A robot-based cable pipeline detection and obstacle removal method and system

Abstract

The present invention relates to the technical field of pipeline obstacle removal, and discloses a robot-based cable pipeline detection and obstacle removal method and system, comprising acquiring multi-source data from within the cable pipeline, performing data processing and feature analysis to obtain obstacle information; generating tool configuration adjustment instructions based on tool parameters and obstacle information of the obstacle removal tool; generating operation force control parameters and tool motion trajectory based on the reaction force and friction coefficient when the obstacle removal robot contacts the obstacle; acquiring a particle distribution image inside the cable pipeline, performing image processing, obtaining a particle cleaning planning path, and generating particle cleaning instructions. Through multimodal perception fusion, dynamic optimization decision-making, and output motion coordinated control, the present invention effectively improves the efficiency of cable pipeline obstacle removal, reduces obstacle removal costs, ensures the safety of the cable pipeline during the obstacle removal process, and provides an effective solution for the intelligent operation and maintenance of urban pipeline networks.

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline obstacle removal, and in particular to a robot-based cable pipeline detection and obstacle removal method and system. Background Art

[0002] As a core component of urban infrastructure, cable conduits undertake the critical task of power and communication transmission. With the acceleration of urbanization, the types and complexity of obstacles in the conduits are increasing. Removing these obstacles has become an important issue in maintaining the function of the conduits. The cleaning and maintenance of the interior of the cable conduits will affect the stability and safety of the system operation.

[0003] Currently, the most commonly used method for clearing cable conduits is a pipeline robot. Because obstacles of varying hardness, such as gravel and cement blocks, may exist inside cable conduits, the types of tools and operating forces required for each obstacle vary. Existing pipeline robots mostly use fixed end-tools, which are difficult to adapt to obstacles with significantly different hardnesses. They lack the ability to quickly and accurately switch clearance tools based on the actual obstacle situation. Frequent tool switching not only leads to inefficient clearance work but also easily causes scratches or secondary damage to the pipe wall. During the clearance process, the reaction force and friction coefficient fluctuate significantly when the tool contacts the obstacle. Current robot control cannot adjust operating parameters in real time based on actual conditions, resulting in unstable clearance. Furthermore, current pipeline robots lack intelligent planning of cleaning paths for particles generated by broken obstacles, further impacting clearance efficiency. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention provides a robot-based cable pipeline detection and obstacle removal method and system, which can solve the problems of low tool switching efficiency and insufficient control accuracy of existing pipeline robots, achieve precise control of cable pipeline obstacle removal robots, and improve the efficiency of cable pipeline obstacle removal.

[0005] In a first aspect, the present invention provides a robot-based cable conduit detection and obstacle removal method, the method comprising:

[0006] Acquire multi-source data inside the cable conduit, and perform data processing and feature analysis on the multi-source data to obtain obstacle information, wherein the obstacle information includes obstacle type and obstacle location;

[0007] Based on the preset tool parameters of the obstacle removal tool and the obstacle information, a multi-objective optimization algorithm is used to calculate the optimal tool switching sequence, and based on the optimal tool switching sequence, a tool configuration adjustment instruction is generated and sent to the obstacle removal robot;

[0008] In response to the obstacle clearing robot executing the tool configuration adjustment instruction to replace the obstacle clearing tool, generating an operation force control parameter and a tool motion trajectory based on a reaction force and a friction coefficient when the obstacle clearing robot contacts the obstacle, and generating a control instruction based on the operation force control parameter and the tool motion trajectory, and sending the control instruction to the obstacle clearing robot;

[0009] In response to the obstacle clearing robot executing the control instruction, a particle distribution image inside the cable pipe is obtained, and image processing is performed to obtain a particle cleaning planning path. According to the particle cleaning planning path, a particle cleaning instruction is generated and sent to the obstacle clearing robot to perform the cleaning operation.

[0010] Furthermore, the step of acquiring multi-source data inside the cable duct and performing data processing and feature analysis on the multi-source data to obtain obstacle information, wherein the obstacle information includes obstacle type and obstacle location, comprises:

[0011] Collect laser point cloud data, acoustic wave data, and infrared data based on obstacles inside cable ducts, and perform data processing and particle filtering to obtain a three-dimensional obstacle feature map;

[0012] Obstacle identification is performed according to the preset material matching rules and the three-dimensional obstacle feature map to obtain the obstacle type and obstacle position of each obstacle.

[0013] Furthermore, the step of calculating the optimal tool switching sequence using a multi-objective optimization algorithm based on preset tool parameters of the obstacle removal tool and the obstacle information includes:

[0014] Determine the hardness of the obstacle according to the obstacle type, and extract the tool hardness, remaining tool life, and expected tool life of each obstacle removal tool from a preset tool database;

[0015] Calculating a tool matching coefficient based on the hardness of the obstacle, the hardness of the tool, the remaining life of the tool, and the expected life of the tool;

[0016] A multi-objective optimization model is established with minimization of tool cost and minimization of tool switching time as objective functions and the tool matching coefficient and the remaining life of the tool as constraints;

[0017] The multi-objective optimization model is solved to obtain an optimal tool switching sequence.

[0018] Furthermore, the tool matching coefficient is expressed by the following formula:

[0019]

[0020] Where, represents the tool matching coefficient between the i-th obstacle removal tool and the j-th obstacle type, S i represents the tool hardness of the i-th obstacle removal tool, S j represents the obstacle hardness of the j-th obstacle type, α1 represents the hardness coefficient, M s,i represents the remaining life of the i-th obstacle removal tool, M i represents the expected life of the i-th obstacle removal tool, and α2 represents the life coefficient;

[0021] The objective function is expressed by the following formula:

[0022]

[0023]

[0024] Where n represents the total number of obstacle removal tools, C i represents the unit price of the i-th obstacle removal tool, N i represents the number of times the i-th obstacle removal tool is used, T s,i represents the switching time of the i-th obstacle removal tool, T o,i represents the operation time of the i-th obstacle removal tool, C total represents the tool cost, T total Indicates that tool switching takes time;

[0025] The constraints are expressed using the following formula:

[0026]

[0027]

[0028] Where, Represents the coefficient threshold, M t Indicates the lifespan threshold.

