摘要
根据空间三自由度并联机构和X-Y二自由度运动平台组成的新型混联机床构型的结构特点,提出两种求解位置正解的方法:一是以刀具所在动平台三个球铰之间的距离为约束条件,提出一种解析方法解出位置正解;二是提出多层前向神经网络求解机构位置正解的方法,此法将位置逆解结果作为训练样本,采用levenberg-marquardt算法,实现了机构从关节变量空间到工作空间的非线性映射,从而求得位置正解。结果表明:与第一种方法相比,神经网络方法的计算精度高,没有复杂公式推导和大量的计算,计算过程简洁,耗时少,可应用于该机床的工作空间控制或是求解机床的工作空间。
Based on the structure of the Hybrid Kinematics Machine (HKM) which is composed of a 3-DOF parallel kinematics mechanism and a 2-DOF XY table, two effective methods for the forward kinematic solution were presented. The first method is an analytical method, which takes the distance between the three spherical hinges on the moving platform as the constraint conditions to get the forward kinematic solution. The second is a multi-layer forward neural network based method, in which the inverse solution result is regarded as training samples to train the ANN using LM (levenberg-marquardt) algorithm. A nonlinear mapping of the mechanism from the joint variables space to work variables space is obtained. The trained ANN can be adopted to acquire the result of the forward kinematic solution. The result shows that the ANN based method has a better computational accuracy with less complicated formula and calculations, compared with the first method. Moreover, the calculation process is comparatively simple and less time consuming. It offers a promising way to solve the forward kinematic solution to control or analyze the workspace of the HKM.
出处
《机械设计与研究》
CSCD
北大核心
2016年第5期10-13,共4页
Machine Design And Research
基金
国家自然科学基金(51275486)
山西省国际科技合作(2015081016)资助项目
山西省回国留学人员科研资助项目(2014050)
关键词
混联机床
位置正解
解析方法
神经网络
hybrid kinematics machine
forward kinematic solution
parse methods
BP neural network