Method and device for measuring sag of high-voltage transmission line

Abstract

The invention relates to a high-voltage transmission line sag measurement method and device. The method comprises the following steps: acquiring transmission line images at different heights and different angles by using a transmission tower climbing robot and a sag measurement device; marking and preprocessing the power transmission line image to obtain a training sample; inputting the training sample into a YOLOv8 network model for training to obtain a power transmission line image segmentation model; segmenting a mask of a power transmission line on the target image by adopting a power transmission line image segmentation model; segmenting an image mask of the power transmission line on the target image by adopting a power transmission line image segmentation model; according to the method, non-contact evaluation of the sag of the power transmission line is realized based on the image of the power transmission line, measurement of the sag of the power transmission line can be completed without short-distance climbing or power-off operation, and thus the personal safety risk of maintenance operation is remarkably reduced.

Description

Technical Field

[0001] This invention relates to the field of high-voltage transmission line sag measurement technology, and in particular to a method and apparatus for measuring high-voltage transmission line sag. Background Technology

[0002] High-voltage transmission line sag measurement is a crucial aspect of power system operation and maintenance. Proper sag control directly impacts line safety; too little sag leads to excessive conductor tension, potentially causing line breaks or tower overload, while too much sag may result in insufficient safety distances, leading to discharges or short circuits. Furthermore, sag affects transmission efficiency, requiring adaptation to environmental changes such as temperature and icing to maintain stability, extend equipment lifespan, and meet industry standards. Traditional measurement methods, including theodolite / total station methods, equal-length methods, and span-end observation methods, offer high accuracy but are limited by terrain. Modern technologies such as laser rangefinders, UAV aerial surveying, and online monitoring systems improve efficiency through non-contact or real-time methods, making them particularly suitable for complex environments or critical sections. During measurement, attention must be paid to environmental correction, multi-span coordination, and safety procedures. Future trends will move towards intelligentization, the Internet of Things (IoT), and digital twins to achieve more precise dynamic management.

[0003] Current methods for measuring sag still have some limitations: traditional methods, such as theodolite surveying, are limited by terrain conditions and human error, and their accuracy is difficult to guarantee in complex environments or large spans; UAV aerial surveying improves efficiency, but it is easily affected by weather and data processing is complex, making it difficult to achieve stable monitoring; online monitoring systems can acquire data in real time, but the high cost of sensors and the difficulty in installation and maintenance make it difficult to promote on a large scale; indirect calculation methods rely on theoretical models and cannot accurately reflect the actual state of the conductor, especially under extreme weather conditions where the error is large. Summary of the Invention

[0004] To address the aforementioned problems, the present invention aims to provide a method and apparatus for measuring the sag of high-voltage transmission lines.

[0005] A method for measuring the sag of a high-voltage transmission line, comprising:

[0006] Step 1: Obtain images of power transmission lines at different heights and angles;

[0007] Step 2: After labeling and preprocessing the transmission line images, training samples are obtained;

[0008] Step 3: Input the training samples into the YOLOv8 network model for training to obtain the power transmission line image segmentation model;

[0009] Step 4: Use the power transmission line image segmentation model to segment the mask of the power transmission line on the target image;

[0010] Step 5: Use the power transmission line image segmentation model to segment the image mask of the power transmission line in the target image;

[0011] Step 6: Calculate the sag of the transmission line based on the image mask of the transmission line.

[0012] Preferably, in step 3, the loss function of the YOLOv8 network model is:

[0013]

[0014] in, This is the final loss value. For boundary loss, For classifying losses, For the distribution focus loss, , , These are the coefficients corresponding to the three. To predict the intersection-union ratio of the boundary with the true boundary, It is Euclidean distance. and These are the center points of the predicted mask and the real mask, respectively. It is the diagonal length that simultaneously includes both the predicted boundary and the true boundary. It is a weighting function. It is a parameter that measures the consistency of aspect ratio. It's a real label. It is the probability of that category predicted by the model. For Softmax prediction The probability of.

[0015] Preferably, step 6: calculating the sag of the transmission line based on the image mask of the transmission line includes:

[0016] Step 6.1: At a distance h1 from the ground, take an image of the first power transmission line to obtain the image mask of the first power transmission line, and obtain the first position of the lowest point of the power transmission line in the image. );

[0017] Step 6.2: At a distance h2 from the ground, take an image of the second transmission line to obtain the image mask of the second transmission line, and obtain the second position of the lowest point of the transmission line in the image. );

[0018] Step 6.3: Calculate the sag of the transmission line based on the first and second positions of the lowest point on the two images of the transmission line taken.

[0019] Preferably, in step 6.3, the formula for calculating the sag of the transmission line is:

[0020]

[0021] in, Indicates the sag of the transmission line. This indicates the height of the transmission line from the ground at the suspension point on the tower.

