An obstacle avoidance method and system for a power inspection robot

Abstract

This invention discloses an obstacle avoidance method and system for a power inspection robot. The invention relates to the field of obstacle avoidance technology for power inspection robots, and includes an ice condition acquisition module, an icing prediction and processing module, an icing risk assessment module, and an obstacle avoidance execution module. The ice condition acquisition module is used to acquire icing data of the obstacle avoidance environment. The icing prediction and processing module is divided into an icing data processing unit, an icing feature extraction unit, and an icing model construction unit. The icing data processing unit is used to convert echo time into ice layer thickness data and convert 3D point cloud data of the ice cone surface into a 3D model of the ice cone. The icing feature extraction unit is used to extract ice cone length data. The icing model construction unit is used to obtain obstacle avoidance results corresponding to different ice layers and ice cones, and construct ice layer obstacle avoidance models and ice cone obstacle avoidance models. The icing risk assessment module analyzes the ice layer thickness data and ice cone length data. The obstacle avoidance execution module receives the analysis results and executes corresponding operations.

Description

Technical Field

[0001] This invention relates to the field of obstacle avoidance technology for power inspection robots, specifically to an obstacle avoidance method and system for power inspection robots. Background Technology

[0002] The background technology of obstacle avoidance methods and systems for power system inspection robots stems from the increasing demand for power system inspection and the rapid development of robotics technology. With the large-scale commissioning of power facilities, the workload of inspections has increased dramatically. Traditional manual inspection methods can no longer meet the demands for efficiency and safety. Therefore, power system inspection robots have emerged to replace manual labor in completing inspection tasks. In terms of obstacle avoidance, robotics technology provides various methods, such as sensor fusion-based obstacle avoidance, AI-based obstacle avoidance, and map-based obstacle avoidance. These methods utilize information from multiple sensors, including LiDAR, ultrasonic sensors, and infrared sensors, combined with AI technologies such as deep learning and fuzzy logic control. This enables the robot to perceive its surrounding environment in real time, accurately identify obstacles, and autonomously plan inspection paths, achieving efficient and safe inspections. With continuous technological advancements, the obstacle avoidance methods and systems of power system inspection robots will become more intelligent and autonomous, providing a more reliable guarantee for the safe and stable operation of the power system.

[0003] Although significant progress has been made in obstacle avoidance methods and systems for existing power line inspection robots, some issues still need optimization. In winter, when power line inspection robots are working, large icicles and thick ice layers in some areas occupy most of the space along the power lines, making it impossible for the robots to avoid obstacles by bypassing them. Furthermore, the icing conditions vary between different sections of the power lines, and the robots cannot take corresponding obstacle avoidance measures based on the icing conditions, which affects their working performance. Summary of the Invention

[0004] To achieve the above objectives, the present invention is implemented through the following technical solution: an obstacle avoidance system for a power inspection robot, comprising an ice condition acquisition module, an icing prediction and processing module, an icing risk assessment module, and an obstacle avoidance execution module;

[0005] The ice condition acquisition module is used to acquire data on icing obstacles in the power inspection environment;

[0006] The icing prediction and processing module is divided into an icing data processing unit, an icing feature extraction unit, and an icing model construction unit. The icing data processing unit is used to convert echo time into ice thickness data and convert the 3D point cloud data of the ice cone surface into a 3D ice cone model. The icing feature extraction unit is used to extract ice cone length data from the 3D ice cone model. The icing model construction unit is used to construct ice layer obstacle avoidance models and ice cone obstacle avoidance models to obtain obstacle avoidance results corresponding to different ice layer data and ice cone data.

[0007] The icing risk assessment module analyzes ice thickness data and icicle length data to assess the risks of robot operation and transmits the analysis results to the obstacle avoidance execution module.

[0008] The obstacle avoidance module receives the assessment results of the inspection robot's operational risks and performs corresponding operations to avoid obstacles.

[0009] Furthermore, the obstacle avoidance environment icing data refers to the ice layer data and icicle data of the area where the power inspection robot moves, and the acquisition process includes:

[0010] A1. Equip the power inspection robot with an icing detector and a 3D scanner, with both the icing detector and the 3D scanner installed at the front end of the power inspection robot.