[0029] Furthermore, the step of generating the operation force control parameter and the tool motion trajectory according to the reaction force and friction coefficient when the obstacle removal robot contacts the obstacle includes:

[0030] Determine a target force according to the type of obstacle, and calculate a force error and an error change rate based on the reaction force when the obstacle-clearing robot contacts the obstacle and the target force;

[0031] Performing fuzzy PID control on the force error and the error change rate to obtain output power;

[0032] Performing friction compensation on the output power according to the friction coefficient when the obstacle removal robot contacts the obstacle to obtain a final output power, and converting the final output power into a motor speed parameter and a motor torque parameter;

[0033] generating an initial path according to the position of the obstacle, and performing curvature smoothing on the initial path to obtain a smooth path;

[0034] Adjusting the initial movement speed according to the friction coefficient to obtain the movement speed;

[0035] A tool motion trajectory of the obstacle removal robot is obtained according to the smooth path and the motion speed.

[0036] Furthermore, the step of acquiring a particle distribution image inside the cable duct and performing image processing to obtain a particle cleaning planning path includes:

[0037] Obtaining a particle distribution image inside the cable conduit, generating a particle density map using a region growing algorithm, and rasterizing the particle density map to obtain a rasterized network;

[0038] Calculating particle density weights and dynamic weight factors according to the rasterized network;

[0039] According to the particle density weight and the dynamic weight factor, a cost function based on a path planning algorithm is constructed and solved to obtain a particle cleaning planning path.

[0040] Furthermore, the particle density weight is expressed by the following formula:

[0041]

[0042] Where d(n) represents the particle density weight of node n, ρ(n) represents the grid density of node n, and ρ t represents the average grid density;

[0043] The dynamic weight factor is expressed by the following formula:

[0044]

[0045] Where w(t) represents the dynamic weight factor at time t, represents the particle density at time t, represents the maximum particle density;

[0046] The cost function is expressed by the following formula:

[0047]

[0048] Where f(n) represents the cost function of node n, g(n) represents the actual cost from the starting point to node n, h(n) represents the estimated cost from node n to the end point, w(t) represents the dynamic weight factor at time t, d(n) represents the particle density weight of node n, and β represents the density coefficient.

[0049] Furthermore, after the step of generating a control instruction according to the operation force control parameter and the tool motion trajectory and sending the instruction to the obstacle removal robot, the method further includes:

[0050] In response to the obstacle removal robot executing the control instruction, the obstacle removal robot acquires laser scanning data of the cable conduit, performs filtering and denoising on the laser scanning data, and generates a conduit wall contour image through three-dimensional reconstruction;

[0051] Inputting the pipe wall contour image into a preset damage classification model to obtain a damage classification result, wherein the damage classification model is constructed based on a convolutional neural network model;

[0052] Extracting damage features of a corresponding area from the laser scanning data according to the damage classification result, the damage features including scratch depth and damage area;

[0053] determining a damage level according to the damage area, and adjusting the tool motion trajectory according to the damage level;

[0054] The output power of the obstacle removal robot is adjusted according to the scratch depth.

[0055] Furthermore, after the step of generating a control instruction according to the operation force control parameter and the tool motion trajectory and sending the instruction to the obstacle removal robot, the method further includes:

[0056] calculating the actual stress based on the reaction force and the tool contact area;

[0057] Calculate the safety factor based on the allowable stress of the cable conduit and the actual stress;

[0058] Adjusting the output power of the obstacle removal robot according to the safety factor;

[0059] The actual stress is expressed by the following formula:

[0060]

[0061] Where, Indicates the actual stress, F ac represents the reaction force, A represents the tool contact area, and K represents the stress coefficient;

[0062] The safety factor is expressed by the following formula:

[0063]

[0064] In the formula, G represents the safety factor, Indicates the allowable stress.

[0065] In a second aspect, the present invention provides a robot-based cable conduit detection and obstacle removal system, the system comprising:

[0066] An obstacle classification module is used to obtain multi-source data inside the cable duct, and perform data processing and feature analysis on the multi-source data to obtain obstacle information, wherein the obstacle information includes obstacle type and obstacle location;

[0067] A tool instruction generation module is used to calculate the optimal tool switching sequence based on the preset tool parameters of the obstacle removal tool and the obstacle information using a multi-objective optimization algorithm, generate tool configuration adjustment instructions based on the optimal tool switching sequence, and send them to the obstacle removal robot;

[0068] an obstacle clearance instruction generation module, configured to, in response to the obstacle clearance robot executing the tool configuration adjustment instruction and replacing the obstacle clearance tool, generate an operation force control parameter and a tool motion trajectory based on the reaction force and friction coefficient when the obstacle clearance robot contacts the obstacle, generate an obstacle clearance control instruction based on the operation force control parameter and the tool motion trajectory, and send the instruction to the obstacle clearance robot;

[0069] The cleaning instruction generation module is used to obtain the particle distribution image inside the cable pipe in response to the obstacle clearance robot executing the control instruction, and perform image processing to obtain a particle cleaning planning path. According to the particle cleaning planning path, a particle cleaning instruction is generated and sent to the obstacle clearance robot to perform the cleaning operation.

