Track planning method and system for insulator detection robot

The insulator detection robot trajectory planning model is constructed through the particle swarm optimization algorithm, which solves the robot's endurance problem, optimizes the motion path, and improves the endurance.

CN119077731APending Publication Date: 2024-12-06STATE GRID HUNAN ELECTRIC POWER COMPANY LIMITED +2
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202411228061.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-03
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The insulator detection robot has battery life problems, which affects its practicality and intelligence.

Method used

The particle swarm optimization algorithm is used to construct an insulator detection robot trajectory planning model. By obtaining historical trajectory and environmental deviations, an offline trajectory library is built to optimize the robot's motion path to reduce energy consumption.

Benefits of technology

The energy consumption of insulator detection robots is reduced during the movement process and its endurance is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119077731A_ABST
    Figure CN119077731A_ABST
Patent Text Reader

Abstract

The invention discloses a trajectory planning method for an insulator detection robot, and the method comprises the following steps: obtaining a historical trajectory of the insulator detection robot, and constructing a deviation space; based on a particle swarm optimization algorithm, constructing an insulator detection robot trajectory planning model; according to the deviation space and an insulator detection robot trajectory planning model, an off-line trajectory library based on environmental deviation is constructed; and according to the offline trajectory library and the insulator detection robot trajectory planning model, performing actual insulator detection robot trajectory planning. The invention also discloses a system for realizing the trajectory planning method of the insulator detection robot. According to the method, on the basis of a particle swarm optimization algorithm, the optimal track of the insulator detection robot is solved by taking the lowest energy consumption as a target function; the obtained optimal track can reduce the energy consumption of the insulator detection robot in the moving process, and the cruising ability is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of robots, and in particular relates to a trajectory planning method and system for an insulator detection robot. Background Art

[0002] Insulators are connected between high-voltage transmission lines and high-voltage towers to ensure the insulation of high-voltage transmission lines and high-voltage towers. An insulator string is made up of multiple insulators connected in parallel. A single ultra-high voltage insulator string contains hundreds of insulator pieces to be tested.

[0003] With the development of robotics technology, insulator inspection robots are gradually replacing manual inspections of insulators. Currently, most UHV porcelain insulator strings in the same direction on the same tower are arranged in multiple strings. Compared with traditional manual inspections, insulator inspection robots are not only safer, but also more efficient.

[0004] The insulator detection robot proposed in the transmission line tension insulator detection robot and its application method with the current publication number CN115542003A is composed of two grippers and a five-degree-of-freedom mechanical arm, and has high flexibility. The insulator detection robot has certain endurance problems, which affects its practicality and intelligence. Summary of the invention

[0005] One of the purposes of the present invention is to provide a trajectory planning method for an insulator inspection robot to address the endurance problem of the insulator inspection robot. By planning the motion path of the insulator inspection robot, the energy consumption of the insulator inspection robot is optimized to improve the endurance of the insulator inspection robot.

[0006] A second objective of the present invention is to provide a system for implementing the trajectory planning method of the insulator inspection robot.

[0007] The present invention provides a trajectory planning method for an insulator detection robot, comprising the following steps:

[0008] S1. Obtain the historical trajectory of the insulator inspection robot and construct the deviation space;

[0009] S2. Based on the particle swarm optimization algorithm, the trajectory planning model of the insulator detection robot is constructed;

[0010] S3. According to the deviation space obtained in step S1 and the insulator detection robot trajectory planning model obtained in step S2, an offline trajectory library based on environmental deviation is constructed;

[0011] S4. Perform actual insulator inspection robot trajectory planning based on the offline trajectory library obtained in step S3 and the insulator inspection robot trajectory planning model obtained in step S2.

[0012] The deviation in the deviation space in step S1 is represented by the position and posture of the target gripper starting point and the target point (x1, y1, α1, x2, y2, α2), wherein x1 is the horizontal coordinate of the target gripper starting point; y1 is the vertical coordinate of the target gripper starting point; α1 is the angle between the center axis of the gripper at the target gripper starting point and the vertical direction; x2 is the horizontal coordinate of the target gripper target point; y2 is the vertical coordinate of the target gripper target point; α2 is the angle between the center axis of the gripper at the target gripper target point and the vertical direction;

[0013] The historical trajectories of the insulator inspection robot are all included in the deviation space.

