Unmanned aerial vehicle-mounted robot power transmission line flaw detection method and system

Abstract

The invention discloses an unmanned aerial vehicle-mounted robot power transmission line flaw detection method and system, and belongs to the technical field of power transmission line detection, and the method comprises the following steps: an unmanned aerial vehicle collects first image data of a power transmission line through a collection device, and sends the first image data to a robot; preprocessing the first image data, analyzing the preprocessed data, generating an execution signal, and sending the execution signal to the unmanned aerial vehicle; the unmanned aerial vehicle automatically adjusts an acquisition device carried by the unmanned aerial vehicle and performs data acquisition on the marked position; and performing quality analysis on the power transmission line. In the implementation process of the technical scheme of the invention, the preprocessed data is analyzed, the execution signals are generated according to the analysis result, the execution signals are sent to the unmanned aerial vehicle in sequence, and the execution signals comprise the specific three-dimensional point coordinates of the power transmission line and the position information in the route. Therefore, the unmanned aerial vehicle can accurately collect the possible damage position in the subsequent collection process.

Description

Technical Field

[0001] The present application relates to the technical field of power transmission line detection, and specifically to a method and system for power transmission line flaw detection using a robot mounted on an unmanned aerial vehicle. Background Art

[0002] Drone technology, especially its use in industrial applications, has developed rapidly in recent years. Drones are highly maneuverable and flexible and can perform efficient inspection tasks in complex environments. Therefore, they are widely used in flaw detection of transmission lines.

[0003] At present, the technology of using drones for power transmission line inspection has gradually matured, and many power companies and service providers are using drones to improve inspection efficiency, reduce costs and reduce risks. Existing drone inspection solutions usually include drones equipped with high-definition cameras, infrared imaging cameras, laser radar and other sensors to collect image data of power transmission lines and equipment in real time, and then identify line faults, damage or potential risks through manual or automated processing and analysis.

[0004] However, in the application process of the above technologies, although sensors such as high-definition cameras and infrared imaging can provide relatively clear image data, the clarity and stability of the image may be affected at a certain flight altitude or in an unstable flight state. In addition, the accuracy of image recognition is limited by factors such as ambient light, sensor quality, and image processing algorithms, resulting in the collected data being unable to truly reflect the actual situation, and the detection process of the transmission line still needs to be optimized.

[0005] Therefore, it is necessary to provide a UAV-mounted robot transmission line flaw detection method and system to solve the above problems.

[0006] It should be noted that the above information disclosed in this background technology section is only for understanding the background technology of the present application concept, and therefore, it may contain information that does not constitute the prior art. Summary of the invention

[0007] Based on the above-mentioned problems existing in the prior art, the problem to be solved by the present application is: to provide a method and system for flaw detection of power transmission lines by a drone-mounted robot, so as to achieve multiple acquisitions and accurately reach the designated position according to the execution signal in subsequent acquisitions, thereby performing precise acquisition.

[0008] The technical solution adopted by the present application to solve the technical problem is: a method for detecting power line flaws using a robot mounted on an unmanned aerial vehicle, comprising:

[0009] The UAV takes off from a first take-off point and flies to a detection area of ​​the power transmission line according to a predetermined first route. During the flight, the UAV collects first image data of the power transmission line through a collection device, and sends the first image data to the robot through a wireless transmission channel.

[0010] The robot preprocesses the first image data, analyzes the preprocessed data, generates an execution signal according to the analysis result, and sends the execution signal to the drone in sequence;

[0011] The drone automatically adjusts the collection equipment it carries based on the received execution signal to collect data at the marked location;

[0012] Conduct quality analysis on transmission lines and classify them according to the analysis results.

[0013] During the implementation of the technical solution of the present application, the preprocessed data is analyzed, an execution signal is generated according to the analysis results, and the execution signal is sent to the drone in sequence. The execution signal contains the specific three-dimensional point coordinates of the transmission line and the position information in the route, so that the drone can accurately collect the possible damaged locations in the subsequent collection process.

[0014] Furthermore, the drone is equipped with a temporary storage device to temporarily store the collected first image data and clear it after uploading it to the robot.

[0015] Furthermore, the first image data is ordered data, and the order of receiving, sending, and storing each data corresponds to the first route.