[0070] The present invention provides a robot-based cable conduit detection and obstacle removal method and system. This system utilizes multi-sensor data fusion modeling to improve the accuracy of obstacle identification within cable conduits. It optimizes dynamic tool scheduling through a multi-objective optimization algorithm, improving the robot's tool switching efficiency and reducing clearance costs. It dynamically regulates the robot's output power through fuzzy PID control, enabling precise control and improving clearance efficiency. Intelligent particle cleaning path planning improves cleaning efficiency. Finally, a closed-loop protection mechanism for pipe wall damage ensures the safety of the cable conduit during the clearance process. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 1 is a flow chart of a robot-based cable conduit detection and obstacle removal method according to an embodiment of the present invention;

[0072] Figure 2 1 is a schematic structural diagram of a robot-based cable conduit detection and obstacle removal system according to an embodiment of the present invention;

[0073] Reference numerals:

[0074] 10. Obstacle classification module; 20. Tool instruction generation module; 30. Obstacle clearance instruction generation module; 40. Cleaning instruction generation module. DETAILED DESCRIPTION

[0075] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0076] See also Figure 1 The first embodiment of the present invention provides a robot-based cable conduit detection and obstacle removal method, comprising steps S10 to S40:

[0077] Step S10: acquiring multi-source data inside the cable duct, and performing data processing and feature analysis on the multi-source data to obtain obstacle information, wherein the obstacle information includes obstacle type and obstacle location;

[0078] Step S20: Calculate an optimal tool switching sequence using a multi-objective optimization algorithm based on preset tool parameters of the obstacle removal tool and the obstacle information; generate a tool configuration adjustment instruction based on the optimal tool switching sequence and send it to the obstacle removal robot;

[0079] Step S30, in response to the obstacle removal robot executing the tool configuration adjustment instruction to replace the obstacle removal tool, generating an operation force control parameter and a tool motion trajectory based on the reaction force and friction coefficient when the obstacle removal robot contacts the obstacle, generating a control instruction based on the operation force control parameter and the tool motion trajectory, and sending the control instruction to the obstacle removal robot;

[0080] Step S40, in response to the obstacle removal robot executing the control instruction, obtain the particle distribution image inside the cable pipe, and perform image processing to obtain the particle cleaning planning path. According to the particle cleaning planning path, generate the particle cleaning instruction and send it to the obstacle removal robot to perform the cleaning operation.

[0081] The present invention uses multiple sensors to collect data for obstacles inside cable conduits, and determines the type of obstacles inside the conduit through multi-data fusion and analysis. The specific steps include:

[0082] Collect laser point cloud data, acoustic wave data, and infrared data based on obstacles inside cable ducts, and perform data processing and particle filtering to obtain a three-dimensional obstacle feature map;

[0083] Obstacle identification is performed according to the preset material matching rules and the three-dimensional obstacle feature map to obtain the obstacle type and obstacle position of each obstacle.

[0084] In this embodiment, information about obstacles inside the pipeline is collected through laser scanning, acoustic wave detection, and infrared thermal imaging technology. For laser point cloud data, the local point cloud density is calculated to distinguish concave and convex areas, thereby obtaining surface structural features, and the texture features are extracted by calculating the distance between adjacent points. For example, a distance less than 1 mm is a smooth feature, and a distance greater than 5 mm is a rough feature. For acoustic wave data, since the reflection time of acoustic waves for materials of different hardness is different, the material hardness of the obstacle can be calculated by the reflection time of ultrasonic waves. For infrared data, since the thermal conductivity curves of different materials are different, the overall thermal conductivity curve under the preset band can be analyzed, and the infrared material data can be matched from the preset material database.

[0085] After processing surface structural features, texture features, acoustic hardness values, and infrared material data, particle filtering is used to correct nonlinear errors. For the filtered multi-source data, feature vectors are calculated and generated. These feature vectors include shape feature vectors (including curvature, normal vectors, and contour curves) and material feature vectors (including hardness values, thermal conductivity, and reflectivity). Finally, these feature vectors are used to generate a three-dimensional obstacle feature map, which contains fused data such as location, shape, hardness, and material labels. The obstacle material classification is performed using material matching rules and classification algorithms, such as decision trees. Finally, obstacle information data, including obstacle type, location coordinates, and size parameters, is output.

[0086] After determining the type and location of obstacles inside the cable duct, it is necessary to select the corresponding obstacle removal tool based on the obstacle information and generate a tool switching sequence and corresponding tool configuration adjustment instructions based on different obstacle removal tools. The specific steps include:

[0087] Determine the hardness of the obstacle according to the obstacle type, and extract the tool hardness, remaining tool life, and expected tool life of each obstacle removal tool from a preset tool database;

[0088] Calculating a tool matching coefficient based on the hardness of the obstacle, the hardness of the tool, the remaining life of the tool, and the expected life of the tool;

[0089] A multi-objective optimization model is established with minimization of tool cost and minimization of tool switching time as objective functions and the tool matching coefficient and the remaining life of the tool as constraints;

[0090] The multi-objective optimization model is solved to obtain an optimal tool switching sequence.

[0091] In this embodiment, the hardness data of the obstacle can be determined based on the obstacle type in the obstacle information. At the same time, a preset tool database stores multiple obstacle clearing tools and corresponding tool parameters required for the obstacle clearing robot to perform obstacle clearing work. These obstacle clearing tools serve as the end effectors of the obstacle clearing robot and are used to contact obstacles for obstacle clearing operations, such as diamond tools, carbide tools, and high-speed steel tools.

[0092] The tool hardness, remaining tool life, and expected tool life of the obstacle removal tools are extracted from the tool database. Combined with the obstacle hardness, the tool matching coefficient corresponding to each obstacle removal tool is calculated. The tool matching coefficient can be expressed as:

[0093]

[0094] Where, represents the tool matching coefficient between the i-th obstacle removal tool and the j-th obstacle type, S i represents the tool hardness of the i-th obstacle removal tool, S j represents the obstacle hardness of the j-th obstacle type, α1 represents the hardness coefficient, M s,i represents the remaining life of the i-th obstacle removal tool, M i represents the expected life of the i-th obstacle removal tool, and α2 represents the life coefficient.