[0014] In step S2, the objective function in the trajectory planning model of the insulator detection robot is the energy consumption of the joint motor during the single-step movement. The integral of the absolute value of the mechanical power and the sum of the Joule heat of the motor are used as the total energy consumption of the joint motor, which is expressed by the following formula:

[0015]

[0016] Among them, W cost is the total energy consumption of a single step; τ motori is the motor torque; ω motori is the motor speed; i motori is the motor current; r is the motor equivalent resistance;

[0017] Through the particle swarm optimization algorithm, the motion trajectory of the insulator detection robot is obtained by iterating a preset number of times. The iterative process of the particle swarm optimization algorithm is expressed using the following formula:

[0018] v i (t+1)=wv i (t)+c1r1(pBest i -x i (t))+c2r2(gBest-x i (t))

[0019] Among them, v i (t) is the initial velocity; w is the inertia coefficient; c1 is the personal optimal learning factor; c2 is the global optimal learning factor; r1 is the personal optimal weight; r2 is the global optimal weight; pBest i gBest is the optimal historical parameter of single ion power consumption; i is the optimal historical parameter of global power consumption; x i (t) is the robot trajectory parameter at the current moment;

[0020] Step S3 specifically comprises: discretizing the deviation space obtained in step S1 to obtain deviation units, and then solving each deviation unit in the deviation space to obtain an offline trajectory library based on environmental deviation;

[0021] When discretizing the deviation space, x1 is discretized with a step size of 5 mm, y1 is discretized with a step size of 4 mm, and α1 is discretized with a step size of 1°;

[0022] The conditions of the discrete unit of the deviation space are input into the trajectory planning model of the insulator inspection robot. Under different conditions of the discrete unit of the deviation space, the value of the objective function is used as the optimization target, and the optimal trajectory corresponding to different discrete units is obtained through the particle swarm optimization algorithm and recorded in the offline trajectory library.

[0023] The offline trajectory library includes optimal trajectory parameters under different environmental deviation parameters.

[0024] The actual insulator detection robot trajectory planning described in step S4 includes the following steps:

[0025] a. Obtain the environmental information of the insulator detection robot;

[0026] b. According to the insulator detection robot environment information obtained in step a, deviation is solved to obtain the deviation spatial orientation of the initial environment of the insulator detection robot, and then the unit with the closest Euclidean distance in the offline trajectory library obtained in step S3 is obtained as the starting unit;

[0027] c. Use the starting unit obtained in step b as the initial point of the particle swarm optimization algorithm in the insulator detection robot trajectory planning model obtained in step S2, iterate and optimize several times, obtain the trajectory parameters, and complete the insulator detection robot trajectory planning.

[0028] The present invention also provides a system for implementing the trajectory planning method of the insulator detection robot, comprising a deviation space construction module, a model construction module, an offline trajectory library construction module and a trajectory planning module;

[0029] The deviation space construction module obtains the historical trajectory of the insulator detection robot, constructs the deviation space, and uploads the data to the offline trajectory library construction module;

[0030] The model building module builds the trajectory planning model of the insulator detection robot based on the particle swarm optimization algorithm and uploads the data to the offline trajectory library;

[0031] The offline trajectory library construction module constructs an offline trajectory library based on environmental deviation according to the received data, and uploads the data to the trajectory planning module;

[0032] The trajectory planning module performs actual insulator inspection robot trajectory planning based on the received data.

[0033] The present invention discloses a trajectory planning method and system for an insulator detection robot. Based on a particle swarm optimization algorithm, the optimal trajectory of the insulator detection robot is obtained by taking the minimum energy consumption as the objective function. The optimal trajectory obtained by the method of the present invention can reduce the energy consumption of the insulator detection robot during its movement and improve its endurance. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic diagram of the process of the present invention;

[0035] Figure 2 It is a schematic diagram of the structure of the system of the present invention. DETAILED DESCRIPTION

[0036] The present invention provides a trajectory planning method for an insulator detection robot, and its flow chart is as follows: Figure 1 As shown, the following steps are included:

[0037] S1. Obtain the historical trajectory of the insulator inspection robot and construct the deviation space;

[0038] The deviation in the deviation space in step S1 is represented by the position and posture of the target gripper starting point and the target point (x1, y1, α1, x2, y2, α2), wherein x1 is the horizontal coordinate of the target gripper starting point; y1 is the vertical coordinate of the target gripper starting point; α1 is the angle between the center axis of the gripper at the target gripper starting point and the vertical direction; x2 is the horizontal coordinate of the target gripper target point; y2 is the vertical coordinate of the target gripper target point; α2 is the angle between the center axis of the gripper at the target gripper target point and the vertical direction;

[0039] The historical trajectories of the insulator inspection robot are all included in the deviation space.

