Nonlinear Design Scaling of Electric Machines Based on Hybrid DE and Meta-Modeling-Application to Synchronous Motors with Combined PM Stator and Reluctance Rotor Excitation

This paper presents an innovative method for nonlinear scaling of electric machines by integrating machine learning (ML)-based meta-modeling with a differential evolution (DE) algorithm. The technique is applied to high-performance combined-excitation synchronous electric motors which exhibit highly nonlinear characteristics, making performance scaling challenging. The proposed approach employs an ML meta-model trained on data obtained from finite element analysis (FEA), utilizing an experimentally validated model for nonlinear scaling and performance prediction at different power ratings. The accuracy of the meta-model in capturing the nonlinear relationships between design parameters and motor performance is first assessed using metrics such as R-squared (R2) and normalized root mean square error (NRMSE) prior to nonlinear scaling. The scaled results are then compared with those obtained from finite element analysis (FEA), demonstrating good correlation within acceptable tolerances. This hybrid ML-DE approach aims to provide a robust and resource-efficient method for electric motor design, optimization, and performance estimation.