[0095] Different types of obstacles require different obstacle removal tools. To ensure that the obstacle removal robot achieves the highest switching efficiency and the lowest cost when switching tools, this embodiment uses a multi-objective optimization algorithm to calculate the optimal tool switching sequence. Specifically, the objective functions are minimizing tool cost and tool switching time, and the tool matching coefficient and remaining tool life are used as constraints to construct a multi-objective optimization model. The objective function can be expressed as:

[0096]

[0097]

[0098] Where n represents the total number of obstacle removal tools, C i represents the unit price of the i-th obstacle removal tool, N i represents the number of times the i-th obstacle removal tool is used, T s,i represents the switching time of the i-th obstacle removal tool, T o,i represents the operation time of the i-th obstacle removal tool, C total represents the tool cost, T totalIndicates the time taken to switch tools.

[0099] The constraints can be expressed as:

[0100]

[0101]

[0102] Where, Represents the coefficient threshold, M t Indicates the lifespan threshold.

[0103] For the above multi-objective optimization model, this embodiment preferably uses the NSGA-II algorithm to solve and screen out the Pareto optimal solution set. The specific solution steps can refer to the conventional NSGA-II algorithm solution steps and will not be explained in detail here.

[0104] After obtaining the optimal tool switching sequence, the position of the obstacle removal tools in the sequence in the obstacle removal robot is determined according to the optimal tool switching sequence. Assuming that the tool library structure of the obstacle removal robot is a circular arrangement structure with multiple stations, the current target station angle is calculated according to the station number of the obstacle removal tool in the sequence. For example, the first obstacle removal tool in the sequence is on station 3, and the current target station angle with station 3 is 90 degrees. In this case, the execution position of the obstacle removal robot needs to be rotated 90 degrees. The tool configuration adjustment instruction is generated according to the rotation angle and sent to the obstacle removal robot to realize tool switching.

[0105] After the tool switching is completed, in order to improve the control accuracy of the obstacle removal robot, this embodiment dynamically adjusts the control instructions of the obstacle removal robot by analyzing and processing the reaction force and friction coefficient when the obstacle removal robot contacts the obstacle. The specific steps include:

[0106] Determine a target force according to the type of obstacle, and calculate a force error and an error change rate based on the reaction force when the obstacle-clearing robot contacts the obstacle and the target force;

[0107] Performing fuzzy PID control on the force error and the error change rate to obtain output power;

[0108] Performing friction compensation on the output power according to the friction coefficient when the obstacle removal robot contacts the obstacle to obtain a final output power, and converting the final output power into a motor speed parameter and a motor torque parameter;

[0109] generating an initial path according to the position of the obstacle, and performing curvature smoothing on the initial path to obtain a smooth path;

[0110] Adjusting the initial movement speed according to the friction coefficient to obtain the movement speed;

[0111] A tool motion trajectory of the obstacle removal robot is obtained according to the smooth path and the motion speed.

[0112] In this embodiment, the force feedback sensor array and friction coefficient sensor installed on the obstacle-clearing robot's end effector are used to obtain the reaction force and friction coefficient when the obstacle-clearing robot contacts the obstacle. The reaction force is filtered using a sliding average filter, while the friction coefficient is filtered using a median filter to eliminate sudden noise. The filtered reaction force is used to calculate the real-time force error and error rate of change based on the target force, where the target force is determined based on the obstacle material type. The force error can be expressed as:

[0113]

[0114] Where, e(t) represents the force error at time t, F mb represents the target force, F ac Represents the reaction force, that is, the actual reaction force after filtering.

[0115] The error change rate is expressed as:

[0116]

[0117] Where △e(t) represents the error change rate at time t.

[0118] In view of the problem that the reaction force and friction coefficient of the obstacle-clearing robot fluctuate greatly when contacting the obstacle during actual obstacle clearing work, the existing robot control instructions lack real-time dynamic adjustment, resulting in low control accuracy. In this embodiment, the output power of the obstacle-clearing robot is calculated by first performing fuzzy PID control on the force error and the error change rate. Specifically, the force error and the error change rate are used as inputs of the fuzzy controller, and rule reasoning is performed through a preset fuzzy rule table to output the dynamic adjustment amount of the PID parameters. Finally, the output power is obtained through PID calculation based on the dynamic adjustment amount and the force error. The output power can be expressed as:

[0119]

[0120] Where, P out Indicates output power, K p , K i and K d Both are dynamic adjustment quantities, and e(t) represents the force error at time t.

[0121] Since the output power calculated by PID does not take into account the influence of the friction coefficient, after obtaining the output power, it is necessary to perform friction compensation on the output power according to the friction coefficient to obtain the final output power. In this embodiment, the output power is compensated by the difference between the real-time friction coefficient and the reference friction coefficient. Specifically, when the friction coefficient is low, such as lower than the reference friction coefficient, the friction force is reduced, and the tool is more likely to slip. In this case, the speed needs to be reduced, so the required driving force needs to be reduced. Similarly, when the friction coefficient is high, the friction force increases. At this time, the speed can be maintained or increased to improve the obstacle removal efficiency, so the driving force can be increased. Based on this principle, the final output power after friction compensation can be expressed as:

[0122]

[0123] Where, P f represents the final output power, represents the compensation coefficient, represents the friction coefficient, Indicates the base friction coefficient.

[0124] For the final output power, it is converted into the motor speed parameters and motor torque parameters of the obstacle removal robot.

[0125] Regarding the tool motion trajectory of the obstacle-clearing robot, in this embodiment, an initial path is first generated according to the position of the obstacle. The maximum allowable curvature is used as the path curvature constraint, and the curvature of the initial path is smoothed so that the smoothed path meets the constraint. Secondly, based on the relationship between the friction coefficient and the motion speed, the initial motion speed is adjusted. The adjustment formula can be expressed as:

[0126]

[0127] Where, v new Indicates the speed of movement, v base represents the initial motion speed, represents the friction coefficient, Indicates the base friction coefficient.