[0011] A2. Send high-frequency electromagnetic waves to the target ice layer in real time through an icing detector, receive the reflected signal, and record its echo time;

[0012] A3. Adjust the 3D scanner to the appropriate scanning parameters for the size of the ice cone. The 3D scanner projects a laser beam onto the surface of the ice cone and captures the reflected light signal. After multiple scans, the 3D point cloud data of the ice cone surface is obtained.

[0013] Furthermore, the icing data processing unit converts the echo time into ice thickness data through calculation, and uses the Delaunay triangulation algorithm to convert the three-dimensional point cloud data of the ice cone surface into a three-dimensional model of the ice cone. The specific process includes:

[0014] B1. The formula for calculating the ice thickness data converted from the echo signal is as follows:

[0015] D = ct / 2

[0016] Where D is the ice thickness, c is the propagation speed of electromagnetic waves in the ice, and t is the echo time;

[0017] B2. Preprocess the 3D point cloud data of the ice cone surface. Use the preprocessed point cloud data as input and construct a mesh model composed of triangles using the Delaunay triangulation algorithm. Connect adjacent points according to the definition of Delaunay edges to form a 3D model of the ice cone.

[0018] Furthermore, the process of extracting ice cone length data from the 3D model of the ice cone in the ice feature extraction unit includes:

[0019] The 3D model of the ice cone is imported into Blender modeling software. The viewpoint and position are adjusted in the Blender 3D view to obtain the tip and base of the ice cone. Based on the geometric principles of 3D space, the length of the ice cone is calculated using the following formula:

[0020]

[0021] Where L is the length of the ice cone, the coordinates of the tip of the ice cone are M(x1,y1,z1), and the coordinates of the bottom of the ice cone are N(x2,y2,z2).

[0022] Furthermore, the process by which the icing model construction unit obtains obstacle avoidance results corresponding to different ice layer data and different ice cone data includes:

[0023] C1. Clean and organize the collected ice thickness and ice cone length data;

[0024] C2. For ice thickness, preset ice thickness thresholds are set as follows: a first threshold of 15mm and a second threshold of 100mm. The preprocessed ice thickness data is input into a clustering algorithm with a cluster size of 3. The clustering algorithm divides the ice thickness data into different clusters based on the similarity of the ice thickness data. According to the preset ice thickness thresholds, the ice thickness data of each cluster is judged. When the ice thickness is less than 15mm, it belongs to the first cluster; when the ice thickness is between 15mm and 100mm, it belongs to the second cluster; and when the ice thickness is greater than 100mm, it belongs to the third cluster. The generated clusters are divided into three clustering results: no impact on obstacle avoidance, obstacle avoidance effect is affected, and obstacle avoidance is impossible. The clustering result is output to obtain the obstacle avoidance results corresponding to different ice layers.

[0025] C3. For ice cone length, set ice cone length thresholds: a first threshold of 5cm and a second threshold of 15cm. Input the preprocessed ice cone length data into the clustering algorithm, setting the number of clusters to 3. The clustering algorithm divides the ice cone length data into different clusters based on the similarity of the ice cone length data. According to the preset thresholds, the ice cone data of each cluster is judged: when the ice cone length is less than 2cm, it belongs to the first cluster; when the ice cone length is between 5 and 15cm, it belongs to the second cluster; when the ice cone length is greater than 15cm, it belongs to the third cluster. The generated clusters are divided into three clustering results: no impact on obstacle avoidance, obstacle avoidance effect affected, and no obstacle avoidance. Output the clustering results to obtain the obstacle avoidance results corresponding to different ice cones.

[0026] Furthermore, the process of constructing an ice layer obstacle avoidance model by the ice model construction unit includes:

[0027] The ice thickness data and obstacle avoidance results were standardized using the ID3 decision tree format. The decision tree was initialized, and the processed ice thickness data and obstacle avoidance results were used as the dataset. The dataset was divided into a training set and a validation set. In the training set, ice thickness features at the root node were defined based on a first and second ice thickness threshold, and corresponding leaf nodes were created. The obstacle avoidance result was recorded at each leaf node. When the input value to the root node was lower than the first ice thickness threshold, the leaf node output a result indicating an obstacle avoidance difficulty of 0%; when the input value was between the first and second ice thickness thresholds, the leaf node output a result indicating an obstacle avoidance difficulty of 50%; and when the input value was higher than the second ice thickness threshold, the leaf node output a result indicating an obstacle avoidance difficulty of 100%. A preliminary ID3 decision tree model was constructed. The model was then validated using the validation set. Thresholds and model parameters were adjusted to optimize the ID3 decision tree model, resulting in the final ice obstacle avoidance model.

