SCI和EI收录∣中国化工学会会刊

›› 2009, Vol. 17 ›› Issue (3): 454-459.

• PROCESS SYSTEMS ENGINEERING • Previous Articles     Next Articles

Modeling and Control of Nonlinear Discrete-time Systems Based on Compound Neural Networks

ZHANG Yan1, LIANG Xiuxia1, YANG Peng1, CHEN Zengqiang2, YUAN Zhuzhi2   

  1. 1. Department of Automation, Hebei University of Technology, Tianjin 300130, China;
    2. Department of Automation, Nankai University, Tianjin 300071, China
  • Received:2008-06-24 Revised:2009-03-20 Online:2009-06-28 Published:2009-06-28
  • Supported by:
    Supported by the National Natural Science Foundation of China (60575009, 60574036)

Modeling and Control of Nonlinear Discrete-time Systems Based on Compound Neural Networks

张燕1, 梁秀霞1, 杨鹏1, 陈增强2, 袁著祉2   

  1. 1. Department of Automation, Hebei University of Technology, Tianjin 300130, China;
    2. Department of Automation, Nankai University, Tianjin 300071, China
  • 通讯作者: ZHANG Yan,E-mail:yzhangzz@yahoo.com.cn
  • 基金资助:
    Supported by the National Natural Science Foundation of China (60575009, 60574036)

Abstract: An adaptive inverse controller for nonliear discrete-time system is proposed in this paper. A compound neural network is constructed to identify the nonlinear system, which includes a linear part to approximate the nonlinear system and a recurrent neural network to minimize the difference between the linear model and the real nonlinear system. Because the current control input is not included in the input vector of recurrent neural network (RNN), the inverse control law can be calculated directly. This scheme can be used in real-time nonlinear single-input single-output (SISO) and multi-input multi-output (MIMO) system control with less computation work. Simulation studies have shown that this scheme is simple and affects good control accuracy and robustness.

Key words: adaptive inverse control, compound neural network, process control, reaction engineering, multi-input multi-output nonlinear system

摘要: An adaptive inverse controller for nonliear discrete-time system is proposed in this paper. A compound neural network is constructed to identify the nonlinear system, which includes a linear part to approximate the nonlinear system and a recurrent neural network to minimize the difference between the linear model and the real nonlinear system. Because the current control input is not included in the input vector of recurrent neural network (RNN), the inverse control law can be calculated directly. This scheme can be used in real-time nonlinear single-input single-output (SISO) and multi-input multi-output (MIMO) system control with less computation work. Simulation studies have shown that this scheme is simple and affects good control accuracy and robustness.

关键词: adaptive inverse control, compound neural network, process control, reaction engineering, multi-input multi-output nonlinear system