Conference: 2021 COMPUMAG
Authors: Soo-Hwan Park, Jun-Woo Chin, Sun-Yong Shin, Kyoung-Soo Cha, Myung-Seop Lim
DOI:
This paper proposes a deep transfer learning based sizing process of permanent magnet synchronous motors (PMSMs). The sizing process is necessary to analyze the electromagnetic characteristics according to the major shape parameters during the initial design stage of PMSMs. However, in the case of a pancake type motor with a small shape ratio, the predicted electromagnetic characteristics based on 2-D finite element analysis (FEA) have an error due to the influence of axial leakage flux. Therefore, the axial leakage flux should be considered in the sizing process. The most accurate way to consider the axial leakage flux is to use 3-D FEA, but it has a disadvantage of high computational cost. In this view, we propose a deep transfer learning based surrogate modeling method to reduce computational cost for calculating 3-D FEA based motor parameters. The transfer learning is conducted using a large amount of 2-D FEA based and small amount of 3-D FEA based motor parameters. Using the proposed process, it is possible to accurately predict the motor characteristics according to the size-related variables that satisfies the required specifications. The proposed method was verified through 3-D FEA for pancake type PMSMs, which is highly affected by axial leakage flux.