[0028] Furthermore, the process of constructing the ice cone obstacle avoidance model by the ice model construction unit includes:

[0029] The ice cone length data and obstacle avoidance results were standardized using the ID3 decision tree format. The decision tree was initialized, and the processed ice cone length data and obstacle avoidance results were used as the dataset. The dataset was divided into a training set and a validation set. In the training set, ice cone length features at the root node were defined based on a first and a second ice cone length threshold, and corresponding leaf nodes were created. The obstacle avoidance result was recorded at each leaf node. When the ice cone length value corresponding to the root node was lower than the first ice cone length threshold, the leaf node output a result indicating an obstacle avoidance difficulty of 0%; when the ice cone length value was between the first and second ice cone length thresholds, the leaf node output a result indicating an obstacle avoidance difficulty of 50%; and when the ice cone length value was higher than the second ice cone length threshold, the leaf node output a result indicating an obstacle avoidance difficulty of 100%. A preliminary ID3 decision tree model was constructed. The constructed ID3 decision tree model was then validated using the validation set. The thresholds and model parameters were adjusted to optimize the ID3 decision tree model, resulting in the ice cone obstacle avoidance model.

[0030] Furthermore, the icing risk assessment module analyzes ice thickness data and ice cone length data, including the following processes:

[0031] S1. Analyze the collected ice thickness data and input it into the ice obstacle avoidance model. When the input value is lower than the first ice thickness threshold, the obstacle avoidance difficulty is 0%; when the input value is between the first ice thickness threshold and the second ice thickness threshold, the obstacle avoidance difficulty is 50%; when the input value is higher than the second ice thickness threshold, the obstacle avoidance difficulty is 100%.

[0032] S2. Analyze the collected ice cone length data and input it into the ice cone obstacle avoidance model. When the input value is lower than the first ice cone length threshold, the obstacle avoidance difficulty is 0%; when the input value is between the first ice cone length threshold and the second ice cone length threshold, the obstacle avoidance difficulty is 50%; when the input value is higher than the second ice cone length threshold, the obstacle avoidance difficulty is 100%.

[0033] S3. Wirelessly transmit the obstacle avoidance difficulty percentage result to the obstacle avoidance execution module.

[0034] Furthermore, the obstacle avoidance execution module, in its process of receiving analysis results and performing corresponding operations, includes:

[0035] When the obstacle avoidance difficulty is received as 0%, it has no effect on the inspection robot's obstacle avoidance; when the obstacle avoidance difficulty is received as 50%, an instruction is issued to activate the mechanical vibration de-icing device of the inspection robot; when the obstacle avoidance difficulty is received as 100%, an instruction is issued to stop the inspection robot from moving forward, change the inspection route, and issue an alarm to the staff for handling.

[0036] Furthermore, an obstacle avoidance method for a power line inspection robot, implemented based on the aforementioned obstacle avoidance system for the power line inspection robot, is characterized by comprising the following steps:

[0037] Step 1: Use an ice detector to emit electromagnetic waves to the ice layer, collect the echo time, and collect the three-dimensional point cloud data of the ice cone using a three-dimensional scanner.

[0038] Step 2: Convert the echo time into ice thickness data through calculation, use the Delaunay triangulation algorithm to convert the three-dimensional point cloud data of the ice cone surface into a three-dimensional model of the ice cone, and then use Blender modeling software to extract the ice cone length data from the three-dimensional model of the ice cone.

[0039] Step 3: Set thresholds for ice thickness data and ice cone length data, and output obstacle avoidance results corresponding to different ice thickness data and different ice cone length data through clustering algorithms;

[0040] Step 4: Construct ice layer obstacle avoidance model and ice cone obstacle avoidance model using ID3 decision tree algorithm;

[0041] Step 5: Analyze real-time ice thickness data and ice cone length data, and transmit the analysis results to the obstacle avoidance execution module;

[0042] Step Six: Receive the analysis results. When the obstacle avoidance difficulty is 0%, it has no impact on the obstacle avoidance of the inspection robot. When the obstacle avoidance difficulty is 50%, an instruction is issued to activate the mechanical vibration de-icing device of the inspection robot. When the obstacle avoidance difficulty is 100%, an instruction is issued to stop the inspection robot from moving forward, change the inspection route, and issue an alarm to the staff for handling.

