一种新型冗余驱动并联机构位姿正解研究

doi:10.3901/JME.2019.09.040

机械工程学报 ›› 2019, Vol. 55 ›› Issue (9): 40-47.doi: 10.3901/JME.2019.09.040

一种新型冗余驱动并联机构位姿正解研究

王启明¹, 苏建², 隋振³, 林慧英², 赵礼辉¹

1. 上海理工大学机械工程学院上海 200093;
2. 吉林大学交通学院长春 130022;
3. 吉林大学通信工程学院长春 130022

收稿日期:2018-04-19 修回日期:2018-06-14 出版日期:2019-05-05 发布日期:2019-05-05
通讯作者: 苏建(通信作者),男,1954年出生,博士,教授,博士研究生导师。主要研究方向为车辆智能监测诊断。E-mail:wang.qiming2008@163.com
作者简介:王启明,女,1991年出生,讲师。主要研究方向为车辆智能监测。E-mail:726571304@qq.com
基金资助:
国家自然科学基金资助项目（51575232，51705322）。

Research on Forward Kinematics of a New Type of Redundant Actuation Parallel Mechanism

WANG Qiming¹, SU Jian², SUI Zhen³, LIN Huiying², ZHAO Lihui¹

1. School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200093;
2. College of Transportation, Jilin University, Changchun 130022;
3. College of Communication Engineering, Jilin University, Changchun 130022

Received:2018-04-19 Revised:2018-06-14 Online:2019-05-05 Published:2019-05-05

摘要/Abstract

摘要： 针对冗余驱动并联机构建立的位姿正解方程组存在冗余，而采用的Newton-Raphson迭代法位姿正解时对迭代初值选取较为敏感且计算速度较慢的问题，提出基于Levenberg-Marquardt （L-M）算法的改进BP神经网络模型与基于改进的Genetic Algorithm优化BP （GA-BP）神经网络模型，前者可在线计算满足实时性要求，后者可离线训练满足较高精度要求；解决了新型冗余驱动并联机构位姿正解问题。并与常用的基于拟牛顿算法（BFGS）和基于量化共轭梯度算法（SCG）的神经网络模型进行对比分析。结果表明，GA-BP模型和L-M算法模型在误差性能分析上明显优于BFGS拟牛顿与SCG算法模型；L-M算法在计算精度稍逊于GA-BP模型，而GA-BP模型迭代时间较长，因此更适用于离线高精度位姿正解。

关键词: GA-BP, L-M算法, Newton-Raphson迭代法, 混合策略, 冗余驱动并联机构, 位姿正解

Abstract: According to the equation of redundancy pose of parallel mechanism establishment of redundant actuation, selection problem is sensitive to the initial value of iteration and the calculation speed is slower and the use of the Newton-Raphson iterative method is proposed, which can satisfy the real-time requirements of the online calculation of Levenberg-Marquardt algorithm (L-M algorithm) improved BP neural network model and off-line training can meet the optimization BP neural network model of Genetic Algorithm based on improved high precision (GA-BP), to solve the new redundancy driven parallel mechanism of initial positive solutions of pose prediction problems. Compared with the commonly used quasi Newton algorithm (BFGS) and the quantitative conjugate gradient algorithm (SCG) based neural network model. The results show that the GA-BP model and the L-M algorithm model in error performance analysis is obviously superior to that of BFGS and SCG quasi Newton algorithm model; L-M algorithm in terms of accuracy slightly inferior to the GA-BP model, GA-BP model and the iteration time is longer, so it is suitable for the high precision posture is offline.

Key words: forward kinematics, GA-BP, hybrid strategy, Levenberg-Marquardt, Newton-Raphson, redundant actuation parallel mechanism

中图分类号:

U279

王启明, 苏建, 隋振, 林慧英, 赵礼辉. 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, LIN Huiying, ZHAO Lihui. Research on Forward Kinematics of a New Type of Redundant Actuation Parallel Mechanism[J]. Journal of Mechanical Engineering, 2019, 55(9): 40-47.