[0128] Based on the above-mentioned smooth path and movement speed, the tool motion trajectory of the obstacle-clearing robot can be determined. At the same time, combined with the above-mentioned motor speed parameters and motor torque parameters, the control instructions of the obstacle-clearing robot are ultimately generated to achieve precise control of the obstacle-clearing robot. It should be noted that in this embodiment, the smooth path and movement speed are directed to the movement speed and movement path of the obstacle-clearing tool when the obstacle-clearing robot uses the obstacle-clearing tool to perform obstacle-clearing work, and are not the movement path and movement speed of the obstacle-clearing robot itself. The control instructions in this embodiment are directed to the control of the obstacle-clearing tool by the obstacle-clearing robot when performing obstacle-clearing work. During the obstacle-clearing process, this embodiment dynamically adjusts the control parameters of the obstacle-clearing robot in real time by analyzing the reaction force and friction coefficient between the obstacle-clearing robot and the obstacle in real time, which can improve the accuracy of the obstacle-clearing robot's control of the obstacle-clearing tool, thereby improving obstacle-clearing efficiency.

[0129] After the obstacle removal robot completes the obstacle removal work, since there may be particles of broken obstacles inside the cable conduit, it is necessary to perform particle cleaning work inside the cable conduit. In this embodiment, by obtaining a particle distribution image inside the cable conduit and performing image processing, a particle cleaning planning path is generated to improve the cleaning efficiency. The specific steps include:

[0130] Obtaining a particle distribution image inside the cable conduit, generating a particle density map using a region growing algorithm, and rasterizing the particle density map to obtain a rasterized network;

[0131] Calculating particle density weights and dynamic weight factors according to the rasterized network;

[0132] According to the particle density weight and the dynamic weight factor, a cost function based on a path planning algorithm is constructed and solved to obtain a particle cleaning planning path.

[0133] In this embodiment, conventional path planning algorithms, such as the traditional A algorithm, are inefficient in responding to dynamic changes in particle distribution during path planning. This algorithm is improved by introducing a dynamic weighting mechanism, enabling real-time response to changes in particle density and optimizing path priority. Specifically, a high-definition camera is used to capture images of the interior of the pipeline. After median filtering and denoising, a region growing algorithm is used to generate a particle density map. This map is then rasterized to produce a gridded network and the density value of each grid cell.

[0134] According to the ratio of network density to average density, the particle density weight is calculated, and the formula is expressed as:

[0135]

[0136] Where d(n) represents the particle density weight of node n, ρ(n) represents the grid density of node n, and ρ t Represents the average grid density. The particle density weight formula means that the higher the density of node n, the greater its particle density weight.

[0137] Then, the dynamic weight factor is calculated based on the ratio of the real-time particle density to the maximum density. The formula is:

[0138]

[0139] Where w(t) represents the dynamic weight factor at time t, represents the particle density at time t, Indicates the maximum particle density.

[0140] In the dynamic weight factor formula, t represents the real-time timestamp, which is used to reflect the dynamic changes of particle distribution. The particle density at time t is It refers to the particle density of the entire particle density map at time t. The maximum particle density is the preset value. The dynamic weight factor is used to characterize high-density areas. The path priority in high-density areas should be increased.

[0141] The above-mentioned particle density weight and dynamic weight factor are introduced into the path cost function to obtain the cost function of the improved A algorithm:

[0142]

[0143] Where f(n) represents the cost function of node n, g(n) represents the actual cost from the starting point to node n, h(n) represents the estimated cost from node n to the end point, w(t) represents the dynamic weight factor at time t, d(n) represents the particle density weight of node n, and β represents the density coefficient.

[0144] For the above cost function, we first initialize the starting point, end point and obstacle positions, and then traverse the adjacent nodes according to the improved A algorithm, giving priority to the path with the smallest cost function. The specific calculation steps can refer to the steps of path planning for the conventional A algorithm, which will not be repeated here.

[0145] This embodiment associates real-time particle density with timestamp t, allowing the algorithm to adapt to changes in particle diffusion or accumulation during the cleaning process. The weight is dynamically adjusted with density, which can prioritize coverage of high-density areas while taking into account path length efficiency. By optimizing the particle cleaning path, the cleaning efficiency of the obstacle removal robot is effectively improved.

[0146] In a preferred embodiment, in order to reduce the damage caused to the cable conduit by the obstacle removal work, the present invention also determines the current damage status inside the conduit in real time when performing the obstacle removal work, thereby adjusting the obstacle removal instructions. The specific steps include:

[0147] In response to the obstacle removal robot executing the control instruction, the obstacle removal robot acquires laser scanning data of the cable conduit, performs filtering and denoising on the laser scanning data, and generates a conduit wall contour image through three-dimensional reconstruction;

[0148] Inputting the pipe wall contour image into a preset damage classification model to obtain a damage classification result, wherein the damage classification model is constructed based on a convolutional neural network model;

[0149] Extracting damage features of a corresponding area from the laser scanning data according to the damage classification result, the damage features including scratch depth and damage area;

[0150] determining a damage level according to the damage area, and adjusting the tool motion trajectory according to the damage level;

[0151] The output power of the obstacle removal robot is adjusted according to the scratch depth.

[0152] In this embodiment, when the obstacle removal robot performs obstacle removal work, laser scanning data of the cable pipe is obtained through laser scanning. These laser scanning data are low-pass filtered to eliminate vibration noise and perform three-dimensional reconstruction to generate a pipe wall contour image. The pipe wall contour image is then input into a pre-trained damage classification model constructed based on a convolutional neural network model for damage identification, and damage classification results are obtained, including different types of damage such as scratches, corrosion, and wear.

