Coupled electromagnetic/thermal machine design optimization based on finite element analysis with application of artificial neural network

Comprehensive optimization of an electrical machine design requires that its electromagnetic (EM) and thermal performance must be optimized simultaneously since electric machines are heavily constrained by thermal limits. The approach presented in this paper is built around a coupled EM/thermal model that uses finite element analysis to efficiently identify the maximum current density for a given machine during steady-state operation. This coupled model is then integrated into an iterative machine design optimization program. An artificial neural network (ANN) that is capable of effectively characterizing input/output relationships for nonlinear multivariable functions is incorporated into the optimization program, resulting in a significant reduction of the total computation time. Results are presented for application of this software to optimize the design of a 30 kW (cont.) fractional-slot concentrated winding (FSCW) surface permanent magnet (SPM) machine for high torque density. The optimal designs found with the coupled EM/thermal optimization exhibit valuable performance improvements compared to designs found with EM-only optimization.