[0040] S2. Based on the particle swarm optimization algorithm, the trajectory planning model of the insulator detection robot is constructed;

[0041] In step S2, the objective function in the trajectory planning model of the insulator detection robot is the energy consumption of the joint motor during the single-step movement. The integral of the absolute value of the mechanical power and the sum of the Joule heat of the motor are used as the total energy consumption of the joint motor, which is expressed by the following formula:

[0042]

[0043] Among them, W cost is the total energy consumption of a single step; τ motori is the motor torque; ω motori is the motor speed; i motori is the motor current; r is the motor equivalent resistance;

[0044] Through the particle swarm optimization algorithm, the motion trajectory of the insulator detection robot is obtained by iterating a preset number of times. The iterative process of the particle swarm optimization algorithm is expressed using the following formula:

[0045] v i (t+1)=wv i (t)+c1r1(pBest i -x i (t))+c2r2(gBest-x i (t))

[0046] Among them, v i (t) is the initial velocity; w is the inertia coefficient; c1 is the personal optimal learning factor; c2 is the global optimal learning factor; r1 is the personal optimal weight; r2 is the global optimal weight; pBest i gBest is the optimal historical parameter of single ion power consumption; i is the optimal historical parameter of global power consumption; x i (t) is the robot trajectory parameter at the current moment;

[0047] S3. According to the deviation space obtained in step S1 and the trajectory planning model of the insulator detection robot obtained in step S2, an offline trajectory library based on environmental deviation is constructed, specifically:

[0048] The deviation space obtained in step S1 is discretized to obtain deviation units, and then each deviation unit in the deviation space is solved to obtain an offline trajectory library based on environmental deviation;

[0049] When discretizing, x1 is discretized in 5mm steps, y1 is discretized in 4mm steps, and α1 is discretized in 1° steps;

[0050] The conditions of the discrete unit of the deviation space are input into the trajectory planning model of the insulator inspection robot. Under different conditions of the discrete unit of the deviation space, the value of the objective function is used as the optimization target, and the optimal trajectory corresponding to different discrete units is obtained through the particle swarm optimization algorithm and recorded in the offline trajectory library.

[0051] The offline trajectory library includes optimal trajectory parameters under different environmental deviation parameters;

[0052] S4. According to the offline trajectory library obtained in step S3 and the insulator detection robot trajectory planning model obtained in step S2, the actual insulator detection robot trajectory planning is performed, comprising the following steps:

[0053] a. Obtain the environmental information of the insulator detection robot;

[0054] b. According to the insulator detection robot environment information obtained in step a, deviation is solved to obtain the deviation spatial orientation of the initial environment of the insulator detection robot, and then the unit with the closest Euclidean distance in the offline trajectory library obtained in step S3 is obtained as the starting unit;

[0055] c. Use the starting unit obtained in step b as the initial point of the particle swarm optimization algorithm in the insulator detection robot trajectory planning model obtained in step S2, iterate and optimize several times, obtain the trajectory parameters, and complete the insulator detection robot trajectory planning.

[0056] In the trajectory planning of the insulator detection robot, the trajectory is defined by describing the three-dimensional space path of the end effector from the starting point to the target point; the high-order Bezier curve is used as the expression of the trajectory, and the end trajectory of the insulator detection robot is corrected by modifying the position of the control point; the high-order Bezier curve defines the curve shape through the control points and is widely used in the path planning of the robotic arm; in the trajectory planning, a difference area is set between the initial point and the target point, multiple control points are set, and the coordinates of the control points are used as optimization variables to establish and solve the optimization problem.

[0057] The present invention also provides a system for implementing the trajectory planning method of the insulator detection robot, comprising a deviation space construction module, a model construction module, an offline trajectory library construction module and a trajectory planning module;

[0058] The deviation space construction module obtains the historical trajectory of the insulator detection robot, constructs the deviation space, and uploads the data to the offline trajectory library construction module;

[0059] The model building module builds the trajectory planning model of the insulator detection robot based on the particle swarm optimization algorithm and uploads the data to the offline trajectory library;

[0060] The offline trajectory library construction module constructs an offline trajectory library based on environmental deviation according to the received data, and uploads the data to the trajectory planning module;

[0061] The trajectory planning module performs actual insulator inspection robot trajectory planning based on the received data.

Claims

1. A trajectory planning method for an insulator inspection robot, characterized in that: The following steps are involved: S1. Obtain the historical trajectory of the insulator inspection robot and construct the deviation space; S2. Based on the particle swarm optimization algorithm, the trajectory planning model of the insulator detection robot is constructed; S3. According to the deviation space obtained in step S1 and the insulator detection robot trajectory planning model obtained in step S2, an offline trajectory library based on environmental deviation is constructed; S4. Perform actual insulator inspection robot trajectory planning based on the offline trajectory library obtained in step S3 and the insulator inspection robot trajectory planning model obtained in step S2.