[0016] Furthermore, analyzing the preprocessed data further includes:

[0017] Extracting geometric features and texture information of the power transmission line from the preprocessed first image data, and quantifying the extracted geometric features and texture information to establish a feature database;

[0018] Preset a standard image of the power transmission line, quantify the standard image, and compare it with the received first image data to determine whether the power transmission line is damaged;

[0019] Surface features of the power transmission line are extracted from the first image data, and the surface complexity of each power transmission line is calculated based on the extracted surface features, wherein the surface features include point cloud data of the power transmission line.

[0020] Furthermore, the method for calculating the surface complexity of the transmission line includes: obtaining point cloud data of the transmission line, and using fractal geometry methods to calculate the fractal dimension of the transmission line surface, and then combining the calculated fractal dimension of the transmission line surface with other parameters in the surface features for comprehensive calculation to obtain the surface complexity.

[0021] Furthermore, the calculation process of the surface complexity includes: first, obtaining the three-dimensional coordinate information of the surface of the transmission line through point cloud data, and these coordinate information can describe in detail the undulations and concavities of the surface of the transmission line; then, using the box counting method or the sphere counting method, the fractal dimension of the point cloud data of the surface of the transmission line is calculated; then, combining other parameters in the surface characteristics of the transmission line, the fractal dimension is weighted to obtain the surface complexity of the transmission line; generating an execution signal, and sending the execution signal to the execution device, which is a drone.

[0022] Furthermore, the execution signal includes a three-dimensional point coordinate signal sent to the drone, and a route marking signal of the drone, that is, marking a specific position in the route, and performing multiple acquisitions after the drone reaches the position.

[0023] Furthermore, when the surface complexity of the transmission line is high, more computing power is required to identify the damage location. When the surface complexity of the transmission line is low, less computing power is required to identify the damage location and perform parallel analysis.

[0024] A UAV-mounted robot transmission line flaw detection system, comprising:

[0025] A first image data acquisition module is used for the UAV to take off from a first take-off point and fly to a detection area of ​​the power transmission line according to a predetermined first route. During the flight, the UAV collects first image data of the power transmission line through an acquisition device and sends the first image data to the robot through a wireless transmission channel;

[0026] An execution signal generation module is used for the robot to preprocess the first image data, analyze the preprocessed data, generate an execution signal according to the analysis result, and send the execution signal to the drone in sequence;

[0027] The execution signal receiving and collecting module is used for the drone to automatically adjust the collection equipment it carries according to the received execution signal and collect data at the marked position;

[0028] The quality analysis module is used to perform quality analysis on the transmission lines and classify them according to the analysis results.

[0029] The beneficial effects of the present application are as follows: the present application provides a method and system for detecting power transmission lines using a robot mounted on a drone, which analyzes the preprocessed data, generates an execution signal according to the analysis result, and sends the execution signal to the drone in sequence. The execution signal contains the specific three-dimensional point coordinates of the transmission line and the position information in the route, thereby enabling the drone to accurately collect the possible damaged locations in the subsequent collection process.

[0030] In addition to the above-described purposes, features and advantages, the present application also has other purposes, features and advantages. The present application will be further described in detail with reference to the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The drawings in the specification, which constitute a part of the present application, are used to provide further understanding of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute improper limitations on the present application.

[0032] In the attached picture:

[0033] Figure 1 This is a schematic diagram of the overall process of a UAV-mounted robot power transmission line flaw detection method in this application;

[0034] Figure 2 This is a schematic diagram of the module structure of a UAV-mounted robot power transmission line flaw detection system in this application. DETAILED DESCRIPTION

[0035] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0036] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0037] Embodiment 1: Figure 1As shown, the present application provides a method for flaw detection of power transmission lines by a robot mounted on a drone. The method is applied to the flaw detection of power transmission lines, and is based on the method of mounting a robot on a drone. The drone performs the inspection and collection steps, and sends the collected transmission line image data to the robot. The robot analyzes the collected data and resends the execution signal to the drone, thereby completing the entire closed-loop detection process and improving the accuracy of the detection results. The detection method includes the following steps:

[0038] Step 01: The UAV takes off from the first take-off point and flies to the detection area of ​​the power transmission line according to the predetermined first route. During the flight, the UAV collects the first image data of the power transmission line through the acquisition device, and sends the first image data to the robot through the wireless transmission channel;

[0039] In this embodiment, the drone is used as an execution device and is equipped with a collection device. The drone is provided with a first take-off point and a first route corresponding to the first take-off point. After arriving in the detection area, the collection device starts to work and collects the surface image of the transmission line as the first image data. When uploading the data, it can be collected and uploaded in real time to ensure the real-time nature of the first image data. It can also be uploaded to the robot uniformly when the drone reaches the edge of the detection area on the first route. The specific method is not limited in this embodiment.

