INVERSE MODEL IDENTIFICATION OF NONLINEAR DYNAMIC SYSTEM USING NEURAL NETWORK

摘要：

This paper investigates the inverse identification of the dynamics nonlinear plants using improved backpropagation (BPNN) neural network.The structure and algorithm of inverse model identification, which is based on improved BPNN, are presented.Essential point of the proposed approach is to make use of the direct inverse learning scheme to achieve simple and accurate inverse system identification.This approach can easily be extended to the area of on-line adaptive control.Simulation results show that the proposed method is efficacious used to identify nonlinear dynamic system, inverse models can be satisfactorily achieved, and the accuracy, the response speed and static error can be evidently improved.

关键词： Inverse model identification BP neural network Nonlinear system Simulation

作者: MING-GUANG ZHANG

作者单位: School of Electrical and Information Engineering, Lanzhou university of Technology, Lanzhou 730050, China P.R.

会议类型: 国际会议

会议名称: 2007 International Conference on Machine Learning and Cybernetics(IEEE第六届机器学习与控制论国际会议)

会议地点: 香港

会议语种:英文

页码: 2451-2455

在线出版日期: 2007-08-19（万方平台首次上网日期，不代表论文的发表时间）