Nonlinear one-step-ahead control using neural networks: Control strategy and stability design

被引:43
作者
Tan, YH [1 ]
vanCauwenberghe, A [1 ]
机构
[1] STATE UNIV GHENT,AUTOMAT CONTROL LAB,B-9052 GHENT,BELGIUM
关键词
neural networks; predictive control; recursive least squares; stability; nonlinearity;
D O I
10.1016/S0005-1098(96)80006-9
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A nonlinear one-step-ahead control strategy based on a neural network model is proposed for nonlinear SISO processes. The neural network used for controller design is a feedforward network with external recurrent terms. The training of the neural network model is implemented by using a recursive least-squares (RLS)-based algorithm. Considering the case of the nonlinear processes with time delay, the extension of the mentioned neural control scheme to d-step-ahead predictive neural control is proposed to compensate the influence of the time-delay. Then the stability analysis of the neural-network-based one-step-ahead control system is presented based on Lyapunov theory. From the stability investigation, the stability condition for the neural control system is obtained. The method is illustrated with some simulated examples, including the control of a continuous stirred tank reactor (CSTR). Copyright (C) 1996 Elsevier Science Ltd.
引用
收藏
页码:1701 / 1706
页数:6
相关论文
共 20 条
  • [11] IMPROVEMENT OF THE BACKPROPAGATION ALGORITHM FOR TRAINING NEURAL NETWORKS
    LEONARD, J
    KRAMER, MA
    [J]. COMPUTERS & CHEMICAL ENGINEERING, 1990, 14 (03) : 337 - 341
  • [12] Narandre K.S., 1990, IEEE T NEURAL NETWOR, V1, P4
  • [13] PSALTIS D, 1988, IEEE CONTROL SYS APR, P17
  • [14] RAY WH, 1981, 2ND P C CHEM PROC CO, P245
  • [15] LEARNING REPRESENTATIONS BY BACK-PROPAGATING ERRORS
    RUMELHART, DE
    HINTON, GE
    WILLIAMS, RJ
    [J]. NATURE, 1986, 323 (6088) : 533 - 536
  • [16] Rumelhart DE, 1986, PARALLEL DISTRIBUTED, V1, DOI DOI 10.7551/MITPRESS/5236.001.0001
  • [17] Schoukens J., 1991, IDENTIFICATION LINEA
  • [18] Tan Y., 1993, Journal A, V34, P12
  • [19] TAN Y, 1994, P IFAC S SYST ID COP
  • [20] TAN Y, 1994, ADV MODEL BASED PRED, P358