[0040] The acquisition equipment includes but is not limited to high-precision cameras, infrared sensors, laser radars, etc. When the data upload method is unified upload, the drone needs to be configured with a temporary storage device with a certain capacity to temporarily store the collected first graphic data and clear it after uploading it to the robot. It can be understood that there is a data exchange channel between the drone and the robot, such as a wired or wireless transmission channel. In this embodiment, a wireless transmission channel is taken as an example;

[0041] It should be noted that the first image data is ordered data, and the order of receiving, sending and storing each data corresponds to the first route, so as to facilitate subsequent tracing and positioning;

[0042] Step 02: The robot preprocesses the first image data, analyzes the preprocessed data, generates an execution signal according to the analysis result, and sends the execution signal to the drone in sequence;

[0043] After obtaining the first image data of the transmission line, it is also necessary to preprocess it to eliminate noise and abnormal points in the image data to ensure the accuracy of analysis. The preprocessing process includes image enhancement, filtering and edge detection, etc. For details, reference may be made to the prior art.

[0044] After the preprocessing is completed, the robot analyzes the preprocessed data. The analysis process mainly includes pattern recognition and damage assessment. The potential damage of the transmission line is identified through the image recognition algorithm, and the degree of damage is assessed. The image recognition algorithm can be an algorithm based on machine learning. The machine learning method relies on a large amount of data to train the model and automatically identify damage, such as support vector machine, random forest, K nearest neighbor algorithm, etc. For details, please refer to the existing technology and will not be described in detail in this embodiment.

[0045] In this embodiment, analyzing the preprocessed data further includes the following steps:

[0046] Step 201: extracting geometric features and texture information of the power transmission line from the pre-processed first image data, and quantifying the extracted geometric features and texture information to establish a feature database;

[0047] The image data of the power transmission line will contain geometric features and texture information, which represent the damage of the power transmission line. It is only necessary to analyze the extracted geometric features and texture information to determine whether damage occurs. In this embodiment, the geometric features and texture information are quantified and a database is established. As the image data increases, the image data categories in the database will increase, thereby improving the subsequent recognition and judgment efficiency;

[0048] Specifically, the geometric features and texture information are quantized by using an octree quantization method, the pixel value distribution of the first image data is recursively divided into a plurality of small blocks, each small block represents a pixel value distribution range, and finally the pixel value of the image is converted into a pixel value of a number node and the depth value of the number node, so as to perform three-dimensional mapping of the transmission line and realize efficient feature extraction;

[0049] Step 202: presetting a standard image of the power transmission line, and after quantifying the standard image, comparing it with the received first image data to determine whether the power transmission line is damaged;

[0050] If the standard image does not match the first image data currently collected, it is possible that a certain area in the transmission line is damaged. Through comparison and analysis, the occurrence and extent of the damage can be determined;

[0051] Step 203: extracting surface features of the transmission line from the first image data, and calculating the surface complexity of each transmission line according to the extracted surface features, wherein the surface features include point cloud data of the transmission line;

[0052] By comparing the preset standard image of the transmission line with the received first image data, the existence of damage can be confirmed. However, for the specific location of the damage, it is necessary to further analyze the surface features of the transmission line. The surface features refer to the surface point cloud data of the transmission line. The data can reflect the fractal dimension of the surface of the transmission line, thereby obtaining the surface complexity information of the transmission line. This surface complexity information will affect the judgment of the damage location. For example, when the surface complexity of the transmission line is high, more computing power is required to identify the damage location. When the surface complexity of the transmission line is low, only less computing power is required to identify the damage location, and parallel analysis can also be performed to improve the efficiency of damage identification.

