Interior permanent magnet synchronous motors are becoming increasingly popular as traction motors in environmentally friendly vehicles. These motors, which offer a wide range of design options, require time-consuming finite element analysis to verify their performance, thereby extending design times. To address this problem, we propose a deep learning model that can accurately predict the iron loss characteristics of different rotor topologies under various speed and current conditions, resulting in an automatic design system for the IPMSM rotor core. Using this system, the computation time for efficiency maps is reduced to less than 1/3000 of the time required for finite element analysis. The system also shows efficiency optimization results similar to the best results of previous research, while reducing the computational time for optimization by one or two orders of magnitude.

The optimal design of interior permanent magnet synchronous motors requires a long time because finite element analysis (FEA) is performed repeatedly. To solve this problem, many researchers have used artificial intelligence to construct a prediction model that can replace FEA. However, because the training data are generated by FEA, it takes a very long time to obtain a sufficient amount of data, making it impossible to train a large-scale prediction model. Here, we propose a method for generating a large amount of data from a small number of FEA results using machine learning. An automatic design system with a deep generative model and a convolutional neural network is then constructed. With its sufficient data, the proposed system can handle three topologies and three motor parameters in a wide range of current vector regions. The proposed system was applied to multi-objective optimization design, with the optimization completed in 13-15 seconds.