[0022] The present invention also provides a high-voltage transmission line sag measuring device, applied to a high-voltage transmission line sag measuring method, comprising:

[0023] A power transmission tower climbing robot has a sag measuring device installed on its external surface. The sag measuring device includes a first motor, a second motor, a third motor, a camera, a motor control circuit board, and a base. The first motor, the second motor, the third motor, the camera, and the motor control circuit board are all mounted on the base. The motor control circuit board is communicatively connected to the first motor, the second motor, and the third motor, respectively, and is used to control the rotation of the first motor, the second motor, and the third motor according to the spatial attitude of the camera, so that the camera remains parallel to the ground in real time.

[0024] Preferably, the camera is equipped with an inertial navigation component to obtain the camera's yaw angle, pitch angle, and roll angle, and to calculate the camera's rotation matrix using the ground as a reference frame.

[0025]

[0026] in, Indicates the camera's yaw angle. Indicates the camera's pitch angle. Indicates the camera's roll angle. This represents the camera's rotation matrix.

[0027] Preferably, the base is equipped with an inertial navigation component to obtain the base's yaw angle, pitch angle, and roll angle, and to calculate the base's rotation matrix using the ground as a reference frame.

[0028]

[0029] in, Indicates the yaw angle of the base. Indicates the pitch angle of the base. Indicates the roll angle of the base. This represents the rotation matrix of the base.

[0030] Preferably, the rotation matrix of the camera relative to the base is calculated based on the rotation matrix of the camera and the rotation matrix of the base:

[0031]

[0032] make ,but

[0033] in, The rotation angles of the second, third, and first motors are respectively. A PID algorithm is introduced into the motor control circuit board to control the rotation of all motors, so that the camera remains parallel to the ground in real time.

[0034] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0035] This invention relates to a method for measuring the sag of high-voltage transmission lines. Compared with the prior art, this invention relies on images of the transmission line to achieve non-contact assessment of the sag of the transmission line. The measurement of the sag of the transmission line can be completed without close-range climbing or power outage operations, thereby significantly reducing the personal safety risks of maintenance operations.

[0036] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the 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.

[0038] Figure 1 This is a schematic diagram of the image acquisition method for power transmission lines provided by the present invention;

[0039] Figure 2 A diagram of the sag measuring device provided by the present invention;

[0040] Figure 3 A flowchart illustrating the image segmentation model provided by this invention;

[0041] Figure 4 A schematic diagram of the lowest point of the power transmission line in two images provided by the present invention;

[0042] Figure 5 A flowchart for calculating the sag of a single transmission line provided by the present invention;

[0043] Figure 6 This is a diagram of the electrical control system of the sag measuring device provided by the present invention. Detailed Implementation

[0044] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0045] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0046] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0047] Please see Figure 3 A method for measuring the sag of high-voltage transmission lines, comprising:

[0048] Step 1: Obtain images of power transmission lines at different heights and angles;

[0049] like Figure 1 As shown, a power transmission tower climbing robot was used to climb various types of power transmission towers and take numerous images of power lines at different heights and angles. During the shooting process, the camera in the sag measuring device had to remain parallel to the ground in real time.

[0050] Step 2: After labeling and preprocessing the transmission line images, training samples are obtained;

[0051] In step 2, an image annotation tool is used to annotate the mask of the power transmission line and generate corresponding labels. YOLOv8 is then used to process this image data and generate an image segmentation model of the power transmission line.

[0052] Step 3: Input the training samples into the YOLOv8 network model for training to obtain the power transmission line image segmentation model;

[0053] The workflow diagram of the image segmentation model for power transmission lines is as follows: Figure 3 As shown, the process is divided into two phases: training and inference. The goal of the training phase is to teach the model how to detect targets by continuously adjusting the network weights to make its predictions increasingly closer to the real mask. First, the input is labeled data of the power transmission line image, followed by image preprocessing and enhancement, including image scaling and data augmentation. Next, the processed image data is input into the backbone network, neck network, and head network. The backbone network includes cross-stage subnetworks and a spatial pyramid pooling module, responsible for extracting multi-level features from the input image. The neck network fuses features extracted from the backbone network at different scales, enriching the feature representation capability, including upsampling high-level feature maps and laterally connecting them to low-level feature maps, and downsampling low-level feature maps and fusing them with high-level features. The head network predicts the classification probability and the boundary of the power transmission line mask. Then, the loss function of the network is calculated:

[0054]

[0055] in, This is the final loss value. For boundary loss, For classifying losses, For the distribution focus loss, , , These are the coefficients corresponding to the three. To predict the intersection-union ratio of the boundary with the true boundary, It is Euclidean distance. and These are the center points of the predicted mask and the real mask, respectively. It is the diagonal length that simultaneously includes both the predicted boundary and the true boundary. It is a weighting function. It is a parameter that measures the consistency of aspect ratio. It is a real label (0 or 1). It is the probability of this class predicted by the model (after Sigmoid activation). For Softmax prediction The probability of.

