Genetic algorithm combined with finite element method for robust design of actuators

Abstract

This paper describes a design optimization procedure based on a genetic algorithm combined with the finite element method. It adopts the concepts of Orthogonal Array for design parameter settings, and Signal-to-Noise Ratio (S/N) for evaluating the individual fitness. Taking advantage of the unique features of genetic algorithms, the robust solution is achieved by a rapid global search. The approach is applied to the robust design problem of a magnet actuator to demonstrate its effectiveness.