Messy genetic algorithm based new learning method for structurally optimized neurofuzzy controllers

The success of a neurofuzzy control system solving any given problem critically depends on the architecture of the network. Various attempts have been made in optimizing its structure using genetic algorithm automated designs. In a regular genetic algorithm, however, a difficulty exists which lies in the encoding of the problem by highly fit gene combinations of a fixed-length. For the structure of the controller to be coded, the required linkage format is not exactly known and the chance of obtaining such a linkage in a random generation of coded chromosomes is slim. This paper presents a new approach to structurally optimized designs of neurofuzzy controllers. Here, we use messy genetic algorithms, whose main characteristic is the variable length of chromosomes, to obtain structurally optimized FLC. Structural optimization is regarded important before neural network based local learning is switched into. The example of a cart-pole balancing problem demonstrates that such an optimal design realizes the potential of nonlinear proportional plus derivative type FLC in dealing with steady-state errors without the need of memberships or rule dimensions of an integral term.