[0053] The calculation method of the surface complexity of the transmission line includes: obtaining point cloud data of the transmission line, and using fractal geometry method to calculate the fractal dimension of the surface of the transmission line, and then combining the calculated fractal dimension of the surface of the transmission line with other parameters in the surface characteristics for comprehensive calculation to obtain the surface complexity;

[0054] The fractal geometry method can be implemented by using the box counting method or the sphere counting method. The specific operating principle can refer to the prior art. Other parameters in the surface features include but are not limited to the average curvature of the transmission line surface, the complexity of the surface texture of the transmission line, the damaged area of ​​the transmission line surface, etc. These parameters can be directly generated by the visual acquisition equipment. Specifically, the calculation process of the surface complexity is as follows:

[0055] Step 02-3-1: First, obtain the three-dimensional coordinate information of the surface of the transmission line through point cloud data. These coordinate information can describe the ups and downs and concavities of the surface of the transmission line in detail;

[0056] Step 02-3-2: Then, the fractal dimension of the point cloud data of the transmission line surface is calculated using the box counting method or the sphere counting method; specifically, the surface of the transmission line is divided into boxes of different sizes or covered with spheres of different radii, and the number of boxes or spheres covering the point cloud data is counted, so as to obtain the fractal dimension of the surface of the transmission line. This step can refer to the prior art, such as the relevant patents containing fractal dimension calculation, which will not be described in detail in this embodiment;

[0057] Step 02-3-3: Then, in combination with other parameters in the surface features of the transmission line, the fractal dimension is weighted to obtain the surface complexity of the transmission line; for example, if the fractal dimension D = 2.8, the average curvature K = 0.02, the texture complexity T = 0.5, and the weights w_1 = 0.7, w_2 = 0.2, w_3 = 0.1, where w_1 is the weight of the fractal dimension, w_2 is the dimension of the average curvature, and w_3 is the dimension of the texture complexity, then the surface complexity of the transmission line = 2.8 × 0.7 + 0.02 × 0.2 + 0.5 × 0.1 = 2.014, which is the surface complexity of the transmission line. When selecting the weight, it can be specified according to the actual situation. For example, a transmission line with a larger fractal dimension may require more detailed processing, so a higher weight is given when calculating the complexity;

[0058] Step 02-4: Generate an execution signal and send it to the execution device, which is a drone. The execution signal includes a three-dimensional point coordinate signal sent to the drone and a route marking signal of the drone, that is, marking a specific location in the route, and performing multiple acquisitions after the drone reaches the location;

[0059] Step 03: The drone automatically adjusts its onboard collection equipment based on the received execution signal to collect data at the marked location;

[0060] After receiving the execution signal, the drone starts to collect data repeatedly and re-collects part of the area from the first take-off point along the first route. Since the execution signal contains specific three-dimensional point coordinates, route marking signals, etc., the drone can collect data repeatedly and collect images of locations where damage may occur for subsequent analysis.

[0061] Step 04: Analyze the quality of the transmission lines and classify them according to the analysis results.

[0062] After re-collection, the quality analysis of the transmission line is carried out through the collected image data to determine the degree and type of damage to the transmission line. Specifically, an automated algorithm can be used to determine the degree and type of damage to the transmission line. The algorithm can evaluate the health status of the transmission line based on historical data and real-time collected information. In this way, various types of damage can be discovered and classified in a timely manner, providing accurate guidance for maintenance work.

[0063] Embodiment 2: Figure 2 As shown, the present application also proposes a UAV-mounted robot transmission line flaw detection system, which runs the detection method in Example 1, and the system includes:

[0064] A first image data acquisition module is used for the UAV to take off from a first take-off point and fly to a detection area of ​​the power transmission line according to a predetermined first route. During the flight, the UAV collects first image data of the power transmission line through an acquisition device and sends the first image data to the robot through a wireless transmission channel;

[0065] An execution signal generation module is used for the robot to preprocess the first image data, analyze the preprocessed data, generate an execution signal according to the analysis result, and send the execution signal to the drone in sequence;

[0066] The execution signal receiving and collecting module is used for the drone to automatically adjust the collection equipment it carries according to the received execution signal and collect data at the marked position;

[0067] The quality analysis module is used to perform quality analysis on the transmission lines and classify them according to the analysis results.

[0068] Through the above steps, the UAV-mounted robot transmission line flaw detection method and system provided in this application can effectively improve the accuracy and efficiency of inspections, while reducing the risk of misjudgment due to environmental factors and sensor limitations.