[0043] The beneficial effects of this invention are as follows: The obstacle avoidance method and system for the power inspection robot, through the close integration of three-dimensional data acquisition technology, three-dimensional modeling technology, feature extraction technology, clustering algorithm analysis technology, model construction technology and modern information technology in the system described in this invention, integrates icing detection technology and three-dimensional scanning technology, accurately captures the ice layer data and icicle data that the inspection robot needs to avoid, and achieves real-time and comprehensive monitoring of the centralized monitoring system of the inspection robot through the ID3 decision tree algorithm. By using the ice layer thickness data, icicle length data, ice layer obstacle avoidance model and icicle obstacle avoidance model obtained after data processing, the obstacle avoidance difficulty prediction of the inspection robot when working in an icy environment is analyzed in real time, and anomalies are monitored in real time. This invention addresses the challenges of timely response to system anomalies during operation. Specifically, it resolves issues encountered by power line inspection robots in winter, such as large, thick icicles obstructing significant space on power lines and hindering obstacle avoidance. Furthermore, the varying icing conditions across different power line sections prevent the robots from adopting appropriate obstacle avoidance strategies, thus impacting their performance. This invention ensures that the method can refine the dynamic monitoring standards for the obstacle avoidance system of power line inspection robots within a more precise range, making the monitored data more accurate under the same conditions. The development and application of this method significantly enhances the intelligence of inspection robots during obstacle avoidance. Attached Figure Description

[0044] Figure 1 This is a block diagram of an obstacle avoidance system for a power inspection robot according to the present invention;

[0045] Figure 2 This is a flowchart of an obstacle avoidance method for a power inspection robot according to the present invention. Detailed Implementation

[0046] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0047] like Figure 1 and Figure 2As shown, the present invention provides a technical solution: an obstacle avoidance system for a power inspection robot, including an ice condition acquisition module, an icing prediction and processing module, an icing risk assessment module, and an obstacle avoidance execution module;

[0048] The ice condition acquisition module is used to acquire data on icing obstacles in the power line inspection environment.

[0049] The icing prediction and processing module is divided into an icing data processing unit, an icing feature extraction unit, and an icing model construction unit. The icing data processing unit is used to convert echo time into ice thickness data and convert the 3D point cloud data of the ice cone surface into a 3D ice cone model. The icing feature extraction unit is used to extract ice cone length data from the 3D ice cone model. The icing model construction unit is used to construct ice layer obstacle avoidance models and ice cone obstacle avoidance models to obtain obstacle avoidance results corresponding to different ice layer data and ice cone data.

[0050] The icing risk assessment module analyzes ice thickness and icicle length data to assess the risks of robot operation and transmits the analysis results to the obstacle avoidance execution module.

[0051] The obstacle avoidance module receives the assessment results of the inspection robot's operational risks and executes corresponding operations to avoid obstacles.

[0052] The obstacle avoidance environment icing data consists of ice layer and icicle data in the area where the power inspection robot moves. The acquisition process includes:

[0053] A1. Equip the power inspection robot with an icing detector and a 3D scanner, with both the icing detector and the 3D scanner installed at the front end of the power inspection robot.

[0054] A2. Send high-frequency electromagnetic waves to the target ice layer in real time through an icing detector, receive the reflected signal, and record its echo time;

[0055] A3. Adjust the 3D scanner to the appropriate scanning parameters for the size of the ice cone. The 3D scanner projects a laser beam onto the surface of the ice cone and captures the reflected light signal. After multiple scans, the 3D point cloud data of the ice cone surface is obtained.

[0056] The icing data processing unit converts echo time into ice thickness data through calculation, and uses the Delaunay triangulation algorithm to convert the 3D point cloud data of the ice cone surface into a 3D model of the ice cone. The specific process includes:

[0057] B1. The formula for calculating the ice thickness data converted from the echo signal is as follows:

[0058] D = ct / 2

[0059] Where D is the ice thickness, c is the propagation speed of electromagnetic waves in the ice, and t is the echo time;

[0060] B2. Preprocess the 3D point cloud data of the ice cone surface. Use the preprocessed point cloud data as input and construct a mesh model composed of triangles using the Delaunay triangulation algorithm. Connect adjacent points according to the definition of Delaunay edges to form a 3D model of the ice cone.

