A novel data based control method based upon neural network and simultaneous perturbation stochastic approximation

被引:11
作者
Dong, Na [1 ]
Chen, Zengqiang [1 ]
机构
[1] Nankai Univ, Dept Automat, Tianjin 300071, Peoples R China
基金
高等学校博士学科点专项科研基金;
关键词
Data based control; Model-free control; SPSA; Neural network; Non-linear tracking problem; ADAPTIVE-CONTROL; SYSTEMS;
D O I
10.1007/s11071-011-0039-x
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
A novel data based control method is proposed by modifying the cost function of a model-free control method based on Simultaneous Perturbation Stochastic Approximation (SPSA). The controller is constructed through use of a Function Approximator (FA), which is fixed as a neural network here. In the novel approach, the ability of the controller has been greatly improved. At last, the proposed modified control method is applied to solve non-linear tracking problems. Simulation comparison tests were done on typical non-linear plants, through which, the effectiveness of the novel data based control method is fully illustrated.
引用
收藏
页码:957 / 963
页数:7
相关论文
共 14 条
[1]   Dynamic structure neural networks for stable adaptive control of nonlinear systems [J].
Fabri, S ;
Kadirkamanathan, V .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (05) :1151-1167
[2]   Discrete-time model reference adaptive control of nonlinear dynamical systems using neural networks [J].
Jagannathan, S ;
Lewis, FL ;
Pastravanu, O .
INTERNATIONAL JOURNAL OF CONTROL, 1996, 64 (02) :217-239
[3]   Theory and development of higher-order CMAC neural networks [J].
Lane, Stephen H. ;
Handelman, David A. ;
Gelfand, Jack J. .
IEEE Control Systems Magazine, 1992, 12 (02) :23-30
[4]   Contro of nonlinear dynamical systems using neural networks .2. Observability, identification, and control [J].
Levin, AU ;
Narendra, KS .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (01) :30-42
[5]   CONTROL OF NONLINEAR DYNAMIC-SYSTEMS USING NEURAL NETWORKS - CONTROLLABILITY AND STABILIZATION [J].
LEVIN, AU ;
NARENDRA, KS .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1993, 4 (02) :192-206
[6]  
Li X., 2002, ASIAN J CONTROL, V4, P231
[7]  
Narendra K. S., 1991, MAN WORKSH NEUR NETW
[8]  
Rudin W., 1984, PRINCIPLES MATH ANAL, p[146, 176]
[9]   GAUSSIAN NETWORKS FOR DIRECT ADAPTIVE-CONTROL [J].
SANNER, RM ;
SLOTINE, JJE .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (06) :837-863
[10]  
Spall J. C., 1993, P 32 IEEE C DEC CONT