An intelligent measurement method and device for electric field strength of overhead transmission lines

Abstract

The present invention discloses an intelligent measurement method and device for the electric field strength of an overhead power transmission line, wherein the intelligent measurement method comprises: after obtaining data such as a tower model and a drone model, simulating and calculating the electric field strength of several spatial points taken from a certain set plane by a finite element method to obtain a soft measurement value; using a drone to perform a patrol measurement on each selected point to obtain a hard measurement value; inputting the spatial three-dimensional coordinates, soft measurement values ​​and hard measurement values ​​of the taken points, using a BP neural network to obtain a predicted value of the electric field strength of the taken points, and by comparing with the true value and positive and negative feedback, the BP neural network continuously learns to reduce the error between the predicted value and the true value. The present invention can replace manual measurement of the electric field strength of overhead power transmission lines, effectively solving the problems of time-consuming, labor-consuming, dangerous and costly manual measurement of aerial work; after a large amount of data is accumulated, the accuracy of electric field strength measurement can be further improved by the BP neural network method.

Description

Technical Field

[0001] The present invention relates to the technical field of ultra-high voltage transmission and transformation line detection, and in particular to an intelligent measurement method and device for the electric field strength of an overhead transmission line. Background Art

[0002] With the rapid development of the national economy and the continuous growth of electricity load, the voltage level of the power grid is constantly increasing, and the spatial density of overhead transmission lines is also increasing, and the contact with the surrounding residents is becoming closer and closer. Therefore, it is necessary to carry out the measurement of the electric field strength of overhead transmission lines, and take corresponding protective measures by measuring the electric field strength to avoid disputes. At present, the electric field strength of overhead transmission lines is measured manually, which has the problems of time-consuming, labor-intensive, dangerous and high-cost manual measurement at high altitude. Summary of the invention

[0003] The present invention aims to overcome the deficiencies of the prior art and to provide an efficient and convenient intelligent measurement method for the electric field strength of overhead power transmission lines, which can quickly and accurately measure the magnitude of the electric field strength in the power transmission lines.

[0004] To achieve the above object, the present invention provides an intelligent measurement method for electric field strength of an overhead transmission line, comprising:

[0005] S1. Import the drone model, the tower model in the overhead transmission line, the current carried by the wire, and the input voltage at both ends of the wire into the finite element simulation software, randomly select a plane passing through the center of the tower model, and use the finite element method to simulate and calculate several evenly distributed points in the plane to obtain the geometric space coordinates of these points and the soft measurement value of the electric field strength corresponding to each point;

[0006] S2. Construct a point cloud model for all selected points, and perform route planning based on intelligent algorithms. Use drones to automatically patrol along the planned routes. During the patrol process, the intelligent detection device carried by the drones conducts patrol measurements on all points one by one, and automatically calibrates the measurement points in combination with the on-site images to obtain the hard measurement value of the electric field strength corresponding to each point.

[0007] S3, the spatial geometric coordinates, soft measurement values ​​of electric field strength and hard measurement values ​​of electric field strength of all selected points are imported into the BP neural network as the input layer, and the hidden layer conditions are input at the same time, and the predicted value of electric field strength of each point is calculated by using the BP neural network;

[0008] S4. The predicted value, soft measurement value and hard measurement value of the electric field strength at each point are compared with the true value respectively. The BP neural network performs back-propagation calculation of the hidden layer error and error gradient training for multiple times, and re-iterates the learning by modifying the weights and thresholds until the error between the predicted value and the true value of the electric field strength at the point is no more than 5%; the threshold includes the error of the UAV spatial geometric positioning, the error of the model during simulation calculation, and the error of the UAV intelligent detection device caused by environmental factors.

[0009] Furthermore, the BP neural network calculates the outputs of the hidden layer and output layer neurons by determining the number of nodes in each layer, the learning rate, the number of training times and the convergence error; and calculates the hidden layer error and the error gradient by correcting the connection weights and thresholds between the hidden layer neurons and the output layer neurons in the BP neural network.

[0010] Furthermore, the intelligent measurement method uses an intelligent measuring device to measure the electric field strength of the overhead transmission line, the intelligent measuring device includes a drone and an intelligent detection device arranged on the drone, the intelligent detection device includes a microcontroller, an electric field sensing module, an AC small signal processing module, a display module and a wireless communication module, the microcontroller is respectively connected to the AC small signal processing module, the display module and the wireless communication module; the microcontroller is used to calculate the electric field value and control the display module and the wireless communication module; the electric field sensing module is connected to the microcontroller through the AC small signal processing module; the electric field sensing module is used to sense the spatial AC electric field and generate an AC small signal; the AC small signal processing module is used to process the AC small signal generated by the electric field sensing module and send it to the microcontroller; the display module is used to display the electric field value; the wireless communication module is used for the intelligent detection device to communicate with the control terminal in real time.

