Fine control of monotonic systems using a global self-learning adaptive fuzzy controller

The goal of this paper is to achieve real time control of a monotonic system which, in general, may be non-linear and whose differential equations are unknown. We assume that there is no model of the plant available so there cannot be any off-line pre-training of the main controller parameters. We propose a both adaptive and self-learning algorithm capable of starting from a "void" fuzzy controller and, in real time, optimizing the fuzzy controller\´s rules (both antecedents and consequents) in order to translate the state of the plant to the desired value in the shortest possible time.