Neural Network Control of Smart Materials with Hysteresis and Creep

摘要：

A model of smart materials with hysteresis and creep has been built in this paper with Prandtle-Ishlinskii (PI) operator. With the model proposed, a radial basis function (RBF) neural network based adaptive PID control scheme for systems with unknown hysteresis nonlinearity is developed. The control scheme is based on two different RBF neural networks; one is used to identify the system model, and the other the controller. In order to accelerate the learning rate of the neural network, we have used a generalized recursive least square (GRLS) learning algorithm to train the identification network. Furthermore, a steepest descent algorithm is introduced here to adjust the parameters of the control network and the convergence criterion is also proved in this paper.

关键词： PI operator RBF network GRLS algorithm.

作者: Chen Jie Ma Tao Chen Wenjie Deng Fang

作者单位: Department of Automatic Control,School of Information Science and Technology,Beijing Institute of Technology,Beijing 100081,China;Education Ministry Key Laboratory of Complex System Intelligent Control and Decision,Beijing Institute of Technology,Beijing

会议类型: 国际会议

会议名称: 2008高等智能国际会议(2008 International Conference on Advanced Intelligence)

会议地点: 北京

会议语种:英文

在线出版日期: 2008-10-18（万方平台首次上网日期，不代表论文的发表时间）