[0011] Furthermore, the electric field sensing module and the AC small signal processing module both include electric field strength sensors.

[0012] Furthermore, the communication mode of the wireless communication module is one or more of 5G, WIFI or Bluetooth communication modes.

[0013] Furthermore, the wireless communication mode of the intelligent measuring device is to integrate the antenna, the charging interface and the data transmission interface on the same flexible circuit board, and any communication modes can be selected for combination.

[0014] Furthermore, the wireless communication module also includes a SIM card, and a Nano-SIM socket for installing the SIM card is provided on the side of the housing of the intelligent detection device.

[0015] Furthermore, the intelligent detection device is fixed on the gimbal bracket of the UAV by mechanical binding.

[0016] Compared with the prior art, the present invention has the following beneficial effects:

[0017] (1) The intelligent measurement method of the electric field strength of overhead power transmission lines of the present invention compares the predicted value of the electric field strength of the taken point, the soft measurement value of the electric field strength and the hard measurement value of the electric field strength with the true value respectively, and performs positive and negative feedback, and the BP neural network continuously learns to reduce the error between the predicted value and the true value. The method of the present invention can replace manual measurement of the electric field strength of overhead power transmission lines, effectively solving the problems of time-consuming, labor-consuming, dangerous and high-cost manual measurement of aerial work; after a large amount of data is accumulated, the accuracy of electric field strength measurement can be further improved through the BP neural network method.

[0018] (2) The intelligent measuring device for the electric field strength of overhead power transmission lines of the present invention comprises an unmanned aerial vehicle and an intelligent detection device, wherein the intelligent detection device comprises a microcontroller, an electric field sensing module, an AC small signal processing module, a display module and a wireless communication module; the intelligent measuring device of the present invention can conveniently obtain the electric field strength data of each point taken, has a high degree of automation and high data acquisition accuracy; and can provide a reliable data source for realizing the intelligent measurement of the electric field strength of overhead power transmission lines through a BP neural network.

[0019] In addition to the above-described purposes, features and advantages, the present invention has other purposes, features and advantages. The present invention will be further described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0021] Figure 1 It is a simplified flow chart of an intelligent measurement method for electric field strength of an overhead transmission line of the present invention;

[0022] Figure 2 It is a block diagram of an intelligent measurement method for electric field strength of an overhead transmission line of the present invention;

[0023] Figure 3 It is a block diagram of a BP neural network algorithm of the present invention;

[0024] Figure 4 is a block diagram of an intelligent measuring device according to an embodiment of the present invention;

[0025] Figure 5It is a structural schematic diagram of an intelligent measuring device for electric field strength of overhead power transmission lines in the present invention;

[0026] Among them, 1-microcontroller, 2-electric field sensing module, 3-AC small signal processing module, 4-display module, 5-wireless communication module. DETAILED DESCRIPTION

[0027] The embodiments of the present invention are described in detail below with reference to the accompanying drawings, but the present invention can be implemented in many different ways as defined and covered by the claims.

[0028] See also Figure 1 This embodiment provides an intelligent measurement method for electric field strength of an overhead transmission line, comprising:

[0029] S1. First, import the drone model, the tower model in the overhead transmission line, the current carried by the conductor, and the input voltage at both ends of the conductor into the finite element simulation software, select a plane passing through the center of the tower model, select several evenly distributed points from the plane, and use the finite element method to simulate and calculate all the selected points to obtain the geometric space coordinates of these points and the soft measurement value of the electric field strength corresponding to each point. Among them, it is preferred that the selected plane is perpendicular to the horizontal direction of the conductor; it is preferred to select 100 evenly distributed points in the plane for simulation calculation to obtain the software simulation measurement value of the electric field strength of each selected point (referred to as the soft measurement value of the electric field strength, also known as the soft measurement result).

[0030] S2. Then, a point cloud model is constructed for the 100 selected points, and routes are planned for these points based on intelligent algorithms. The drone is started to automatically patrol along the planned route. During the patrol, the intelligent detection device carried by the drone conducts patrol measurements on these points one by one, and automatically calibrates the measurement points in combination with the on-site images to obtain the hard measurement value of the electric field strength corresponding to each point. During the patrol, if the drone's positioning is offset, it will automatically calibrate and hover at each point for 3 seconds. During this period, the electric field strength of the point is measured through the intelligent detection device, and it will automatically hover for 3 seconds before patrolling to the next point.

[0031] S3, the spatial geometric coordinates, soft measurement values ​​of electric field strength and hard measurement values ​​of electric field strength of all selected points are imported into the BP neural network as the input layer, and the hidden layer conditions are input at the same time, and the BP neural network is used to calculate the predicted value of electric field strength of each selected point.

