As artificial intelligence emerges as the core engine of the 4th industrial revolution, researches combining deep learning in the field of mechanical engineering are increasing rapidly. It shows that complex mechanical engineering problems that have been solved based on mechanics can be solved more efficiently based on data. In particular, the field of optimal design is based on probability and optimization theory the same as deep learning, so the combination of deep learning is very natural compared to other fields. 
Research on the combination of optimal design and deep learning covers various sub-areas such as topology optimization, parametric design, computer-aided engineering (CAE) simulation, surrogate model, material design, design preference modeling, and generative design.&nbsp; 
&nbsp;Recently, the possibility of development as a design automation technology based on artificial intelligence is increasing through the combination with the generation model of deep learning.&nbsp; 
&nbsp;In this paper, we propose an optimal design method based on deep learning to increase the efficiency of the interior permanent magnet synchronous motor (IPMSM) used in the electric oil pump (EOP). The proposed optimal design method improves the rated efficiency characteristics by optimizing the shape of the IPMSM. At the same time, torque ripple is reduced, which improves the control performance of the EOP. As a result, the optimal design result based on the proposed deep learning is verified by comparing it with the conventional method and the improvement of efficiency characteristics is confirmed.

Optimal Design Based on Deep Learning of Interior Permanent Magnet Synchronous Motor Used in Electric Oil Pump

Paper Proceedings: https://asmedigitalcollection.asme.org/ISPS/ISPS2021/volume/84799

ASME 2021 Information Storage and Processing Systems (ISPS2021)

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.