参考文献

[1] 苏建,王金田,刘玉梅,等. 一种龙门框架式轨道车辆转向架参数测定试验台:中国,CN103048149A[P]. 2013-04-17. SU Jian,WANG Jintian,LIU Yumei,et al. A gantry frame-type rail vehicle bogie parameter test bench:China,CN103048149A[P]. 2013-04-17.
[2] ABBASNEJAD G,DANIALI H M,FATHI A. Closed form solution for direct kinematics of a 4PUS +1PS parallel manipulator[J]. Scientialranica,2012,19(2):320-326.
[3] 王秀刚,苏建,曹晓宁. 基于旋转矩阵正交性的转向架6自由度平台位姿正解解算[J]. 吉林大学学报:工学版,2013,43(5):1241-1246. WANG Xiugang,SU Jian,CAO Xiaoning. Forward kinematics solution of bogie 6-DOF platform based on the orthogonality of rotation matrix[J]. Journal of Jilin University(Engineering and Technology Edition),2013,43(5):1241-1246.
[4] 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. Position positive solution of parallel mechanism based on quasi Newton method[J]. Journal of Mechanical Engineering,2015,51(9):28-36.
[5] YANG C,ZHENG S,JIN J,et al. Forward kinematics analysis of parallel manipulator using modified global Newton-Raphson method[J]. Journal of Central South University of Technology,2010,17:1264-1270.
[6] GHASEMI A,EGHTESAD M,FARID M. Neural network solution for forward kinematics problem of cable robots[J]. Journal of Intelligent & Robotic Systems,2010,60(2):201-215.
[7] 张代磊,黄大年,张冲. 基于遗传算法优化的BP神经网络在密度界面反演中的应用[J]. 吉林大学学报(地球科学版),2017,47(2):580-588. ZHANG Dailei,HUANG Danian,ZHANG Chong. Application of BP neural network optimization based on Genetic Algorithm in density interface inversion[J]. Journal of Jilin University (Earth Science Edition),2017,47(2):580-588.
[8] 杨永刚,赵杰,刘玉斌. 6-PRRS并联机器人正运动学求解[J]. 吉林大学学报(工学版),2008,38(3):731-734. YANG Yonggang,ZHAO Jie,LIU Yubin. Solving forward kinematics of 6-PRRS parallel robot[J]. Journal of Jilin University (Engineering and Technology Edition),2008,38(3):731-734.
[9] 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. Structural characteristics and kinematic analysis of a redundant 6-DOF parallel mechanism[J]. Journal of Mechanical Engineering,2017,53(18):121-130.
[10] 沈惠平,尹洪波,王振. 基于拓扑结构分析的求解6-SPS并联机构位置正解的研究[J]. 机械工程学报,2013,49(21):70-80. SHEN Huiping,YIN Hongbo,WANG Zhen. Research on forward position solutions for 6-SPS parallel mechanisms based on topology structure analysis[J]. Journal of Mechanical Engineering,2013,49(21):70-80.
[11] 杨廷力,刘安心,罗玉峰,等. 机器人机构拓扑结构设计[M]. 北京:科学出版社,2012. YANG Tingli,LIU Anxin,LUO Yufeng,et al. Theory and application of robot mechanism topology[M]. Beijing:Science Press,2012.
[12] 尹洪波,沈惠平,邓嘉鸣. 球面并联机构的结构降耦及其位置正解求解[J]. 机械科学与技术,2015,34(1):51-55. YIN Hongbo,SHEN Huiping,DENG Jiaming. The reducing in structure coupling and the forward position analysis for the spherical parallel mechanisms[J]. Mechanical Science and Technology for Aerospace Engineering,2015,34(1):51-55.
[13] 张彦斌,吴鑫,刘宏昭. 无耦合3自由度并联机构的设计与分析[J]. 农业机械学报,2008,39(8):208-210. ZHANG Yanbin,WU Xin,LIU Hongzhao. Design and analysis of a 3-DOF non-coupled parallel manipulator[J]. Transactions of the Chinese Society for Agricultural Machinery,2008,39(8):208-210.
[14] 张彦斌,刘宏昭,吴鑫,等. 2T1R弱耦合并联机构的运动学和奇异性分析[J]. 农业机械学报,2008,39(4):132-136. ZHANG Yanbin,LIU Hongzhao,WU Xin. Kinematics and singularity analysis of a novel weakly-coupled parallel manipulator[J]. Transactions of the Chinese Society for Agricultural Machinery,2008,39(4):132-136.
[15] 沈花玉,王兆霞,高成耀,等. BP神经网络隐含层单元数的确定[J]. 天津理工大学学报,2008,24(5):13-15. SHEN Huayu,WANG Zhaoxia,GAO Chengyao,et al. The determination of the number of hidden layer units in BP neural network[J]. Journal of Tianjin University of Technology,2008,24(5):13-15.

一种新型冗余驱动并联机构位姿正解研究

Research on Forward Kinematics of a New Type of Redundant Actuation Parallel Mechanism

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

[1]	王启明, 苏建, 张益瑞, 吕志超, 林慧英, 徐观. 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.
[2]	张秀玲;刘宏民. 板形控制的传递矩阵方法[J]. , 2003, 39(11): 100-103.