[0153] Then, based on the damage classification results, the damage features of the corresponding area are extracted from the filtered laser scanning data. For scratch types, the scratch depth is extracted by calculating the point cloud height difference, such as the height difference between the scratch area and the normal area. For corrosion and wear types, the projected area of ​​the damaged area is statistically analyzed through connected domain analysis to calculate the damage area.

[0154] In this embodiment, the damage area measures the spatial extent of the damaged region on the pipe wall. A larger damage area indicates a greater degree of structural weakness. Therefore, the damage severity can be defined based on the damage area. If the damage area exceeds a preset area threshold, it is marked as a high-damage area. In this case, the tool's trajectory needs to be adjusted to avoid this area as much as possible to prevent further damage to the pipe wall. Regarding the scratch depth, if the scratch depth exceeds the depth threshold, it indicates that the damage to the pipe wall is severe. To clear this area, the output power can be reduced to reduce the operating force of the clearance tool, thereby preventing further damage to the pipe wall.

[0155] This embodiment dynamically adjusts the control instructions of the obstacle removal tool of the obstacle removal robot based on the damage to the pipe wall. While ensuring the obstacle removal efficiency, it further reduces the damage to the cable pipe wall caused by the obstacle removal work, thereby effectively extending the maintenance cycle of the cable pipe.

[0156] In another preferred embodiment, the present invention calculates a safety factor by the reaction force when the obstacle removal tool contacts the obstacle, and adjusts the output power of the obstacle removal robot according to the safety factor. The specific steps include:

[0157] calculating the actual stress based on the reaction force and the tool contact area;

[0158] Calculate the safety factor based on the allowable stress of the cable conduit and the actual stress;

[0159] According to the safety factor, the output power of the obstacle removal robot is adjusted.

[0160] In this embodiment, the actual stress is first calculated based on the reaction force when the obstacle removal tool contacts the obstacle and the tool contact area. The actual stress can be expressed as:

[0161]

[0162] Where, Indicates the actual stress, F ac represents the reaction force, A represents the tool contact area, and K represents the stress coefficient.

[0163] Then, the safety factor is calculated based on the actual stress and the allowable stress of the cable conduit, and the material strength is evaluated by the safety factor. The calculation formula of the safety factor can be expressed as:

[0164]

[0165] In the formula, G represents the safety factor, It represents the allowable stress, that is, the allowable stress of the cable duct wall material. It is a theoretical value based on static ideal conditions, which means no damage and uniform material.

[0166] In this embodiment, the safety factor is used to determine whether the current output of the obstacle removal robot needs to be adjusted. If S = 1.0, it means that the pipe wall is in a critical state at this time. However, in actual working conditions, the problem of excessive instantaneous stress caused by dynamic loads and excessive local stress in the damaged area due to stress concentration effects must also be considered. The safety factor should be appropriately increased to ensure stress safety under actual working conditions. Therefore, in this embodiment, preferably, when S ≥ 1.5, it is considered that the stress on the pipe wall is within the safety range and the output power of the obstacle removal robot does not need to be adjusted. If 1.2 < S < 1.5, it means that there is a certain risk of material stress exceeding the limit, and the output power of the obstacle removal robot needs to be appropriately reduced, such as by 20%. If S ≤ 1.2, after comprehensively considering the actual risks such as dynamic loads, detection errors, and material fatigue, preventive measures should be taken. At this time, the pipeline should be shut down for emergency maintenance to maximize pipeline safety.

[0167] This embodiment comprehensively evaluates the pipeline material and the output of the obstacle removal robot through the safety factor, realizes dynamic regulation of the output power of the obstacle removal robot, and effectively ensures the safety of the cable pipeline during the obstacle removal process.

[0168] This embodiment provides a robot-based cable conduit detection and obstacle removal method. The present invention improves the accuracy of obstacle identification inside cable conduits through multi-sensor data fusion modeling; optimizes dynamic tool scheduling through a multi-objective optimization algorithm, improves the efficiency of the obstacle removal robot's tool switching, and reduces obstacle removal costs; dynamically regulates the output power of the obstacle removal robot through fuzzy PID control, achieves precise control of the obstacle removal robot, and improves obstacle removal efficiency; effectively improves cleaning efficiency through intelligent particle cleaning path planning; and effectively ensures the safety of cable conduits during the obstacle removal process through a pipe wall damage closed-loop protection mechanism. Through multi-modal perception fusion, dynamic optimization decision-making, and output motion coordinated control, the present invention effectively improves the efficiency of cable conduit obstacle removal work, reduces obstacle removal costs, ensures the safety of cable conduits during the obstacle removal process, and provides an effective solution for the intelligent operation and maintenance of urban pipe networks.

[0169] See also Figure 2 Based on the same inventive concept, a second embodiment of the present invention provides a robot-based cable conduit detection and obstacle removal system, comprising:

[0170] The obstacle classification module 10 is used to obtain multi-source data inside the cable duct, and perform data processing and feature analysis on the multi-source data to obtain obstacle information, wherein the obstacle information includes obstacle type and obstacle location;

[0171] The tool instruction generation module 20 is used to calculate the optimal tool switching sequence based on the preset tool parameters of the obstacle removal tool and the obstacle information using a multi-objective optimization algorithm, generate tool configuration adjustment instructions based on the optimal tool switching sequence, and send them to the obstacle removal robot;

[0172] an obstacle clearance instruction generation module 30 for replacing an obstacle clearance tool in response to the obstacle clearance robot executing the tool configuration adjustment instruction, generating an operation force control parameter and a tool motion trajectory based on the reaction force and friction coefficient when the obstacle clearance robot contacts the obstacle, and generating an obstacle clearance control instruction based on the operation force control parameter and the tool motion trajectory, and sending the instruction to the obstacle clearance robot;

[0173] The cleaning instruction generation module 40 is used to obtain the particle distribution image inside the cable pipe in response to the obstacle clearance robot executing the control instruction, and perform image processing to obtain a particle cleaning planning path. According to the particle cleaning planning path, a particle cleaning instruction is generated and sent to the obstacle clearance robot to perform the cleaning operation.