2. The trajectory planning method of the insulator inspection robot according to claim 1, characterized in that: The deviation in the deviation space in step S1 is represented by the position and posture of the target gripper starting point and the target point (x1, y1, α1, x2, y2, α2), wherein x1 is the horizontal coordinate of the target gripper starting point; y1 is the vertical coordinate of the target gripper starting point; α1 is the angle between the center axis of the gripper at the target gripper starting point and the vertical direction; x2 is the horizontal coordinate of the target gripper target point; y2 is the vertical coordinate of the target gripper target point; α2 is the angle between the center axis of the gripper at the target gripper target point and the vertical direction; The historical trajectories of the insulator inspection robot are all included in the deviation space.

3. The trajectory planning method of the insulator inspection robot according to claim 1, characterized in that: In step S2, the objective function in the trajectory planning model of the insulator detection robot is the energy consumption of the joint motor during the single-step movement. The integral of the absolute value of the mechanical power and the sum of the Joule heat of the motor are used as the total energy consumption of the joint motor, which is expressed by the following formula: Among them, W cost is the total energy consumption of a single step; τ motori is the motor torque; ω motori is the motor speed; i motori is the motor current; r is the motor equivalent resistance; Through the particle swarm optimization algorithm, the motion trajectory of the insulator detection robot is obtained by iterating a preset number of times. The iterative process of the particle swarm optimization algorithm is expressed using the following formula: v i (t+1)=wv i (t)+c1r1(pBest i -x i (t))+c2r2(gBest-x i (t)) Among them, v i (t) is the initial velocity; w is the inertia coefficient; c1 is the personal optimal learning factor; c2 is the global optimal learning factor; r1 is the personal optimal weight; r2 is the global optimal weight; pBest i gBest is the optimal historical parameter of single ion power consumption; i is the optimal historical parameter of global power consumption; x i (t) is the robot trajectory parameter at the current moment.

4. The trajectory planning method of the insulator inspection robot according to claim 3, characterized in that: Step S3 specifically comprises: discretizing the deviation space obtained in step S1 to obtain deviation units, and then solving each deviation unit in the deviation space to obtain an offline trajectory library based on environmental deviation; When discretizing the deviation space, x1 is discretized with a step size of 5 mm, y1 is discretized with a step size of 4 mm, and α1 is discretized with a step size of 1°; The conditions of the discrete unit of the deviation space are input into the trajectory planning model of the insulator inspection robot. Under different conditions of the discrete unit of the deviation space, the value of the objective function is used as the optimization target, and the optimal trajectory corresponding to different discrete units is obtained through the particle swarm optimization algorithm and recorded in the offline trajectory library. The offline trajectory library includes optimal trajectory parameters under different environmental deviation parameters.

5. The trajectory planning method of the insulator inspection robot according to claim 4, characterized in that: The actual insulator detection robot trajectory planning described in step S4 includes the following steps: a. Obtain the environmental information of the insulator detection robot; b. According to the insulator detection robot environment information obtained in step a, deviation is solved to obtain the deviation spatial orientation of the initial environment of the insulator detection robot, and then the unit with the closest Euclidean distance in the offline trajectory library obtained in step S3 is obtained as the starting unit; c. Use the starting unit obtained in step b as the initial point of the particle swarm optimization algorithm in the insulator detection robot trajectory planning model obtained in step S2, iterate and optimize several times, obtain the trajectory parameters, and complete the insulator detection robot trajectory planning.

6. A system for implementing the trajectory planning method of the insulator inspection robot according to any one of claims 1 to 5, characterized in that: It includes a deviation space construction module, a model construction module, an offline trajectory library construction module and a trajectory planning module; The deviation space construction module obtains the historical trajectory of the insulator detection robot, constructs the deviation space, and uploads the data to the offline trajectory library construction module; The model building module builds the trajectory planning model of the insulator detection robot based on the particle swarm optimization algorithm and uploads the data to the offline trajectory library; The offline trajectory library construction module constructs an offline trajectory library based on environmental deviation according to the received data, and uploads the data to the trajectory planning module; The trajectory planning module performs actual insulator inspection robot trajectory planning based on the received data.

Citation Information

Patent Citations

  • Power transmission line strain insulator detection robot and application method thereof

    CN115542003A