Combined Machine Learning and Differential Evolution for Optimal Design of Electric Aircraft Propulsion Motors

Electric aircraft propulsion requires highly efficient and power-dense fault-tolerant electric motors optimized for specific flight profile operation. State-of-the-art design of electric motors involves substantial computational resources and combines electromagnetic finite element analysis (FEA) and optimization techniques. This paper proposes a new approach using a physics-based machine learning (ML) multi-input univariate meta-model trained on FEA and differential evolution (DE) optimization results to predict electromagnetic torque output. Hundreds of individual designs, generated through multiple generations of a DE algorithm, are analyzed by 3D FEA to create a database, which is then employed for the training and satisfactory validation of the ML model. The coreless axial flux permanent magnet (CAFPM) machine topology considered for an example study typically necessitates intensive 3D FEA simulation due to its specific geometry, although it does not experience the non-linear saturation associated with ferromagnetic core materials. The hybrid ML-DE model is satisfactorily validated with an R² value of 0.97 and normalized root mean squared error (NRMSE) of less than 0.05. The relative merits of the newly proposed combined ML-DE optimization are discussed, especially in terms of low error and the potential for overall computational time minimization.