基于CS-BP神经网络的巡检机器人位移补偿方法研究

doi:10.12398/j.issn.2096-7217.2022.02.007

智能化农业装备学报（中英文） ›› 2022, Vol. 3 ›› Issue (2): 53-63.DOI: 10.12398/j.issn.2096-7217.2022.02.007

基于CS-BP神经网络的巡检机器人位移补偿方法研究

王星辰¹，潘伟¹，周立春²，侯英勇²，Petr Bartos³，肖茂华^1*

1. 南京农业大学工学院，江苏南京，210031； 2. 江苏华丽智能科技股份有限公司，江苏常州，213000； 3. 南波希米亚大学农学院，布杰约维采，370 05，捷克

出版日期:2022-11-15 发布日期:2022-11-15
通讯作者: 肖茂华
作者简介:王星辰

Research on displacement compensation method of inspection robot based on CS-BP neural network

Wang Xingchen¹, Pan Wei¹, Zhou Lichun², Hou Yingyong², Petr Bartos³, Xiao Maohua^1*

1. College of Engineering, Nanjing Agricultural University, Nanjing 210031, China；
2. Jiangsu Huali Intelligent Technology Co., Ltd., Changzhou 213000, China；
3. Faculty of Agriculture, University of South Bohemia, Ceske Budejovice 370 05, Czech

Online:2022-11-15 Published:2022-11-15
Contact: Xiao Maohua
About author:Wang Xingchen, research interests: intelligent agricultural machinery equipment. E-mail: 2268783082@qq.com
Supported by:
Jiangsu Province International Cooperation Project (BZ2021022); Changzhou International Science and Technology Cooperation Project (CZ20220011); Jiangsu Province Modern Agricultural Machinery Equipment and Technology Demonstration and Promotion Project (NJ2020-01); Nanjing Agricultural University SRT Project(202110307050)

摘要/Abstract

摘要： 智能巡检机器人沿着固定轨迹进行巡检工作时所产生的位移误差会不断地增加，从而偏离既定的巡检路线。因此，提出一种基于CS-BP神经网络的位移补偿方法，利用布谷鸟搜索算法对BP神经网络的权值与阈值进行优化，得到性能最为优异的神经网络结构。试验表明，理论位移曲线乘以通过神经网络输出的位移补偿系数后得到的补偿后的位移曲线与实际位移曲线更加接近，其位移误差远远小于未经补偿的理论位移曲线，试验结果在58.8 s时，经过CS-BP神经网络补偿后输出的位移与实际位移能够维持在3 cm左右的偏差。该位移补偿具有可行性，能够有效缓解智能巡检机器人的运动路径偏离巡检路线的问题。

关键词: 智能巡检机器人, BP神经网络, 布谷鸟搜索算法, 位移补偿

Abstract: The displacement error of intelligent patrol robot will continuously increase when it conducts patrol inspection along a fixed trajectory, thus deviating from the established inspection route. This paper presents a displacement compensation method based on CS-BP neural network. The Cuckoo search algorithm is used to optimize the weight and threshold of BP neural network in order to obtain the most excellent neural network structure. The experimental results show that the compensated displacement curve is closer to the actual displacement curve, and the displacement error is much smaller than the uncompensated theoretical displacement curve. At 58.8 s in the experiment, the deviation between the output displacement and the actual displacement after compensation by CS-BP neural network can be maintained at about 3 cm. The displacement compensation method is feasible and can effectively alleviate the problem that the motion path of the intelligent inspection robot deviates from the inspection route.

Key words: intelligent inspection robot, BP neural network, Cuckoo search algorithm, displacement compensation

中图分类号:

王星辰, 潘伟, 周立春, 侯英勇, Petr Bartos, 肖茂华. 基于CS-BP神经网络的巡检机器人位移补偿方法研究[J]. 智能化农业装备学报（中英文）, 2022, 3(2): 53-63.

Wang Xingchen, Pan Wei, Zhou Lichun, Hou Yingyong, Petr Bartos, Xiao Maohua. Research on displacement compensation method of inspection robot based on CS-BP neural network[J]. Journal of Intelligent Agricultural Mechanization, 2022, 3(2): 53-63.

参考文献

［1］Zheng Y H, Yu X T, Ma S H, et al. Autonomous motion planning of inspection robot for substation fault warning ［J］. Journal of Shenyang University of Technology, 2021, 43(1): 6-11. (in Chinese)

［2］Zhang S, Yao J T, Wang Y B, et al. Design and motion analysis of reconfigurable wheel-legged mobile robot ［J］. Defence Technology, 2022, 18(6): 1023-1040.