[0061] In the icing feature extraction unit, the process of extracting ice cone length data from the 3D model of the ice cone includes:

[0062] The 3D model of the ice cone is imported into Blender modeling software. The viewpoint and position are adjusted in the Blender 3D view to obtain the tip and base of the ice cone. Based on the geometric principles of 3D space, the length of the ice cone is calculated using the following formula:

[0063]

[0064] Where L is the length of the ice cone, the coordinates of the tip of the ice cone are M(x1,y1,z1), and the coordinates of the bottom of the ice cone are N(x2,y2,z2).

[0065] The process of constructing an icing model unit to obtain obstacle avoidance results corresponding to different ice layer data and different ice cone data includes:

[0066] C1. Clean and organize the collected ice thickness and ice cone length data;

[0067] C2. For ice thickness, preset ice thickness thresholds are set as follows: a first threshold of 15mm and a second threshold of 100mm. The preprocessed ice thickness data is input into a clustering algorithm with a cluster size of 3. The clustering algorithm divides the ice thickness data into different clusters based on the similarity of the ice thickness data. According to the preset ice thickness thresholds, the ice thickness data of each cluster is judged. When the ice thickness is less than 15mm, it belongs to the first cluster; when the ice thickness is between 15mm and 100mm, it belongs to the second cluster; and when the ice thickness is greater than 100mm, it belongs to the third cluster. The generated clusters are divided into three clustering results: no impact on obstacle avoidance, obstacle avoidance effect is affected, and obstacle avoidance is impossible. The clustering result is output to obtain the obstacle avoidance results corresponding to different ice layers.

[0068] C3. For ice cone length, set ice cone length thresholds: a first threshold of 5cm and a second threshold of 15cm. Input the preprocessed ice cone length data into the clustering algorithm, setting the number of clusters to 3. The clustering algorithm divides the ice cone length data into different clusters based on the similarity of the ice cone length data. According to the preset thresholds, the ice cone data of each cluster is judged: when the ice cone length is less than 2cm, it belongs to the first cluster; when the ice cone length is between 5 and 15cm, it belongs to the second cluster; when the ice cone length is greater than 15cm, it belongs to the third cluster. The generated clusters are divided into three clustering results: no impact on obstacle avoidance, obstacle avoidance effect affected, and no obstacle avoidance. Output the clustering results to obtain the obstacle avoidance results corresponding to different ice cones.

[0069] The process of building an ice layer obstacle avoidance model using the ice model building unit includes:

[0070] The ice thickness data and obstacle avoidance results were standardized using the ID3 decision tree format. The decision tree was initialized, and the processed ice thickness data and obstacle avoidance results were used as the dataset. The dataset was divided into a training set and a validation set. In the training set, ice thickness features at the root node were defined based on a first and second ice thickness threshold, and corresponding leaf nodes were created. The obstacle avoidance result was recorded at each leaf node. When the input value to the root node was lower than the first ice thickness threshold, the leaf node output a result indicating an obstacle avoidance difficulty of 0%; when the input value was between the first and second ice thickness thresholds, the leaf node output a result indicating an obstacle avoidance difficulty of 50%; and when the input value was higher than the second ice thickness threshold, the leaf node output a result indicating an obstacle avoidance difficulty of 100%. A preliminary ID3 decision tree model was constructed. The model was then validated using the validation set. Thresholds and model parameters were adjusted to optimize the ID3 decision tree model, resulting in the final ice obstacle avoidance model.

[0071] The process of constructing an ice cone obstacle avoidance model using the icing model building unit includes:

[0072] The ice cone length data and obstacle avoidance results were standardized using the ID3 decision tree format. The decision tree was initialized, and the processed ice cone length data and obstacle avoidance results were used as the dataset. The dataset was divided into a training set and a validation set. In the training set, ice cone length features at the root node were defined based on a first and a second ice cone length threshold, and corresponding leaf nodes were created. The obstacle avoidance result was recorded at each leaf node. When the ice cone length value corresponding to the root node was lower than the first ice cone length threshold, the leaf node output a result indicating an obstacle avoidance difficulty of 0%; when the ice cone length value was between the first and second ice cone length thresholds, the leaf node output a result indicating an obstacle avoidance difficulty of 50%; and when the ice cone length value was higher than the second ice cone length threshold, the leaf node output a result indicating an obstacle avoidance difficulty of 100%. A preliminary ID3 decision tree model was constructed. The constructed ID3 decision tree model was then validated using the validation set. The thresholds and model parameters were adjusted to optimize the ID3 decision tree model, resulting in the ice cone obstacle avoidance model.

