Title :
Direct neural control system: nonlinear extension of adaptive control
Author :
Yuan, M. ; Poo, A.N. ; Hong, G.S.
Author_Institution :
Dept. of Mech. & Production Eng., Nat. Univ. of Singapore, Singapore
fDate :
11/1/1995 12:00:00 AM
Abstract :
The methodology of design of a conventional model-reference-adaptive-control is extended to design a direct neural for a class of nonlinear system with structural uncertainty. A structured feedforward neural network, a Sigmoid-linear network, is used as the controller, which can be interpreted as a nonlinear extension of the conventional adaptive control. Without a specific pretraining stage, the weights of the neural network are adjusted online to minimise the error between the plant output and the desired output signal, according to a learning law derived in light of gradient-descent method. The local stability can be achieved provided that proper conditions are satisfied for the system. Simulation studies are carried out for linear and nonlinear plants, respectively, and verify the applicability of the proposed control strategy
Keywords :
adaptive control; control system synthesis; feedforward neural nets; linear systems; model reference adaptive control systems; neurocontrollers; nonlinear systems; stability; Sigmoid-linear network; direct neural control system; feedforward neural network; gradient-descent method; linear systems; model reference adaptive control; nonlinear systems; stability; structural uncertainty;
Journal_Title :
Control Theory and Applications, IEE Proceedings -
DOI :
10.1049/ip-cta:19952122