[0174] The technical features and effects of the robot-based cable conduit inspection and clearance system proposed in the embodiments of the present invention are the same as those of the method proposed in the embodiments of the present invention and are not further elaborated here. Each module in the robot-based cable conduit inspection and clearance system can be implemented in whole or in part through software, hardware, or a combination thereof. Each of these modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a computer device memory in software form, allowing the processor to call and execute the corresponding operations of each module.

[0175] In summary, embodiments of the present invention provide a robot-based cable conduit detection and obstacle removal method and system. The method obtains multi-source data from within the cable conduit and performs data processing and feature analysis on the multi-source data to obtain obstacle information, including obstacle type and obstacle location. A multi-objective optimization algorithm is used to calculate an optimal tool switching sequence based on preset tool parameters of the obstacle removal tool and the obstacle information. A tool configuration adjustment instruction is generated based on the optimal tool switching sequence and sent to the obstacle removal robot. In response to the obstacle removal robot executing the tool configuration adjustment instruction, the obstacle removal tool is replaced. Based on the reaction force and friction coefficient when the obstacle removal robot contacts the obstacle, an operation force control parameter and a tool motion trajectory are generated. Based on the operation force control parameter and the tool motion trajectory, a control instruction is generated and sent to the obstacle removal robot. In response to the obstacle removal robot completing the control instruction, a particle distribution image of the interior of the cable conduit is obtained and image processed to obtain a particle cleaning plan path. Based on the particle cleaning plan path, a particle cleaning instruction is generated and sent to the obstacle removal robot to perform the cleaning operation. Through multimodal perception fusion, dynamic optimization decision-making and output motion coordinated control, the present invention effectively improves the efficiency of cable pipeline clearance, reduces clearance costs, ensures the safety of cable pipelines during the clearance process, and provides an effective solution for the intelligent operation and maintenance of urban pipeline networks.

[0176] Each embodiment in this specification is described in a progressive manner, and the same or similar parts of each embodiment can be directly referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. It should be noted that the various technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0177] The above-described embodiments merely represent several preferred implementations of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent. It should be noted that a person skilled in the art could make several improvements and substitutions without departing from the technical principles of the present invention, and these improvements and substitutions should also be considered within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be based on the scope of protection of the claims.

Claims

1. A robot-based cable pipeline detection and obstacle removal method, characterized in that: include: Acquire multi-source data inside the cable conduit, and perform data processing and feature analysis on the multi-source data to obtain obstacle information, wherein the obstacle information includes obstacle type and obstacle location; Based on the preset tool parameters of the obstacle removal tool and the obstacle information, a multi-objective optimization algorithm is used to calculate the optimal tool switching sequence, and based on the optimal tool switching sequence, a tool configuration adjustment instruction is generated and sent to the obstacle removal robot; In response to the obstacle clearing robot executing the tool configuration adjustment instruction to replace the obstacle clearing tool, generating an operation force control parameter and a tool motion trajectory based on a reaction force and a friction coefficient when the obstacle clearing robot contacts the obstacle, and generating a control instruction based on the operation force control parameter and the tool motion trajectory, and sending the control instruction to the obstacle clearing robot; In response to the obstacle removal robot executing the control instruction, an image of the particle distribution inside the cable conduit is acquired, and image processing is performed to obtain a particle cleaning plan path. According to the particle cleaning plan path, a particle cleaning instruction is generated and sent to the obstacle removal robot to perform a cleaning operation; The step of generating the operation force control parameter and the tool motion trajectory according to the reaction force and friction coefficient when the obstacle removal robot contacts the obstacle includes: Determine a target force according to the type of obstacle, and calculate a force error and an error change rate based on the reaction force when the obstacle-clearing robot contacts the obstacle and the target force; Performing fuzzy PID control on the force error and the error change rate to obtain output power; Performing friction compensation on the output power according to the friction coefficient when the obstacle removal robot contacts the obstacle to obtain a final output power, and converting the final output power into a motor speed parameter and a motor torque parameter; generating an initial path according to the position of the obstacle, and performing curvature smoothing on the initial path to obtain a smooth path; Adjusting the initial movement speed according to the friction coefficient to obtain the movement speed; A tool motion trajectory of the obstacle removal robot is obtained according to the smooth path and the motion speed.

2. The robot-based cable conduit detection and obstacle removal method according to claim 1, characterized in that: The step of acquiring multi-source data inside the cable duct and performing data processing and feature analysis on the multi-source data to obtain obstacle information, wherein the obstacle information includes obstacle type and obstacle location, comprises: Collect laser point cloud data, acoustic wave data, and infrared data based on obstacles inside cable ducts, and perform data processing and particle filtering to obtain a three-dimensional obstacle feature map; Obstacle identification is performed according to the preset material matching rules and the three-dimensional obstacle feature map to obtain the obstacle type and obstacle position of each obstacle.

3. The robot-based cable conduit detection and obstacle removal method according to claim 1, characterized in that: The step of calculating the optimal tool switching sequence using a multi-objective optimization algorithm based on preset tool parameters of the obstacle removal tool and the obstacle information includes: Determine the hardness of the obstacle according to the obstacle type, and extract the tool hardness, remaining tool life, and expected tool life of each obstacle removal tool from a preset tool database; Calculating a tool matching coefficient based on the hardness of the obstacle, the hardness of the tool, the remaining life of the tool, and the expected life of the tool; A multi-objective optimization model is established with minimization of tool cost and minimization of tool switching time as objective functions and the tool matching coefficient and the remaining life of the tool as constraints; The multi-objective optimization model is solved to obtain an optimal tool switching sequence.

