基于PSO-BPNN和Newton-Raphson法融合的并联机构正运动学解法
Solution for Forward Kinematics of Parallel Mechanism based on PSO-BPNN and Newton-Raphson Algorithm
- 机械传动 2021年45卷第7期 页码：96-102
- 作者机构：
1.重庆交通大学 机电与车辆工程学院， 重庆 400074
2.柳州铁道职业技术学院 装备制造学院， 广西 柳州 545000
3.川庆钻探工程公司 安全环保质量监督检测研究院， 四川 广汉 618300
- 作者简介：
- 基金信息：
DOI：10.16578/j.issn.1004.2539.2021.07.014
中图分类号：
扫 描 看 全 文
胡启国,骆艳丽,曹历杰等.基于PSO-BPNN和Newton-Raphson法融合的并联机构正运动学解法[J].机械传动,2021,45(07):96-102.
Hu Qiguo,Luo Yanli,Cao Lijie,et al.Solution for Forward Kinematics of Parallel Mechanism based on PSO-BPNN and Newton-Raphson Algorithm[J].Journal of Mechanical Transmission,2021,45(07):96-102.
胡启国,骆艳丽,曹历杰等.基于PSO-BPNN和Newton-Raphson法融合的并联机构正运动学解法[J].机械传动,2021,45(07):96-102. DOI： 10.16578/j.issn.1004.2539.2021.07.014.
Hu Qiguo,Luo Yanli,Cao Lijie,et al.Solution for Forward Kinematics of Parallel Mechanism based on PSO-BPNN and Newton-Raphson Algorithm[J].Journal of Mechanical Transmission,2021,45(07):96-102. DOI： 10.16578/j.issn.1004.2539.2021.07.014.
摘要
以并联机构为研究对象，针对求解正运动学时神经网络法易陷入局部最优及Newton-Raphson法对迭代初值敏感的问题，提出了一种融合PSO-BPNN（Back propagation neural network，BPNN）和Newton-Raphson法的正运动学通用求解算法。建立了并联机构逆运动学方程，得到驱动杆值，以此为训练样本，利用粒子群算法（Particle swarm optimization，PSO）优化BPNN（PSO-BPNN）模型获得位置正解，再以PSO-BPNN的正解值作为Newton-Raphson法的迭代初值对并联机构正运动学问题进行求解。为验证算法的有效性和通用性，给出了3-PCR、3-PPR两种并联机构的算例仿真。结果表明，由于迭代初值选取与目标值相差较大，导致Newton-Raphson法无法收敛；相比于PSO-BPNN算法，PSO-BPNN和Newton-Raphson法相结合得到的绝对误差最少降低了99.68%和99.96%，迭代次数更少；该方法既克服了神经网络法局部收敛性差的缺点，又避免了初值选取对Newton-Raphson法求解精度的影响，具有较好的通用性。
Abstract
Taking parallel mechanism as a research object， aiming at the problem that neural network algorithm is easy to fall into local optimization and the Newton-Raphson algorithm is sensitive to the initial value of iteration when solving forward kinematics， a general forward kinematics algorithm combining PSO-BPNN and Newton-Raphson algorithm is proposed. The inverse kinematics equation of parallel mechanism is established to obtain the value of the driving rod， which is used as the training sample， and the BPNN model is optimized by PSO to obtain the solution for forward kinematic， which is taken as the initial iterative value of the newton-raphson algorithm to solve the forward kinematics of parallel mechanism. To verify the effectiveness and universality of the algorithm， simulation examples of 3-PCR and 3-PPR parallel mechanisms are given. The simulation results show that Newton-Raphson algorithm does not converge due to the large difference between the initial iteration value and the target value. Compared with the PSO-BPNN algorithm， the absolute error obtained by combining PSO-BPNN and Newton-Raphson algorithm is reduced by at least 99.68% and 99.96%， and the number of iterations is less. PSO-BPNN and Newton-Raphson algorithm not only overcomes the shortcomings of poor local convergence of the neural network algorithm， but also avoids the influence of initial value selection on the accuracy of the Newton-Raphson algorithm， which has good versatility.