[0056] In the inference phase, the trained model is used to segment the image of the new power transmission line. The image undergoes preprocessing and enhancement before being sequentially input into the backbone network, neck network, and head network. Then, post-processing—non-maximum suppression—is performed to select the most effective mask. Finally, the segmented power transmission line mask is output.

[0057] Step 4: Use the power transmission line image segmentation model to segment the mask of the power transmission line on the target image;

[0058] Step 5: Use the power transmission line image segmentation model to segment the image mask of the power transmission line in the target image;

[0059] Step 6: Calculate the sag of the transmission line based on the image mask of the transmission line.

[0060] Directly using the generated image segmentation model to extract the image mask of the power transmission line results in significant errors because the edges of the image mask generated by the segmentation model are relatively coarse. Therefore, further processing of the image mask is needed to accurately identify the location of the lowest point of the power transmission line. Power transmission lines sag naturally under gravity, and the curve they form can be described by the catenary equation. However, the images of power transmission lines captured by the sag measurement device undergo affine and perspective transformations, making the solution to the catenary equation very complex. Here, a quadratic polynomial is used to fit and solve the equation only in a local region around the lowest point of the power transmission line.

[0061] The origin is the point where the power transmission tower climbing robot is located, where the angle steel of the tower intersects with the ground. The height of the transmission line suspension point on the tower from the ground is... The distance from the sag measuring device to the ground is Ignore the angle of inclination between the tower angle steel and the ground. At this time, the sag measuring device takes the first image 1 of the high-voltage transmission line, and the location of the lowest point of a certain transmission line in the image is found by the above method. ),in The data is normalized, with a value range of [0,1]. Then, the power transmission tower climbing robot climbs upwards to a point [distance from the ground]. At the height of the high-voltage transmission line, take a second image 2 and find the location of the lowest point of the transmission line in the previous image. ),in The data is normalized, with a value range of [0,1]. A schematic diagram of the two measurements is shown below. Figure 4 As shown. Then the sag of the transmission line... The procedure for calculating the sag of a single transmission line is as follows: Figure 5 As shown.

[0062] The above method calculates the sag of a single transmission line. The camera on the sag measuring device can simultaneously capture images of multiple transmission lines, thus allowing for the simultaneous acquisition of the lowest points of multiple lines. As the transmission tower climbing robot ascends, it continuously captures images of the transmission lines and tracks the positional changes of each line. This ensures that each transmission line can be distinguished during the second acquisition of its lowest point, avoiding mismatch issues due to the large number of transmission lines.

[0063] The present invention also provides a high-voltage transmission line sag measuring device, applied to a high-voltage transmission line sag measuring method, comprising:

[0064] like Figure 2 As shown, a power transmission tower climbing robot has a sag measuring device installed on its external surface. The sag measuring device includes a first motor, a second motor, a third motor, a camera, a motor control circuit board, and a base. The first motor, the second motor, the third motor, the camera, and the motor control circuit board are all mounted on the base. The motor control circuit board is communicatively connected to the first motor, the second motor, and the third motor, respectively, and is used to control the rotation of the first motor, the second motor, and the third motor according to the spatial attitude of the camera, so that the camera remains parallel to the ground in real time.

[0065] The electrical control system of the entire sag measuring device, such as Figure 6 As shown, the motor control circuit board controls the drivers for motors 1-3, thereby controlling motors 1-3 to ensure the camera remains level with the ground. The Jetson Orin Nano edge computing unit acquires image information from the camera and calculates the sag of multiple power transmission lines. The entire sag measurement device communicates with the power transmission tower climbing robot controller via USB.

[0066] The electronic control system controls the motor to keep the camera level with the ground as follows. There are two inertial navigation units: one on the camera and one on the base of the sag measurement device. Assume the inertial navigation unit on the camera reads the yaw, pitch, and roll angles as follows: Find its corresponding rotation matrix:

[0067]

[0068] The yaw, pitch, and roll angles read from the inertial navigation components on the same base are... Find its corresponding rotation matrix:

[0069]

[0070] The rotation matrix of the camera relative to the base can then be calculated: .

[0071] make ,but

[0072] in, For matrix Various data in the middle; This refers to the rotation angle of motors 2, 3, and 1. Once the motors have completed their rotations, the camera remains horizontal to the ground. To ensure the camera remains horizontal in real-time, PID control of the motor rotation is implemented. These are the input parameters for the PID controllers of three motors, enabling the motors to respond quickly and keeping the camera level in real time. The design of the PID controller for each motor is the same; we will now use the design of a single motor PID controller as an example. First, determine the PID formula. ,in For the first The controller output at a given time is used to control the motor rotation angle. For the first The difference between the target angle and the actual angle at any given moment. This is the cumulative sum of errors. , , These are the set PID parameters. Through the above control strategy, the motor can be moved quickly to a specified angle, thus keeping the camera level in real time.

