力觉临场感系统中操作环境动力学的小波神经网络模型  

Research on the Dynamic Model of Operating Environment in Force Telepresence System

作　　者：俞阿龙[1] 黄惟一[2] 

机构地区：[1]淮阴师范学院物理系,淮安223001 [2]东南大学仪器科学与工程系,南京210096

出　　处：《仪器仪表学报》2006年第1期14-18,共5页Chinese Journal of Scientific Instrument

基　　金：江苏省高等学校自然科学基金(04KJD140033)资助项目。

摘　　要：在力觉临场感系统中机器人操作环境经常是非线性的和未知的。为使本地操作者了解环境特性,需对操作环境进行建模。为此,进一步研究力觉临场感系统中机器人操作环境动力学模型,提出一种新的基于小波神经网络的环境非线性动力学模型的建立方法,分析网络的拓扑结构,给出网络参数训练和初始化方法。采用引入动量项的最速下降法训练网络权值、尺度因子和平移因子,将小波网络参数的初始化与小波类型、小波时频参数和学习样本等联系起来。结果表明,采用小波神经网络的力觉临场感系统中操作环境模型优于同等规模的BP网络,具有训练方法收敛速度更快、非线性逼近能力更强及建模精度更高等优点。The operating environment in force telepresence system is often nonlinear and unknown. In order to enable local operator to sense the environment, it is necessary to building model. For this reason, the dynamic model of operating environment is further researched and a kind of new building method of dynamic model of operating environment in force telepresence system based on wavelet neural network （WNN） is presented. Geometrical structure of the network is analyzed and the methods of network parameters training and initialization are given. The weights of network ,scale factor and displacement factor are studied by the steepest descent method, and the network parameters initialization integrates with the wavelet type, time frequency parameters of wavelet and the training samples. The results show that the proposed wavelet neural network provides better approximation ability and higher precision and faster training speed than the BP neural network when used in building model of operating environment in force telepresence system.

关 键 词：机器人 力觉临场感 操作环境 小波神经网络 建模 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]