4. The robot-based cable conduit detection and obstacle removal method according to claim 3, characterized in that: The tool matching coefficient is expressed as follows: Where, represents the tool matching coefficient between the i-th obstacle removal tool and the j-th obstacle type, S i represents the tool hardness of the i-th obstacle removal tool, S j represents the obstacle hardness of the j-th obstacle type, α1 represents the hardness coefficient, M s,i represents the remaining life of the i-th obstacle removal tool, M i represents the expected life of the i-th obstacle removal tool, and α2 represents the life coefficient; The objective function is expressed by the following formula: Where n represents the total number of obstacle removal tools, C i represents the unit price of the i-th obstacle removal tool, N i represents the number of times the i-th obstacle removal tool is used, T s,i represents the switching time of the i-th obstacle removal tool, T o,i represents the operation time of the i-th obstacle removal tool, C total represents the tool cost, T total Indicates that tool switching takes time; The constraints are expressed using the following formula: Where, Represents the coefficient threshold, M t Indicates the lifespan threshold.

5. The robot-based cable conduit detection and obstacle removal method according to claim 1, characterized in that: The step of obtaining a particle distribution image inside the cable duct and performing image processing to obtain a particle cleaning planning path includes: Obtaining a particle distribution image inside the cable conduit, generating a particle density map using a region growing algorithm, and rasterizing the particle density map to obtain a rasterized network; Calculating particle density weights and dynamic weight factors according to the rasterized network; According to the particle density weight and the dynamic weight factor, a cost function based on a path planning algorithm is constructed and solved to obtain a particle cleaning planning path.

6. The robot-based cable conduit detection and obstacle removal method according to claim 5, characterized in that: The particle density weight is expressed using the following formula: Where d(n) represents the particle density weight of node n, ρ(n) represents the grid density of node n, and ρ t represents the average grid density; The dynamic weight factor is expressed by the following formula: Where w(t) represents the dynamic weight factor at time t, represents the particle density at time t, represents the maximum particle density; The cost function is expressed by the following formula: Where f(n) represents the cost function of node n, g(n) represents the actual cost from the starting point to node n, h(n) represents the estimated cost from node n to the end point, w(t) represents the dynamic weight factor at time t, d(n) represents the particle density weight of node n, and β represents the density coefficient.

7. The robot-based cable conduit detection and obstacle removal method according to claim 1, characterized in that: After the step of generating a control instruction according to the operation force control parameter and the tool motion trajectory and sending the control instruction to the obstacle removal robot, the method further includes: In response to the obstacle removal robot executing the control instruction, the obstacle removal robot acquires laser scanning data of the cable conduit, performs filtering and denoising on the laser scanning data, and generates a conduit wall contour image through three-dimensional reconstruction; Inputting the pipe wall contour image into a preset damage classification model to obtain a damage classification result, wherein the damage classification model is constructed based on a convolutional neural network model; Extracting damage features of a corresponding area from the laser scanning data according to the damage classification result, the damage features including scratch depth and damage area; determining a damage level according to the damage area, and adjusting the tool motion trajectory according to the damage level; The output power of the obstacle removal robot is adjusted according to the scratch depth.

8. The robot-based cable conduit detection and obstacle removal method according to claim 7, characterized in that: After the step of generating a control instruction according to the operation force control parameter and the tool motion trajectory and sending the control instruction to the obstacle removal robot, the method further includes: calculating the actual stress based on the reaction force and the tool contact area; Calculate the safety factor based on the allowable stress of the cable conduit and the actual stress; Adjusting the output power of the obstacle removal robot according to the safety factor; The actual stress is expressed by the following formula: Where, Indicates the actual stress, F ac represents the reaction force, A represents the tool contact area, and K represents the stress coefficient; The safety factor is expressed by the following formula: In the formula, G represents the safety factor, Indicates the allowable stress.

9. A robot-based cable pipeline detection and obstacle removal system, characterized in that: include: An obstacle classification module is used to obtain multi-source data inside the cable duct, and perform data processing and feature analysis on the multi-source data to obtain obstacle information, wherein the obstacle information includes obstacle type and obstacle location; A tool instruction generation module is used to calculate the optimal tool switching sequence based on the preset tool parameters of the obstacle removal tool and the obstacle information using a multi-objective optimization algorithm, generate tool configuration adjustment instructions based on the optimal tool switching sequence, and send them to the obstacle removal robot; an obstacle clearance instruction generation module, configured to, in response to the obstacle clearance robot executing the tool configuration adjustment instruction and replacing the obstacle clearance tool, generate an operation force control parameter and a tool motion trajectory based on the reaction force and friction coefficient when the obstacle clearance robot contacts the obstacle, generate an obstacle clearance control instruction based on the operation force control parameter and the tool motion trajectory, and send the instruction to the obstacle clearance robot; The step of generating the operation force control parameter and the tool motion trajectory according to the reaction force and friction coefficient when the obstacle removal robot contacts the obstacle includes: Determine a target force according to the type of obstacle, and calculate a force error and an error change rate based on the reaction force when the obstacle-clearing robot contacts the obstacle and the target force; Performing fuzzy PID control on the force error and the error change rate to obtain output power; Performing friction compensation on the output power according to the friction coefficient when the obstacle removal robot contacts the obstacle to obtain a final output power, and converting the final output power into a motor speed parameter and a motor torque parameter; generating an initial path according to the position of the obstacle, and performing curvature smoothing on the initial path to obtain a smooth path; Adjusting the initial movement speed according to the friction coefficient to obtain the movement speed; Obtaining a tool motion trajectory of the obstacle removal robot according to the smooth path and the motion speed; The cleaning instruction generation module is used to obtain the particle distribution image inside the cable pipe in response to the obstacle clearance robot executing the control instruction, and perform image processing to obtain a particle cleaning planning path. According to the particle cleaning planning path, a particle cleaning instruction is generated and sent to the obstacle clearance robot to perform the cleaning operation.

Images