An adaptive response surface method combined with (1+λ) evolution algorithm and its application to optimal design of electromagnetic devices

This paper presents a global optimization algorithm combining an adaptive response surface approximation of the objective function and (1+λ) evolution algorithm. In the adaptive approximation, an optimal Latin hypercube sampling strategy based on multi-objective Pareto optimization is developed to obtain the sampling data in the design variable space, and multiquadric radial basis function is employed to construct the response surface. The proposed method is tested and applied to the optimal design of permanent magnet linear synchronous motors.