formula to dynamically adjust the calibration time. After an extreme rainstorm, immediately conduct an additional environmental adaptability check on the sensor to comprehensively evaluate the impact of factors such as temperature, humidity, and electromagnetic field interference on the sensor, and determine whether early calibration is needed based on the evaluation results.

[0060] Continuously collect sensor data during the operation process and conduct in-depth analysis of the data. If it is found that the prediction accuracy of the model has decreased due to environmental changes, a detailed model update strategy will be formulated based on the data analysis results, and the model parameters will be updated in time to adapt it to the new environmental conditions again. For example, after a period of use, through the analysis of a large amount of data, the weight and bias of the model are adjusted to improve the prediction accuracy. Over a period of one year, the average false alarm rate of the system has been significantly reduced from the initial 10% to 3%, which greatly improves the reliability and durability of the system and provides long-term and stable safety protection for high-voltage line operations.

[0061] Furthermore, the sensor calibration time is dynamically determined by a formula based on the high-voltage line voltage level, environmental conditions and sensor accuracy requirements. This mechanism ensures the high accuracy and reliability of the sensor under different environmental conditions. In addition, by regularly collecting and analyzing sensor data during the operation process, it helps to promptly discover and correct potential errors, and can also guide the formulation of model update strategies, thereby preventing performance degradation due to sensor aging or model obsolescence, providing long-lasting and stable safety guarantees for high-voltage line operations.

[0062] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for predicting the safe distance of high-voltage lines based on changes in electric field strength and probe speed, characterized in that: The following steps are involved: Step 1: Preliminary preparation: set the initial safety distance threshold according to the high-voltage line voltage level and safety specifications stipulated by the industry, and set up safety warning signs around the work site; Step 2: Input parameter acquisition to obtain the electric field strength data around the high-voltage line and the movement speed direction data of the probe; Step 3: Data processing: pre-process the acquired data of electric field strength, electric field strength change and probe movement speed direction, convert the data into a format suitable for neural network algorithm processing, and extract key features that can be used to predict the distance between the probe and the high-voltage line; Step 4: Build a prediction model, select a neural network algorithm, train the prediction model, and verify and evaluate the trained model; Step 5: Alarm and feedback: According to the output results of the prediction model, the relationship between the distance between the probe and the high-voltage line and the safety distance threshold is judged. When the prediction results show that the distance between the probe and the high-voltage line is less than the preset safety distance threshold, the alarm mechanism is triggered; Step 6: Post-maintenance: regularly calibrate and maintain the sensors, and update and optimize the prediction model based on operating conditions and data changes.

2. The method for predicting the safe distance of a high-voltage line based on changes in electric field strength and probe speed according to claim 1 is characterized in that: In the step 1, the initial safety distance threshold is set according to the voltage level of the high-voltage line. For a 110kV high-voltage line, the safety distance is set to 4m, and for a 220kV high-voltage line, the safety distance is set to 6m. The safety warning signs are yellow warning tapes, hazard warning stickers, and LED flashing lights.

3. The method for predicting the safe distance of a high-voltage line based on changes in electric field strength and probe speed according to claim 1 is characterized in that: In the step 2, the electric field strength data around the high-voltage line is obtained in a specific manner by using an electric field strength sensor to capture the electric field strength data around the high-voltage line in real time, recording the changing trend of the electric field strength, and obtaining the movement speed and direction data of the probe in a specific manner by using a speed sensor to obtain the movement speed and direction data of the probe in real time, and recording the movement trajectory of the probe.

4. The method for predicting the safe distance of a high-voltage line based on changes in electric field strength and probe speed according to claim 1 is characterized in that: In the step three, the preprocessing includes data cleaning and data formatting. Data cleaning can remove outliers, missing values ​​and duplicate values ​​in the data. Data formatting uses a normalization method to convert the data into the same order of magnitude. The key features are extracted by using a feature selection algorithm to screen out features related to the predicted target, and based on the data of electric field strength, electric field strength change trend and probe movement speed direction obtained in step two, new features are combined to generate new features.

