Application of soft computing techniques to induction motor design

Purpose - The purpose of this paper is to present a comparative study of the various soft computing techniques and their application to optimum design of three-phase induction motor design. Design/methodology/approach - The need for energy conservation is increasing the requirements for increased efficiency levels of induction motor. It is therefore important to optimize the efficiency of induction motor in order to obtain significant energy savings. To optimize the efficiency, design of the induction motor has to be chosen appropriately. In this paper, computational intelligence techniques such as artificial neural network, fuzzy logic, genetic algorithm, differential evolution, evolutionary programming, particle swarm optimization, simulated annealing approach, radial basis function, and hybrid approach are applied to solve the induction motor design optimization problem. Findings - These methods are tested on two sample motors and the results are compared and validated against the conventional Modified Hooke-Jeeves design results and the effectiveness of each proposed method has also been illustrated in detail. Originality/value - This comparison will be highly useful for the design engineers in selecting the best method for obtaining the optimal dimensions of three-phase induction motor.