Fuzzy Controller Design by Clustering-Aided Ant Colony Optimization

This paper proposes a Clustering-aided Ant Colony Optimization (ACO) algorithm (CACO) for fuzzy controller design. The objective of CACO is to improve both the design efficiency of a fuzzy controllers and its performance. In CACO, the number of rules in CACO is created on-line by a newly proposed fuzzy clustering. Once a new rule is generated, the consequence is selected from a list of candidate control actions by ACO. In ACO, the tour of an ant is regarded as a combination of consequent actions selected from every rule. Searching for the best one among all consequence combinations involves using a proposed pheromone matrix and a new heuristic value assignment method. To verify the performance of CACO on fuzzy control, simulations on water bath temperature control are performed.