Combined Random Forest and Genetic Algorithm for Optimal Design of PMa-SynRM for Electric Vehicles

This paper proposes a method combining random forest technique (RF) and genetic algorithm (GA) for optimal design of traction motors for electric vehicles (EVs). The target motor is the permanent magnet assistant synchronous re-luctance Motor (PMa-SynRM) and the design goal is increasing the average torque and efficiency and reducing torque ripple and the total harmonic distortion of line-to-line back elec-tromotive force. The prediction accuracy of the RF was im-proved through hyperparameter tuning and verified through several test functions. The applicability of the proposed method is verified by deriving the optimal design of PMa-SynRM for EVs and improving the target motor performance.