Optimisation of electromagnetic devices using computational intelligence techniques

Much research has been expended on artificial intelligence techniques, such as neural networks, fuzzy logic, genetic algorithms, evolutionary strategies and simulated annealing amongst others However, the recent realization of the limits of each of these techniques or conversely the strength of a composite approach has prompted enthusiasm and growing research into combined strategies featuring several methods together [1]-[2] This emergent field of computational intelligence aims to exploit the relative merits of individual techniques to create a new class of composite tool This work investigates the use of computational intelligence techniques, i.e. neurofuzzy systems and genetic algorithms, for the optimization of electromagnetic devices The results of a seven variable loud speaker problem are discussed