Optimisation of reverse salient rotor for interior permanent magnet synchronous motor and experimental validation

The prosperous development of electric vehicles has promoted the application of interior permanent magnet synchronous motors (IPMSMs). The flux-intensifying IPMSM has attracted more attention due to its high power-density and better flux-weakening performance. However, the optimisation efficiency and motor performance require further study in the actual optimisation design. To this end, this study is to optimise the electromagnetic field structure of motor rotors with the back propagation neural networks (BPNN) and multi-objective optimisation methods. Concretely, dimensional parameters of an initial motor are extracted as optimisation variables. Then, the BPNN are utilised to stimulate the motor performance obtained with finite element methods (FEM). With the trained BPNN, FEM tools are replaced in the subsequent optimisation process, which alleviates the computational burden. Besides, to address the problem of multi-objective optimisation with inequality constraints, the sequential unconstrained minimisation technique is incorporated into the non-dominated sorting genetic algorithm to obtain the Pareto frontier. Finally, the optimal design point is selected from the Pareto frontier. The simulation and experiment have been implemented to verify the superiority of the optimised rotor structure. Generally, this study has laid the foundation of the following motor optimisation with the higher executability and lower computational burden.