[0073] The icing risk assessment module analyzes ice thickness and ice cone length data, including the following processes:

[0074] S1. Analyze the collected ice thickness data and input it into the ice obstacle avoidance model. When the input value is lower than the first ice thickness threshold, the obstacle avoidance difficulty is 0%; when the input value is between the first ice thickness threshold and the second ice thickness threshold, the obstacle avoidance difficulty is 50%; when the input value is higher than the second ice thickness threshold, the obstacle avoidance difficulty is 100%.

[0075] S2. Analyze the collected ice cone length data and input it into the ice cone obstacle avoidance model. When the input value is lower than the first ice cone length threshold, the obstacle avoidance difficulty is 0%; when the input value is between the first ice cone length threshold and the second ice cone length threshold, the obstacle avoidance difficulty is 50%; when the input value is higher than the second ice cone length threshold, the obstacle avoidance difficulty is 100%.

[0076] S3. Wirelessly transmit the obstacle avoidance difficulty percentage result to the obstacle avoidance execution module.

[0077] The obstacle avoidance execution module receives analysis results and performs corresponding operations, including the following process:

[0078] When the obstacle avoidance difficulty is received as 0%, it has no effect on the inspection robot's obstacle avoidance; when the obstacle avoidance difficulty is received as 50%, an instruction is issued to activate the mechanical vibration de-icing device of the inspection robot; when the obstacle avoidance difficulty is received as 100%, an instruction is issued to stop the inspection robot from moving forward, change the inspection route, and issue an alarm to the staff for handling.

[0079] An obstacle avoidance method for a power line inspection robot, based on the aforementioned obstacle avoidance system for the power line inspection robot, comprises the following steps:

[0080] Step 1: Use an ice detector to emit electromagnetic waves to the ice layer, collect the echo time, and collect the three-dimensional point cloud data of the ice cone using a three-dimensional scanner.

[0081] Step 2: Convert the echo time into ice thickness data through calculation, use the Delaunay triangulation algorithm to convert the three-dimensional point cloud data of the ice cone surface into a three-dimensional model of the ice cone, and then use Blender modeling software to extract the ice cone length data from the three-dimensional model of the ice cone.

[0082] Step 3: Set thresholds for ice thickness data and ice cone length data, and output obstacle avoidance results corresponding to different ice thickness data and different ice cone length data through clustering algorithms;

[0083] Step 4: Construct ice layer obstacle avoidance model and ice cone obstacle avoidance model using ID3 decision tree algorithm;

[0084] Step 5: Analyze real-time ice thickness data and ice cone length data, and transmit the analysis results to the obstacle avoidance execution module;

[0085] Step Six: Receive the analysis results. When the obstacle avoidance difficulty is 0%, it has no impact on the obstacle avoidance of the inspection robot. When the obstacle avoidance difficulty is 50%, an instruction is issued to activate the mechanical vibration de-icing device of the inspection robot. When the obstacle avoidance difficulty is 100%, an instruction is issued to stop the inspection robot from moving forward, change the inspection route, and issue an alarm to the staff for handling.

[0086] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, the phrase "comprising an element defined as..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An obstacle avoidance system for a power line inspection robot, comprising an ice condition acquisition module, an icing prediction and processing module, an icing risk assessment module, and an obstacle avoidance execution module, characterized in that: The ice condition acquisition module is used to acquire data on icing obstacles in the power inspection environment; The icing prediction and processing module is divided into an icing data processing unit, an icing feature extraction unit, and an icing model construction unit. The icing data processing unit converts echo time into ice thickness data and converts 3D point cloud data of the ice cone surface into a 3D ice cone model. The icing feature extraction unit extracts ice cone length data from the 3D ice cone model. The icing model construction unit constructs ice layer obstacle avoidance models and ice cone obstacle avoidance models to obtain obstacle avoidance results corresponding to different ice layer data and different ice cone data, specifically including: C1. Clean and organize the collected ice thickness and ice cone length data; C2. For ice layer thickness, preset ice layer thickness thresholds are set as the first ice layer thickness threshold and the second ice layer thickness threshold. The preprocessed ice layer thickness data is input into the clustering algorithm, and the number of clusters is set to 3. The clustering algorithm divides the ice layer thickness data into different clusters based on the similarity of the ice layer data. According to the preset ice layer thickness threshold, the ice layer thickness data of each cluster is judged and divided into three clustering results: no impact on obstacle avoidance, obstacle avoidance effect is affected, and obstacle avoidance is not possible. The clustering result is output to obtain the obstacle avoidance results corresponding to different ice layers. C3. For ice cone length, preset ice cone length thresholds are set as the first ice cone length threshold and the second ice cone length threshold. The preprocessed ice cone length data is input into the clustering algorithm, and the number of clusters is set to 3. The clustering algorithm divides the ice cone length data into different clusters based on the similarity of ice cone lengths. According to the preset threshold, the ice cone data of each cluster is judged and divided into three clustering results: no impact on obstacle avoidance, obstacle avoidance effect is affected, and obstacle avoidance is impossible. The clustering result is output to obtain the obstacle avoidance results corresponding to different ice cones. The icing risk assessment module analyzes ice thickness data and icicle length data to assess the risks of robot operation and transmits the analysis results to the obstacle avoidance execution module. The obstacle avoidance module receives the assessment results of the inspection robot's operational risks and performs corresponding operations to avoid obstacles.