[0032] S4, compare the predicted value of the electric field strength, the soft measurement value of the electric field strength, the hard measurement value of the electric field strength and the simulation structure of each point with the true value and perform positive and negative feedback respectively, and calculate the hidden layer error and error gradient by back propagation multiple times according to the variable control of multiple input layers and hidden layers, and reduce the error of the predicted value as much as possible, including: the BP neural network calculates the output of the hidden layer and output layer neurons by determining the number of nodes, learning rate, number of training times and convergence error of each layer; calculates the hidden layer error and error gradient by correcting the connection weights and thresholds of the hidden layer neurons and the output layer neurons in the BP neural network, until the error between the predicted value of the electric field strength at the point taken and the true value is no more than 5%. Among them, the true value is the measured true value obtained by measuring each point using professional tools, which can be understood by those skilled in the art.

[0033] In a specific implementation, a BP neural network is used for prediction. The BP neural network consists of three parts: an input layer, a hidden layer, and an output layer. The input layer of the research object contains the following five values: x1, x2, x3, x4, and x5; wherein x1, x2, and x3 correspond to the spatial geometric coordinates (x, y, and z) of the 100 points taken, respectively, and x4 is the simulation result of the finite element simulation software, that is, the soft measurement value of the electric field strength; and x5 is the measurement value of the unmanned aerial vehicle intelligent detection device, that is, the hard measurement value of the electric field strength; by calculating the hidden layer error and the error gradient, modifying the weight and the threshold to relearn, the output value result can be made more accurate through iterative operations; wherein the threshold mainly includes the error of the spatial geometric positioning of the unmanned aerial vehicle, the error of the model during the simulation calculation, and the error caused by environmental factors such as temperature, humidity, and the influence of other charged bodies on the unmanned aerial vehicle intelligent detection device. Through multiple multi-point calculations and neuron learning, the prediction result is as close to the true value as possible until the calculation is terminated when the error between the prediction result and the true value is less than 5%.

[0034] Next, the intelligent detection method for electric field strength of overhead transmission lines provided in the embodiments of the present application will be introduced in detail with reference to the accompanying drawings.

[0035] See also Figure 2 As shown, the calculation process of the BP algorithm of this embodiment is as follows: there are five inputs [x1, x2, x3, x4, x5], two weights [w11, w12], and two bias values ​​​​[w21, w22]. Therefore, it can be seen that the input layer has five objects and two hidden layers, two in each layer. In the BP neural network, the back propagation of errors is based on the Delta learning rule. The main purpose of the back propagation of errors, the BP neural network is to correct the weights so that the error value is minimized; the Delta learning rule is a general learning rule that uses gradient descent, thereby improving the accuracy and making the error between the predicted value and the true value less than 5%.

[0036] The following combination Figure 3 While embodiments of the invention have been described in detail, the invention can be implemented in many different ways as defined and covered by the claims.

[0037] Example 1

[0038] In Example 1, the plane with y=0 is selected as an example, and the electric field strength of 100 uniformly distributed points on the plane is measured by the finite element method. The attached table lists the electric field strength of 30 points therein, and the results are shown in Table 1.

[0039] Table 1 Example of soft measurement values ​​of electric field strength

[0040]

[0041] At the same time, the electric field strength of the 100 selected points was measured one by one using a drone equipped with an intelligent detection device. The attached table lists the electric field strength of 30 points among them. The results are shown in Table 2.

[0042] Table 2 Example of hard measured values ​​of electric field strength

[0043]

[0044] By comparing the above results, it can be seen that the error between the predicted value of the electric field strength at each point calculated by the BP network and the true value at each point is no more than 5%. Therefore, the intelligent detection method of the electric field strength of the overhead transmission line of the present invention is effective.

[0045] See also Figure 4 and Figure 5The embodiment of the present invention also provides an intelligent measuring device for the electric field strength of an overhead power transmission line, including a drone and an intelligent detection device, and the intelligent detection device is fixed on the pan-tilt bracket of the drone by mechanical binding. The intelligent detection device includes a microcontroller 1, an electric field sensing module 2, an AC small signal processing module 3, a display module 4 and a wireless communication module 5, and the microcontroller 1 is connected to the AC small signal processing module 3, the display module 4 and the wireless communication module 5 respectively; the microcontroller 1 is used to calculate the electric field value and control the wireless communication module 5 and the display module 4; the electric field value is the electric field strength value obtained by phase and vector calculation; the electric field sensing module 2 is connected to the microcontroller 1 through the AC small signal processing module 3; the electric field sensing module 2 is used to sense the spatial AC electric field and generate an AC small signal; the AC small signal processing module 3 is used to process the AC small signal generated by the electric field sensing module and send it to the microcontroller 1; the display module 4 is used to display the electric field value; the wireless communication module 5 is used to perform wireless signal transmission; the intelligent detection device detects the hard measurement value of the electric field strength of the point taken in the overhead power transmission line, and communicates with the cloud, APP end, etc. in real time through the wireless communication module. By carrying intelligent detection devices on drones, non-contact measurement of electric field values ​​can be achieved in situations where floating power supply is used and where there is large AC electric field interference, making the measurement of electric field values ​​more accurate.

