Title :
An H∞ design approach for neural net-based control schemes
Author :
Lin, Chun-Liang ; Lin, Tsai-Yuan
Author_Institution :
Inst. of Autom. Control Eng., Feng Chia Univ., Taichung, Taiwan
fDate :
10/1/2001 12:00:00 AM
Abstract :
Presents an H∞ 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∞ control is specified to eliminate the effect of approximation errors and external disturbances to achieve the desired performance. It is shown that finding the permissible control gain matrices can be transformed to a standard linear matrix inequality problem and solved using the convex optimization method
Keywords :
H∞ control; matrix algebra; multilayer perceptrons; neurocontrollers; nonlinear control systems; optimisation; robust control; state feedback; H∞ design approach; approximation errors; convex optimization method; external disturbances; linear differential inclusion model; multilayer perceptrons; neural net-based control schemes; nonlinear systems; permissible control gain matrices; standard linear matrix inequality problem; state feedback control law; Automatic control; Control design; Councils; Equations; Linear feedback control systems; Linear matrix inequalities; Multi-layer neural network; Multilayer perceptrons; Neural networks; State feedback;
Journal_Title :
Automatic Control, IEEE Transactions on
