A design methodology for an intelligent controller using fuzzylogic and artificial neural networks

摘要

The optimal control of nonlinear time-varying systems,particularly when the mathematical model of the system is unavailable orinexact, is an interesting and difficult control problem. This paperoutlines a methodology for the design of an intelligent controller toperform optimal control of a nonlinear system adaptively, using emergingtechnologies of fuzzy logic (FL) and artificial neural networks (ANN).FL is utilized to incorporate the available knowledge into the controlsystem, and ANN technology is applied to adaptively provide an optimalcontrol strategy based on some performance criteria. The technique istested on a system that consists of a DC motor (a linear time-invariant(LTI) system) and a thermal system (a time-varying nonlinear system).Performance criteria such as tracking accuracy, cost, robustness, areconsidered, and the results are presented in this paper