关键词
并联机构正运动学PSO-BPNNNewton-Raphson迭代法
Keywords
Parallel mechanismForward kinematicsPSO back propagation neural networkNewton-Raphson iteration algorithm
references
冯李航，张为公，龚宗洋，等.Delta系列并联机器人研究进展与现状［J］.机器人，2014，36（3）：375-384.
FENG Lihang，ZHANG Weigong，GONG Zongyang，et al.Developments of Delta-like parallel manipulators-a review［J］.Robot，2014，36（3）：375-384.
WANG Y，YU J J，XU P.Fast forward kinematics algorithm for real-time and high-precision control of the 3-RPS parallel mechanism［J］.Frontiers of Mechanical Engineering，2018，13（3）：368-375.
王启明，苏建，张益瑞，等.一种冗余6-DOF并联机构的结构特性与运动学分析［J］.机械工程学报，2017，53（18）：121-130.
WANG Qiming，SU Jian，ZHANG Yirui，et al. Structure characteristics and kinematic analysis of redundant 6-DOF parallel mechanism［J］.Journal of Mechanical Engineeering，2017，53（18）：121-130.
郭玉，赵新华，李彬.一种过约束3自由度并联机构的位置正解研究［J］.天津理工大学学报，2012，28（2）：20-22.
GUO Yu，ZHAO Xinhua，LI Bin. Forward position analysis of an over-constrained 3-DOF parallel mechanism［J］.Journal of Tianjin University of Technology，2012，28（2）：20-22.
杨辉，郝丽娜，项超群.并联机构正运动学AWPSO-SM求解算法［J］.农业机械学报，2017，48（1）：346-352.
YANG Hui，HAO Li′na，XIANG Chaoqun.AWPSO-SM algorithm for parallel mechanism forward kinematics［J］.Transactions of the Chinese Society for Agricultural Machinery，2017，48（1）：346-352.
PUGLISI L J，SALTAREN R J，REY G，et al.Design and kinematic analysis of 3PSS-1S wrist for needle insertion guidance［J］.Robotics and Autonomous Systems，2012，61（5）：417-427.
LI T Y，ZHAO D X，HAN F Y，et al. A fast forward kinematics algorithm for 3-PRS parallel mechanism［J］.Advanced Materials Research，2012，1670：303-308.
王启明，苏建，隋振，等.一种新型冗余驱动并联机构位姿正解研究［J］.机械工程学报，2019，55（9）：40-47.
WANG Qiming，SU Jian，SUI Zhen，et al.Research on forward kinematics of a new type of redundant actuation parallel mechanism［J］.Journal of Mechanical Engineering，2019，55（9）：40-47.
耿明超，赵铁石，王唱，等.基于拟Newton法的并联机构位置正解［J］.机械工程学报，2015，51（9）：28-36.
GENG Mingchao，ZHAO Tieshi，WANG Chang，et al.Direct position analysis of parallel mechanism based Newton method［J］.Journal of Mechanical Engineering，2015，51（9）：28-36.
RAHMANI A，GHANBARI A.Neural network solutions for forward kinematics analysis of 2-（6UPS） manipulator［J］.Applied Mechanics and Materials，2014，624：424-428.
DEHGHANI M，AHMADI M，KHAYATIAN A，et al.Neural network solution for forward kinematics problem of HEXA parallel robot［C］//Proceedings of the 2008 American Control Conference，June 11-13，2008，Washington，USA，IEEE，2008：4214-4219.
下转第134页
0
浏览量
3
下载量
0
CSCD
- 网络PDF下载
- Meta-XML下载
- BibTeX下载
- Endnote下载
- RefMan 下载
- NoteExpress下载
- NoteFirst下载
关联资源
相关文章
相关作者
相关机构
- 技术支持由北京北大方正电子有限公司提供 豫ICP备05013835号-5
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies