Year: 2025
Type: conference-paper
Abstract: This paper introduces a novel approach for high-performance electric motor design that combines machine learning (ML)-based meta-modeling with a differential evolution (DE) optimization algorithm. The method leverages finite element analysis (FEA) results to train the ML meta-model, enabling efficient design optimization for high-power density cored machines, such as spoke interior permanent magnet motors (IPM), which exhibit complex nonlinearities and saturation effects. This hybrid ML-DE framework seeks to provide an alternative for physics-based electric motor design and optimization, offering significant reductions in computational effort while maintaining accuracy. The meta-model’s accuracy in capturing the nonlinear relationships between design parameters, core losses, and torque is assessed using metrics such as R-squared (R2), normalized root mean square error (NRMSE), and mean absolute percentage error (MAPE), showing promising performance.
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4412030920