[0069] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for detecting power line flaws using a robot mounted on an unmanned aerial vehicle, characterized in that: include: The UAV takes off from a first take-off point and flies to a detection area of ​​the power transmission line according to a predetermined first route. During the flight, the UAV collects first image data of the power transmission line through a collection device, and sends the first image data to the robot through a wireless transmission channel. The robot preprocesses the first image data, analyzes the preprocessed data, generates an execution signal according to the analysis result, and sends the execution signal to the drone in sequence; The drone automatically adjusts the collection equipment it carries based on the received execution signal to collect data at the marked location; Conduct quality analysis on transmission lines and classify them according to the analysis results.

2. The method for detecting power line flaws using a robot mounted on an unmanned aerial vehicle according to claim 1, characterized in that: The drone is equipped with a temporary storage device to temporarily store the collected first image data and clear it after uploading it to the robot.

3. The method for detecting power line flaws using a robot mounted on an unmanned aerial vehicle according to claim 1, characterized in that: The first image data is ordered data, and the order of receiving, sending, and storing each data corresponds to the first route.

4. The method for detecting power line flaws using a robot mounted on an unmanned aerial vehicle according to claim 1, characterized in that: The analysis of the preprocessed data further includes: Extracting geometric features and texture information of the power transmission line from the preprocessed first image data, and quantifying the extracted geometric features and texture information to establish a feature database; Preset a standard image of the power transmission line, quantify the standard image, and compare it with the received first image data to determine whether the power transmission line is damaged; Surface features of the power transmission line are extracted from the first image data, and the surface complexity of each power transmission line is calculated based on the extracted surface features, wherein the surface features include point cloud data of the power transmission line.

5. The method for detecting power line flaws using a robot mounted on an unmanned aerial vehicle according to claim 4, characterized in that: The calculation method of the surface complexity of the transmission line includes: obtaining point cloud data of the transmission line, and using fractal geometry method to calculate the fractal dimension of the transmission line surface, and then combining the calculated fractal dimension of the transmission line surface with other parameters in the surface characteristics for comprehensive calculation to obtain the surface complexity.

6. The method for detecting power line flaws using a robot mounted on an unmanned aerial vehicle according to claim 4, characterized in that: The calculation process of surface complexity includes: first, obtaining the three-dimensional coordinate information of the transmission line surface through point cloud data, and these coordinate information can describe the undulations and bumps of the transmission line surface in detail; then, using the box counting method or the sphere counting method to calculate the fractal dimension of the point cloud data of the transmission line surface; then, combining other parameters in the surface characteristics of the transmission line, weighting the fractal dimension to obtain the surface complexity of the transmission line; generating an execution signal, and sending the execution signal to the execution device, which is a drone.

7. The method for detecting power line flaws using a robot mounted on an unmanned aerial vehicle according to claim 6, characterized in that: The execution signal includes the three-dimensional point coordinate signal sent to the drone, and the route marking signal of the drone, that is, marking the specific position in the route and performing multiple acquisitions after the drone reaches the position.

8. The method for detecting power line flaws using a robot mounted on an unmanned aerial vehicle according to claim 6, characterized in that: When the surface complexity of the transmission line is high, more computing power is required to identify the damage location. When the surface complexity of the transmission line is low, less computing power is required to identify the damage location and perform parallel analysis.

9. A UAV-mounted robot transmission line flaw detection system, characterized in that: include: A first image data acquisition module is used for the UAV to take off from a first take-off point and fly to a detection area of ​​the power transmission line according to a predetermined first route. During the flight, the UAV collects first image data of the power transmission line through an acquisition device and sends the first image data to the robot through a wireless transmission channel; An execution signal generation module is used for the robot to preprocess the first image data, analyze the preprocessed data, generate an execution signal according to the analysis result, and send the execution signal to the drone in sequence; The execution signal receiving and collecting module is used for the drone to automatically adjust the collection equipment it carries according to the received execution signal and collect data at the marked position; The quality analysis module is used to perform quality analysis on the transmission lines and classify them according to the analysis results.

10. The UAV-mounted robot power transmission line flaw detection system according to claim 9, characterized in that: Used to implement the UAV-mounted robot power transmission line flaw detection method as described in any one of claims 1 to 8.

Images