2. The obstacle avoidance system for a power inspection robot according to claim 1, characterized in that: The data on icing obstacles in the power line inspection environment consists of ice layer data and icicle data in the area where the power line inspection robot moves. The acquisition process includes: A1. Equip the power inspection robot with an icing detector and a 3D scanner, with both the icing detector and the 3D scanner installed at the front end of the power inspection robot. A2. Send high-frequency electromagnetic waves to the target ice layer in real time through an icing detector, receive the reflected signal, and record its echo time; A3. Adjust the 3D scanner to the appropriate scanning parameters for the size of the ice cone. The 3D scanner projects a laser beam onto the surface of the ice cone and captures the reflected light signal. After multiple scans, the 3D point cloud data of the ice cone surface is obtained.

3. The obstacle avoidance system for a power inspection robot according to claim 2, characterized in that: The icing data processing unit converts echo time into ice thickness data through calculation, and uses the Delaunay triangulation algorithm to convert the three-dimensional point cloud data of the ice cone surface into a three-dimensional model of the ice cone. The specific process includes: B1. The formula for calculating the ice thickness data converted from the echo signal is as follows: D = ct / 2 Where D is the ice thickness, c is the propagation speed of electromagnetic waves in the ice, and t is the echo time; B2. Preprocess the 3D point cloud data of the ice cone surface. Use the preprocessed point cloud data as input and construct a mesh model composed of triangles using the Delaunay triangulation algorithm. Connect adjacent points according to the definition of Delaunay edges to form a 3D model of the ice cone.

4. The obstacle avoidance system for a power inspection robot according to claim 3, characterized in that: The process of extracting ice cone length data from the 3D model of the ice cone in the ice feature extraction unit includes: The 3D model of the ice cone is imported into Blender modeling software. The viewpoint and position are adjusted in the Blender 3D view to obtain the tip and base of the ice cone. Based on the geometric principles of 3D space, the length of the ice cone is calculated using the following formula: Where L is the length of the ice cone, the coordinates of the tip of the ice cone are M(x1,y1,z1), and the coordinates of the bottom of the ice cone are N(x2,y2,z2).

5. The obstacle avoidance system for a power inspection robot according to claim 4, characterized in that: The process of constructing an ice layer obstacle avoidance model by the ice model construction unit includes: The ice thickness data and obstacle avoidance results were standardized using the ID3 decision tree format. The decision tree was initialized, and the processed ice thickness data and obstacle avoidance results were used as the dataset. The dataset was divided into a training set and a validation set. In the training set, ice thickness features at the root node were defined based on a first and a second ice thickness threshold, and corresponding leaf nodes were created. The obstacle avoidance result was recorded at each leaf node. When the value corresponding to the input root node was lower than the first ice thickness threshold, the leaf node output a result indicating an obstacle avoidance difficulty of 0%; when the value was between the first and second ice thickness thresholds, the leaf node output a result indicating an obstacle avoidance difficulty of 50%; and when the value was higher than the second ice thickness threshold, the leaf node output a result indicating an obstacle avoidance difficulty of 100%. A preliminary ID3 decision tree model was constructed. The constructed ID3 decision tree model was then validated using the validation set. The thresholds and model parameters were adjusted to optimize the ID3 decision tree model, resulting in the final ice obstacle avoidance model.