[0046] In a specific embodiment, the electric field sensing module and the AC small signal processing module both include an electric field strength sensor. The wireless communication module has multiple communication modes, such as one or more of 5G, WIFI or Bluetooth communication modes. The wireless communication mode of the intelligent measuring device is to integrate the antenna with the charging interface and the data transmission interface on the same flexible circuit board, and any of the communication modes can be selected for combination. The wireless communication module also includes a SIM card, and a Nano-SIM socket for installing a SIM card is also provided on the side of the housing of the intelligent detection device.

[0047] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent measurement method for electric field strength of overhead transmission lines, characterized in that: include: S1. Import the drone model, the tower model in the overhead transmission line, the current carried by the wire, and the input voltage at both ends of the wire into the finite element simulation software, randomly select a plane passing through the center of the tower model, select a number of evenly distributed points in the plane, and use the finite element method to simulate and calculate all the selected points to obtain the geometric space coordinates of these points and the soft measurement value of the electric field strength corresponding to each point; S2. Construct a point cloud model for all selected points, and perform route planning based on intelligent algorithms. Use drones to automatically patrol along the planned routes. During the patrol process, the intelligent detection device carried by the drone performs patrol measurements on all selected points one by one, and automatically calibrates the measurement points in combination with the on-site images to obtain the hard measurement value of the electric field strength corresponding to each point. S3, the spatial geometric coordinates, soft measurement values ​​of electric field strength and hard measurement values ​​of electric field strength of all selected points are imported into the BP neural network as the input layer, and the hidden layer conditions are input at the same time, and the predicted value of electric field strength of each point is calculated by using the BP neural network; S4. The predicted value, soft measurement value and hard measurement value of the electric field strength at each point are compared with the true value respectively. The BP neural network performs back-propagation calculation of the hidden layer error and the error gradient for multiple times, and re-iterates the learning by modifying the weights and thresholds until the error between the predicted value and the true value of the electric field strength at the point is no more than 5%; the threshold includes the error of the spatial geometric positioning of the UAV, the error of the model during the simulation calculation, and the error of the UAV intelligent detection device caused by environmental factors.

2. The intelligent measurement method according to claim 1, characterized in that: The BP neural network calculates the outputs of the hidden layer and output layer neurons by determining the number of nodes in each layer, the learning rate, the number of training times and the convergence error; and calculates the hidden layer error and the error gradient by correcting the connection weights and thresholds between the hidden layer neurons and the output layer neurons in the BP neural network.

3. The intelligent measurement method according to claim 1, characterized in that: An intelligent measuring device is used to measure the electric field strength of an overhead power transmission line. The intelligent measuring device comprises an unmanned aerial vehicle and an intelligent detection device arranged on the unmanned aerial vehicle. The intelligent detection device comprises a microcontroller (1), an electric field sensing module (2), an alternating current small signal processing module (3), a display module (4) and a wireless communication module (5). The microcontroller (1) is connected to the alternating current small signal processing module (3), the display module (4) and the wireless communication module (5) respectively. The microcontroller (1) is used to calculate an electric field value and control the display module (4) and the wireless communication module (5). The electric field sensing module (2) is connected to the microcontroller (1) via the alternating current small signal processing module (3). The electric field sensing module (2) is used to sense a spatial alternating current electric field and generate an alternating current small signal. The alternating current small signal processing module (3) is used to process the alternating current small signal generated by the electric field sensing module (2) and send it to the microcontroller (1). The display module (4) is used to display the electric field value. The wireless communication module (5) is used for the intelligent detection device to communicate with a control terminal in real time.

4. The intelligent measurement method according to claim 3, characterized in that: The electric field sensing module (2) and the AC small signal processing module (3) both include electric field intensity sensors.

5. The intelligent measurement method according to claim 3, characterized in that: The communication mode of the wireless communication module (5) is one or more of 5G, WIFI or Bluetooth communication modes.

6. The intelligent measurement method according to claim 3, characterized in that: The wireless communication mode of the intelligent measuring device is to integrate the antenna, the charging interface and the data transmission interface on the same flexible circuit board, and any communication modes can be selected for combination.

7. The intelligent measurement method according to claim 3, characterized in that: The wireless communication module (5) also includes a SIM card, and a Nano-SIM socket for installing the SIM card is provided on the side of the housing of the intelligent detection device.

8. The intelligent measurement method according to claim 3, characterized in that: The intelligent detection device is fixed on the gimbal bracket of the UAV by mechanical binding.

Images