5. The method for predicting the safe distance of a high-voltage line based on the change of electric field strength and probe speed according to claim 1 is characterized in that: In the step 4, the neural network algorithm adopts a convolutional neural network, and the corresponding input layer, hidden layer and output layer are configured according to the input characteristics of the electric field strength, the trend of the change of the electric field strength and the direction of the probe movement speed. The specific method of training the prediction model is to divide the training data set into multiple batches with the same number of samples, calculate the loss function value on the batch, calculate the gradient through the back propagation algorithm, and update the weight and bias according to the calculated gradient at a learning rate of 0.

001. The performance of the model on the verification data set is monitored. When the verification performance begins to decline, the training process is terminated in advance to avoid further overfitting of the model.

6. The method for predicting the safe distance of a high-voltage line based on the change of electric field strength and probe speed according to claim 5 is characterized in that: In step 4, the specific formula for calculating the loss function value on the batch is as follows: Among them, y i Represents the true value of the i-th sample, y' i represents the predicted value of the i-th sample, n represents the number of samples, (y i -y' i ) 2 represents the square of the error between the predicted value and the true value, α represents the regularization parameter, m represents the number of features, j represents the index of the traversed feature, ω j represents the weight corresponding to the jth feature, S represents the loss function, and the smaller the value of S is, the smaller the average gap between the model's predicted value and the true value is, and the better the performance of the model is.

7. The method for predicting the safe distance of a high-voltage line based on changes in electric field strength and probe speed according to claim 1 is characterized in that: In the fifth step, the specific warning method is that the prediction model continuously monitors the distance between the probe and the high-voltage line in real time, compares the prediction result with the preset safety distance threshold, and triggers the corresponding warning mechanism according to the result. The warning mechanism is divided into three levels: general warning, danger warning, and high-risk warning. Let X be the safety distance threshold, which is the safety distance threshold in the first step, and L be the distance shown in the prediction result. When 0.8X < L ≤ X, a general warning is triggered; when 0.5X < L ≤ 0.8X, a danger warning is triggered; when L ≤ 0.5X, a high-risk warning is triggered.

8. The method for predicting the safe distance of a high-voltage line based on the change of electric field strength and probe speed according to claim 7 is characterized in that: In the fifth step, the general warning method is that the LED flashing light emits yellow flashing light, flashing 2 times per second. The danger warning method is that the LED flashing light emits orange flashing light, flashing 3 times per second, and a voice prompt is given. The high-risk warning method is that the LED flashing light emits red flashing light, flashing 5 times per second, automatically cuts off the power supply and equipment related to the high-voltage line, and sends a distress signal to the emergency rescue department.

9. The method for predicting the safe distance of a high-voltage line based on the change of electric field strength and probe speed according to claim 1 is characterized in that: The specific method of the later maintenance is as follows: for the high-precision sensors in the environment, a quarterly basic calibration period is set; for the sensors with relatively low frequency and relatively stable environmental conditions, a semi-annual basic calibration period is set, and the calibration time of the sensors is dynamically judged through a formula. The specific formula is as follows: Among them, Q t is the basic calibration cycle, Q v is the high voltage line voltage level influencing factor, H1 is the temperature influencing factor, H2 is the humidity influencing factor, H3 is the electromagnetic field interference influencing factor, K1, K2 and K3 are the weight coefficients of the three environmental influencing factors, and K1:K2:K3=2:3:5, the above Q v The values ​​of H1, H2, and H3 are obtained based on a large amount of historical data experiments. C is the sensor accuracy requirement coefficient, and F is the time since the last calibration. After operating in extreme weather or harsh environments, additional environmental adaptability checks are performed on the sensors. Sensor data during the operation is continuously collected and analyzed. Based on the data analysis results, a model update strategy is formulated.

Images