Prediction of Motor Characteristic Maps via Deep Operator Networks for Topology Optimization
IEEE Transactions on Magnetics · 2024-12 · 60 (12) · 1-5
DOI: 10.1109/tmag.2024.3477448 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Magnetics, 2024-12. Verfasst von Hidenori Sasaki und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 10 Literaturangaben. Gefördert von: Japan Society for the Promotion of Science (JSPS) through the Grant-in-Aid for Early Career Scientists.
Abstract (Originalsprache)
This study proposes a novel methodology for directly training response surfaces of torque and magnet flux density distributions of interior permanent magnet synchronous motors (IPMSMs) under specified input conditions and predicting the speed-torque characteristics or torque wave. Existing models have low prediction accuracy when simultaneously integrating shape information and current conditions. To overcome this challenge and improve the prediction of motor characteristics, a new deep learning (DL) model that combines deep operator networks and convolutional neural networks is proposed. This advanced approach greatly improves the accuracy of motor characteristic predictions across varying current levels and rotational angles, achieving an 89.6% increase in accuracy compared to comparative methods. The model is successfully applied to parameter and topology optimization (TO), effectively maximizing the speed-torque characteristics of IPMSMs.
Förderung
- Japan Society for the Promotion of Science (JSPS) through the Grant-in-Aid for Early Career Scientists
Zitieren
APA
Sasaki, H., Iwata, K., Sato, T., & Sato, Y. (2024). Prediction of Motor Characteristic Maps via Deep Operator Networks for Topology Optimization. IEEE Transactions on Magnetics, 60(12), 1-5. https://doi.org/10.1109/tmag.2024.3477448
Vancouver
Sasaki H, Iwata K, Sato T, Sato Y. Prediction of Motor Characteristic Maps via Deep Operator Networks for Topology Optimization. IEEE Transactions on Magnetics. 2024;60(12):1-5. doi:10.1109/tmag.2024.3477448
BibTeX
@article{Sasaki2024,
author = {Sasaki, Hidenori and Iwata, Kazuhisa and Sato, Takahiro and Sato, Yuki},
title = {Prediction of Motor Characteristic Maps via Deep Operator Networks for Topology Optimization},
journal = {IEEE Transactions on Magnetics},
year = {2024},
volume = {60},
number = {12},
pages = {1--5},
doi = {10.1109/tmag.2024.3477448}
}
EUVIMED