Stable fuzzy controller design employing group improvisation based harmony search algorithm

Abstract

The present paper proposes a group improvisation based variant of harmony search (HS) algorithm, for solving optimization problems, conceptualizing the mutual cooperation of philharmonic orchestra. The proposed conception of meta-heuristic optimization is aimed to bring the effects of local neighborhood topological model (lbest model) to the HS algorithm as found, particularly, in swarm based optimizations. This variant of HS employs a novel cooperative method for generating new solution vectors that enhances the accuracy and convergence rate of harmony search (HS) algorithm. The proposed variant of HS algorithm has been successfully applied to design stable fuzzy controllers, optimizing both its structures and free parameters, so that the designed controller can guarantee desired stability and simultaneously it can provide satisfactory performance with a high degree of automation in the design process. The variant and the original HS algorithm are implemented for two nonlinear benchmark systems in simulation case study and their results demonstrate that the proposed variant outperforms the original HS algorithm.