面向工作空间的Stewart型并联机床结构参数优化

Workspace-Oriented Methodology for Optimizing Stewart-Platform-Based Machine Tool

以满足给定最小可达章动角球形主工作空间为条件 ,操作灵活度最优为目标 ,对 Stewart型并联机床的通用模型进行了结构参数优化。在最小可达章动角球形主工作空间的确定上 ,采用了随机抽样并对样本进行工作空间边界校验的方法。基于目标函数无法用设计变量显式表示且设计变量较多的特点 ,优化方法采用了遗传算法 ,其适应度函数用训练后的 BP神经网络来逼近。结果表明 ,该方法效果良好。

In this paper, the spherical position workspace is resolved using statistic theory. To design a Stewart type parallel machine tool which fulfill the given spherical position workspace and have the best dexterity, a genetic algorithm is used. Because the calculation of the fitness function is complex, back-propagation neural network is used to approach the fitness function. The results show that this method has good precision and computing efficiency.