A kind of real-time stable self-learning fuzzy neural network (FNN) co
ntrol system is proposed in this paper. The control system is composed
of two parts: (1) A FNN controller which use genetic algorithm (GA) t
o search optimal fuzzy rules and membership functions for the unknown
controlled plant; (2) A supervisor which can guarantee the stability o
f the control system during the real-time learning stage, since the GA
has some random property which may cause control system unstable. The
approach proposed in this paper combine a priori knowledge of designe
r and the learning ability of FNN to achieve optimal fuzzy control for
an unknown plant in real-time. The efficiency of the approach is veri
fied by computer simulation. (C) 1998 Elsevier Science B.V. All rights
reserved.