An H∞ design approach for neural net-based control schemes

被引：62
作者：
Lin, CL [1 ]
Lin, TY [1 ]
机构：
[1] Feng Chia Univ, Inst Automat Control Engn, Taichung 40724, Taiwan
来源：
IEEE TRANSACTIONS ON AUTOMATIC CONTROL | 2001年 / 46卷 / 10期
关键词：
H-infinity control; linear matrix inequality (LMI); neural network; robustness; stability;
D O I：
10.1109/9.956056
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
This note presents an H-infinity design approach for a neural net-based control scheme. In this scheme, a class of nonlinear systems is approximated by two multilayer perceptrons. The neural networks are piecewisely interpolated to generate a linear differential inclusion model. Based on this model, a state feedback control law is designed. The H-infinity control is specified to eliminate the effect of approximation errors and external disturbances to achieve desired performance. It is shown that finding the permissible control gain matrices can be transformed to a standard linear matrix inequality (LMI) problem and solved using the convex optimization method.
引用
收藏
页码：1599 / 1605
页数：7
相关论文
共 14 条
[1]  
Bishop C. M., 1995, NEURAL NETWORKS PATT
[2]  
Boyd S., 1994, LINEAR MATRIX INEQUA, DOI https://doi.org/10.1109/jproc.1998.735454
[3]   ADAPTIVELY CONTROLLING NONLINEAR CONTINUOUS-TIME SYSTEMS USING MULTILAYER NEURAL NETWORKS [J].
CHEN, FC ;
LIU, CC .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1994, 39 (06) :1306-1310
[4]  
Feng ZS, 1999, IEEE T CIRCUITS-I, V46, P1482, DOI 10.1109/81.809550
[5]  
Limanond S, 1998, IEEE T NEURAL NETWOR, V9, P1422, DOI 10.1109/72.728392
[6]   Analysis and design of fuzzy controller and fuzzy observer [J].
Ma, XJ ;
Sun, ZQ ;
He, YY .
IEEE TRANSACTIONS ON FUZZY SYSTEMS, 1998, 6 (01) :41-51
[7]   Stability analysis of dynamic neural control [J].
Poznyak, AS ;
Yu, W ;
Sanchez, EN ;
Perez, JP .
EXPERT SYSTEMS WITH APPLICATIONS, 1998, 14 (1-2) :227-236
[8]  
Rao D. H, 1994, NEURO CONTROL SYSTEM
[9]  
STOORVOGEL AA, 1992, H INFINITY CONTROL P
[10]  
Suykens J. A. K., 1996, ARTIFICIAL NEURAL NE
12