Optimization design of special induction motors using improved intelligent simulated annealing algorithm

Improvements on an intelligent simulated annealing (ISA) algorithm for the optimal design of electromagnetic devices is investigated in this paper. By using a fuzzy inference method, the ISA can not only reject infeasible design schemes before design calculation, but can also circumscribe the whereabouts of the global optimum and automatically narrow the search scope. In case of making improper decisions in ISA searching, a criterion of recognizing error judgment is developed. The algorithm is applied to the optimal design of induction motors used in electric locomotives, and satisfactory results are achieved.