6. The obstacle avoidance system for a power inspection robot according to claim 5, characterized in that: The process of constructing the ice cone obstacle avoidance model by the ice model construction unit includes: The ice cone length data and its obstacle avoidance results are standardized using the ID3 decision tree format. The decision tree is initialized, and the processed ice cone length data and its obstacle avoidance results are used as the dataset. The dataset is divided into a training set and a validation set. In the training set, ice cone length features at the root node are defined based on a first and a second ice cone length threshold, and corresponding leaf nodes are created. The obstacle avoidance result is recorded at each leaf node. When the ice cone length value corresponding to the input root node is lower than the first ice cone length threshold, the leaf node outputs an obstacle avoidance difficulty of 0%; when the ice cone length value is between the first and second ice cone length thresholds, the leaf node outputs an obstacle avoidance difficulty of 50%; when the ice cone length value is higher than the second ice cone length threshold, the leaf node outputs an obstacle avoidance difficulty of 100%. A preliminary ID3 decision tree model is constructed. The constructed ID3 decision tree model is then validated using the validation set. The thresholds and model parameters are adjusted to optimize the ID3 decision tree model, resulting in an ice cone obstacle avoidance model.

7. The obstacle avoidance system for a power inspection robot according to claim 6, characterized in that: The icing risk assessment module analyzes ice thickness data and ice cone length data, including the following processes: S1. Analyze the collected ice thickness data and input it into the ice obstacle avoidance model. When the input value is lower than the first ice thickness threshold, the obstacle avoidance difficulty is 0%; when the input value is between the first ice thickness threshold and the second ice thickness threshold, the obstacle avoidance difficulty is 50%; when the input value is higher than the second ice thickness threshold, the obstacle avoidance difficulty is 100%. S2. Analyze the collected ice cone length data and input it into the ice cone obstacle avoidance model. When the input value is lower than the first ice cone length threshold, the obstacle avoidance difficulty is 0%; when the input value is between the first ice cone length threshold and the second ice cone length threshold, the obstacle avoidance difficulty is 50%; when the input value is higher than the second ice cone length threshold, the obstacle avoidance difficulty is 100%. S3. Wirelessly transmit the obstacle avoidance difficulty percentage result to the obstacle avoidance execution module.

8. The obstacle avoidance system for a power inspection robot according to claim 7, characterized in that: The obstacle avoidance execution module receives the analysis results and performs corresponding operations, including the following process: When the obstacle avoidance difficulty is received as 0%, it has no effect on the inspection robot's obstacle avoidance; when the obstacle avoidance difficulty is received as 50%, an instruction is issued to activate the mechanical vibration de-icing device of the inspection robot; when the obstacle avoidance difficulty is received as 100%, an instruction is issued to stop the inspection robot from moving forward, change the inspection route, and issue an alarm to the staff for handling.

9. An obstacle avoidance method for a power inspection robot, implemented based on the obstacle avoidance system of the power inspection robot according to any one of claims 1-8, characterized in that, It consists of the following steps: Step 1: Use an ice detector to emit electromagnetic waves to the ice layer, collect the echo time, and collect the three-dimensional point cloud data of the ice cone using a three-dimensional scanner. Step 2: Convert the echo time into ice thickness data through calculation, use the Delaunay triangulation algorithm to convert the three-dimensional point cloud data of the ice cone surface into a three-dimensional model of the ice cone, and then use Blender modeling software to extract the ice cone length data from the three-dimensional model of the ice cone. Step 3: Set thresholds for ice thickness data and ice cone length data, and output obstacle avoidance results corresponding to different ice thickness data and different ice cone length data through clustering algorithms; Step 4: Construct ice layer obstacle avoidance model and ice cone obstacle avoidance model using ID3 decision tree algorithm; Step 5: Analyze real-time ice thickness data and ice cone length data, and transmit the analysis results to the obstacle avoidance execution module; Step Six: Receive the analysis results. When the obstacle avoidance difficulty is 0%, it has no impact on the obstacle avoidance of the inspection robot. When the obstacle avoidance difficulty is 50%, an instruction is issued to activate the mechanical vibration de-icing device of the inspection robot. When the obstacle avoidance difficulty is 100%, an instruction is issued to stop the inspection robot from moving forward, change the inspection route, and issue an alarm to the staff for handling.

Images