［3］Jaca N A, Amilibia J L, Garmendia I U, et al. Industrial robotics trajectory compensation model and joints torsional stiffness impact analysis ［C］// 2020 6th International Conference on Control, Automation and Robotics (ICCAR). 2020.
［4］Liu Z, Zhao Z, Ren S, et al. Kinematic calibration and compensation for a robot with structural deformation ［J］. Robot, 2015, 3: 376-384.
［5］Chen G, Yang J Z, Xiang H, et al. New positional accuracy Calibration method for an autonomous robotic inspection system ［J］. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2022, 44(5): 1-10.
［6］Qi J, Chen B, Zhang D. A calibration method for enhancing robot accuracy through integration of kinematic model and spatial interpolation algorithm ［J］. Journal of Mechanisms and Robotics: Transactions of the ASME, 2021, 13(6): 061013.
［7］Cai Y, Yuan P J, Shi Z Y, et al. Application of universal Kriging for calibrating offline-programming ［J］. Journal of Intelligent & Robotic Systems, 2019, 94(2): 339-348.
［8］Chen D D, Yuan P J, Wang T M, et al. A compensation method for enhancing aviation drilling robot accuracy based on Co-Kriging ［J］. International Journal of Precision Engineering and Manufacturing, 2018, 19(8): 1133-1142.
［9］Al Janaideh M, Rakotondrabe M, Al-Darabsah I, et al. Internal model-based feedback control design for inversion-free feedforward rate-dependent hysteresis compensation of piezoelectric cantilever actuator ［J］. Control Engineering Practice, 2018, 72: 29-41.
［10］Li H F, Xiang S T, Ruan L L. Trajectory error compensation method for autonomous mobile robot ［J］. Mechanical design and research, 2018, 34(6): 21-24. (in Chinese)
［11］Shi X, Lu J, Liu F, et al.Patrol robot navigation control based on memory algorithm ［C］// 2014 4th IEEE International Conference on Information Science and Technology, 2014: 188-191.
［12］Liu X, Jiang D, Tao B, et al. Genetic algorithm-based trajectory optimization for digital twin robots ［J］. Frontiers In Bioengineering and Biotechnology, 2022, 9: 793782.
［13］Alhalabi A, Ezim M, Canbek K O, et al. A multiple sensor fusion based drift compensation algorithm for mecanum wheeled mobile robots ［J］. Turkish Journal of Electrical Engineering and Computer Sciences, 2021, 29(2): 704-716.
［14］Maekawa S. Machine learning device for machine tool and thermal displacement compensation device ［P］. US20180196405A1, 2018.
［15］Fujishima M, Narimatsu K, Irino N, et al. Adaptive thermal displacement compensation method based on deep learning ［J］. CIRP Journal of Manufacturing Science and Technology, 2019, 25: 22-25.
［16］Sliwinski P. The methodology of design of axial clearances compensation unit in hydraulic satellite displacement machine and their experimental verification ［J］. Archives of Civil and Mechanical Engineering, 2019, 19(4): 1163-1182.
［17］Lü Q, Liu Z W, Wang W, et al. Fast method to detect and calculate displacement errors in a Littrow grating-based interferometer ［J］. Applied Optics, 2019, 58(12): 3193-3199.
［18］Zheng K L, Han B L, Wang X D. Ackerman robot motion planning system based on improved TEB algorithm ［J］. Science Technology and Engineering, 2020, 20(10): 3997-4003. (in Chinese)
［19］Ren J X, Wu T, Zhou X H, et al. SLAM, path planning algorithm and application research of an indoor substation wheeled robot navigation system ［J］. Electronics, 2022, 11(12): 1838.
［20］Liu J H, Zhao T, Dian S Y. General type-2 fuzzy sliding mode control for motion balance adjusting of power-line inspection robot ［J］. Methodologies and Application, 2021, 25(2): 1033-1047.
［21］Gao H B, Lu S Y, Wang T. Motion path planning of 6-DOF industrial robot based on fuzzy control algorithm ［J］. Journal of Intelligent & Fuzzy Systems, 2020, 38(4): 3773-3782.
［22］Tsai M S, Huang Y C. A novel integrated dynamic acceleration/deceleration interpolation algorithm for a CNC controller ［J］. International Journal of Advanced Manufacturing Technology, 2016, 87(1): 279-292.
［23］Yu D Y, Ding Z, Tian X Q. Incomplete smooth S-curve acceleration and deceleration federate planning modeling and analysis ［J］. International Journal of Advanced Manufacturing Technology, 2022, 120: 11-12.
［24］Li D, Wu J, Wan J, et al. The implementation and experimental research on an S-curve acceleration and deceleration control algorithm with the characteristics of end-point and target speed modification on the fly ［J］. The International Journal of Advanced Manufacturing Technology, 2017, 91(1): 1145-1169.
［25］Yang S B, Xia T L, Zhang Z Q, et al. Prediction of significant wave heights based on CS-BP model in the South China Sea ［J］. IEEE ACCESS, 2019, 7: 147490-147500.
［26］Xiao M H, Liao Y B, Bartos P, et al. Fault diagnosis of rolling bearing based on back propagation neural network optimized by Cuckoo search algorithm ［J］. Multimedia Tools and Applications, 2022, 81(2): 1567-1587.
［27］Zhang W B, Han G J, Wang J,et al. A BP neural network prediction model based on dynamic Cuckoo search optimization algorithm for industrial equipment fault prediction ［J］. IEEE ACCESS, 2019, 7: 11736-11746.
［28］Wang C, Ma Y, Li W, et al. Design of monitoring system for temperature and humidity of garlic cold storage based on the Internet of Things technology ［J］. Journal of Intelligent Agricultural Mechanization, 2022, 3(1): 37-45.

[1]	王鹏军, 陈永生, 孙冬霞, 吴爱兵, 郝延杰, 陈明江. 基于BP神经网络算法的固体有机肥撒施装置控制系统设计^*[J]. 智能化农业装备学报（中英文）, 2021, 2(1): 13-19.
[2]	毛婷婷, 董淑娴, 薛金林. 农业机器人车辆人机协作控制的动态功能分配研究^*[J]. 智能化农业装备学报（中英文）, 2020, 1(1): 24-31.

基于CS-BP神经网络的巡检机器人位移补偿方法研究

Research on displacement compensation method of inspection robot based on CS-BP neural network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价