Designing a hierarchical fuzzy logic controller using differential evolution

Abstract

In conventional fuzzy logic controllers, the computational complexity increases with the dimensions of the system variables; the number of rules increases exponentially as the number of system variables increases, Hierarchical fuzzy logic controllers have been introduced to reduce the number of rules to a linear function of system variables. However the use of hierarchical fuzzy logic controllers raises new issues in the automatic design of controllers, namely the coordination of outputs of sub-controllers at lower levels of the hierarchy. In this paper, we describe a method for automating the design of hierarchical fuzzy logic controllers using an Evolutionary Algorithm called Differential Evolution. We demonstrate the applicability of our method by developing a two-stage hierarchical fuzzy logic controller for controlling a cart-pole with four state variables.