Towards End-to-End Deep Learning Performance Analysis of Electric Motors

Nikita Gabdullin,Alexey Vilkin,Sadjad Madanzadeh

doi:10.3390/act10020028

Abstract

Convolutional Neural Networks (CNNs) and Deep Learning (DL) revolutionized numerous research fields including robotics, natural language processing, self-driving cars, healthcare, and others. However, DL is still relatively under-researched in physics and engineering. Recent works on DL-assisted analysis showed enormous potential of CNN applications in electrical engineering. This paper explores the possibility of developing an end-to-end DL analysis method to match or even surpass conventional analysis techniques such as finite element analysis (FEA) based on the ability of CNNs to predict the performance characteristics of electric machines. The required depth in CNN architecture is studied by comparing a simplistic CNN with three ResNet architectures. Studied CNNs show over 90% accuracy for an analysis conducted under a minute, whereas a FEA of comparable accuracy required 200 h. It is also shown that training CNNs to predict multidimensional outputs can improve CNN performance. Multidimensional output prediction with data-driven methods is further discussed in context of multiphysics analysis showing potential for developing analysis methods that might surpass FEA capabilities.

Highlights

Whereas Deep Learning (DL) Convolutional Neural Networks (CNNs) were previously used to speed up the optimization while final results were obtained using finite element analysis (FEA) [20,22], this paper shows the possibility of accurately evaluating rotor geometries using DL CNNs
This paper investigates the possibility of predicting multidimensional outputs of electric machines with a DL CNNs
Four DL CNNs were trained to predict output torque curves of Interior permanent magnet synchronous motors (IPMSMs) showing over 90% prediction accuracy

Summary

Introduction

DL methods allow making predictions for complex systems with various non-explicitly connected parameters, making them promising for high-accuracy, fast, low-cost electromagnetic analysis. The latter is extremely important for the design of high-density high-efficiency electric machines that have various industrial applications. Interior permanent magnet synchronous motors (IPMSMs) are highly valued for high power density, torque density, and energy efficiency owing to the properties of strong rare earth permanent magnets (PMs) [11,12]. They are widely used as traction motors for transport vehicles and in-wheel motors for electric vehicles [13]. Due to low-weight and compact size, IPMS motors and generators have been gaining increasing attention for more electric aircraft applications where compact lightweight high-torque machines are needed [14,15]

Objectives

Findings

Discussion

Conclusion