[0073] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0074] This invention enables non-contact assessment of power transmission line sag based on images of the power transmission line. It can measure the power transmission line sag without the need for close-range climbing or power outage operations, thereby significantly reducing the personal safety risks of maintenance work.

[0075] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for measuring the sag of high-voltage transmission lines, characterized in that, include: Step 1: Obtain images of power transmission lines at different heights and angles; Step 2: After labeling and preprocessing the transmission line images, training samples are obtained; Step 3: Input the training samples into the YOLOv8 network model for training to obtain the power transmission line image segmentation model; Step 4: Use the power transmission line image segmentation model to segment the mask of the power transmission line on the target image; Step 5: Use the power transmission line image segmentation model to segment the image mask of the power transmission line in the target image; Step 6: Calculate the sag of the transmission line based on the image mask of the transmission line.

2. The method for measuring the sag of a high-voltage transmission line according to claim 1, characterized in that, In step 3, the loss function of the YOLOv8 network model is: Among them, L total L is the final loss value. box For boundary regression loss, L cls For classification loss, L dfl For the distribution focus loss, λ box , λ cls , λ dfl These are the coefficients corresponding to the three, IoU is the intersection-union ratio between the predicted boundary and the true boundary, ρ is the Euclidean distance, and b and b gt Here, represents the center points of the prediction mask and the ground truth mask, respectively; c is the diagonal length that simultaneously encompasses both the prediction and ground truth boundaries; α is the weighting function; v is a parameter measuring aspect ratio consistency; y is the ground truth label; p is the probability of the class predicted by the model; and S... i For y predicted by Softmax i The probability of.

3. The method for measuring the sag of a high-voltage transmission line according to claim 1, characterized in that, Step 6: Calculate the sag of the transmission line based on the image mask of the transmission line, including: Step 6.1: Take an image of the first power transmission line at a distance h1 from the ground to obtain the image mask of the first power transmission line and obtain the first position (x1, y1) of the image where the lowest point of the power transmission line is located. Step 6.2: Take an image of the second power transmission line at a distance h2 from the ground to obtain the image mask of the second power transmission line, and obtain the second position (x2, y2) of the lowest point of the power transmission line in the image; Step 6.3: Calculate the sag of the transmission line based on the first and second positions of the lowest point on the two images of the transmission line taken.

4. The method for measuring the sag of a high-voltage transmission line according to claim 3, characterized in that, In step 6.3, the formula for calculating the sag of the transmission line is: Where H represents the sag of the transmission line, and h0 represents the height of the transmission line from the ground at the suspension point of the tower.

5. A high-voltage transmission line sag measuring device, applied to the high-voltage transmission line sag measuring method according to any one of claims 1-4, characterized in that, include: A power transmission tower climbing robot has a sag measuring device installed on its external surface. The sag measuring device includes a first motor, a second motor, a third motor, a camera, a motor control circuit board, and a base. The first motor, the second motor, the third motor, the camera, and the motor control circuit board are all mounted on the base. The motor control circuit board is communicatively connected to the first motor, the second motor, and the third motor, respectively, and is used to control the rotation of the first motor, the second motor, and the third motor according to the spatial attitude of the camera, so that the camera remains parallel to the ground in real time.

6. The method for measuring the sag of a high-voltage transmission line according to claim 5, characterized in that, The camera is equipped with an inertial navigation component to obtain the camera's yaw angle, pitch angle, and Calculate the roll angle and, using the ground as a reference frame, determine the camera's rotation matrix: Where, ψ c θ represents the camera's yaw angle. c φ represents the camera's pitch angle. c R represents the camera's roll angle. c This represents the camera's rotation matrix.

7. A method for measuring the sag of a high-voltage transmission line according to claim 6, characterized in that, An inertial navigation system is installed on the base to obtain the base's yaw, pitch, and roll angles, and to calculate the base's rotation matrix using the ground as a reference frame. Where, ψ b θ represents the yaw angle of the base. b The pitch angle of the base is represented by φ. b R represents the roll angle of the base. b This represents the rotation matrix of the base.

8. A method for measuring the sag of a high-voltage transmission line according to claim 7, characterized in that, Calculate the rotation matrix of the camera relative to the base using the rotation matrix of the camera and the base: make but Where Δθ, Δψ, and Δφ are the rotation angles of the second motor, the third motor, and the first motor, respectively, and r 11 Let matrix R cb The elements in the first row and first column of the matrix are used to introduce a PID algorithm into the motor control circuit board to control the rotation of all motors, so that the camera remains parallel to the ground in real time.

Images