FIREFLY ALGORITHM IMPROVEMENT WITH APPLICATION TO INDUCTION MACHINE PARAMETERS IDENTIFICATION

Firefly algorithm is one of a nature-inspired optimization algorithm. It was based on the behaviour of tropical fireflies. In the original version, every firefly movement is based on the brightness of the other one. In this paper, we have introduced an improvement of the original firefly algorithm in order to intensify the search in the closest area and also to increase the ability of finding the quasi optimal solution. To enhance firefly's movement, it is proposed to orient firefly's movement to the global centroid of the swarm if there was not any better location around them. Firstly, the proposed algorithm was tested on some standard functions that have ever used for testing the optimization algorithms. Secondly, it was applied to estimate simultaneously the electrical and mechanical parameters of a three-phase induction machine based only on the starting current and the corresponding phase voltage. The results show the superiority of the proposed algorithm versus the original firefly algorithm.