Yuan Gao
Neural Network aided PMSM multi-objective design and optimization for more-electric aircraft applications
Gao, Yuan; Yang, Tao; Bozhko, Serhiy; Wheeler, Pat; Dragicevic, Tomis-Lav; Gerada, Chris
Authors
TAO YANG TAO.YANG@NOTTINGHAM.AC.UK
Professor of Aerospace Electricalsystems
Professor SERHIY BOZHKO serhiy.bozhko@nottingham.ac.uk
Professor of Aircraft Electric Power Systems
Professor PATRICK WHEELER pat.wheeler@nottingham.ac.uk
Professor of Power Electronic Systems
Tomis-Lav Dragicevic
CHRISTOPHER GERADA CHRIS.GERADA@NOTTINGHAM.AC.UK
Professor of Electrical Machines
Abstract
This study uses the Neural Network (NN) technique to optimize design of surface-mounted Permanent Magnet Synchronous Motors (PMSMs) for More-Electric Aircraft (MEA) applications. The key role of NN is to provide dedicated correction factors for the analytical PMSM mass and loss estimation within the entire design space. Based on that, a globally optimal design can be quickly obtained. Matching the analytical estimation with Finite-Element Analysis (FEA) is the main research target of training the NN. Conventional analytical formulae serve as the basis of this study, but they are prone to loss accuracy (especially for a large design space) due to their assumptions and simplifications. With the help of the trained NNs, the analytical motor model can give an estimation as accurate as the FEA but with super less time during the optimization process. The Average Correction Factor (ACF) approach is regarded as the comparison method to demonstrate the excellent performance of the proposed NN model. Furthermore, a NN aided three-stage-seven-step optimization methodology is proposed. Finally, a Pole-10-Slot-12 PMSM case study is given to demonstrate the feasibility and gain of the NN aided multi-objective optimization approach. In this case, the NN aided analytical model can generate one motor design in 0.04 s while it takes more than 1 min for the used FEA model.
Citation
Gao, Y., Yang, T., Bozhko, S., Wheeler, P., Dragicevic, T.-L., & Gerada, C. (2022). Neural Network aided PMSM multi-objective design and optimization for more-electric aircraft applications. Chinese Journal of Aeronautics, 35(10), 233-246. https://doi.org/10.1016/j.cja.2021.08.006
Journal Article Type | Article |
---|---|
Acceptance Date | Jun 2, 2021 |
Online Publication Date | Sep 16, 2021 |
Publication Date | 2022-10 |
Deposit Date | Aug 11, 2021 |
Publicly Available Date | Sep 20, 2022 |
Journal | Chinese Journal of Aeronautics |
Print ISSN | 1000-9361 |
Electronic ISSN | 1000-9361 |
Publisher | Elsevier |
Peer Reviewed | Peer Reviewed |
Volume | 35 |
Issue | 10 |
Pages | 233-246 |
DOI | https://doi.org/10.1016/j.cja.2021.08.006 |
Keywords | Permanent Magnet Synchronous Motor (PMSM); Design and Optimization; Neural Network (NN); Mean Length per Turn (MLT); Loss Estimation; More-Electric Aircraft (MEA) |
Public URL | https://nottingham-repository.worktribe.com/output/6012785 |
Publisher URL | https://www.sciencedirect.com/science/article/pii/S100093612100279X |
Files
1-s2.0-S100093612100279X-main
(3.1 Mb)
PDF
Publisher Licence URL
https://creativecommons.org/licenses/by-nc-nd/4.0/
You might also like
Active DC-link capacitor harmonic current reduction in two-level back-to-back converter
(2015)
Journal Article
Impact of Soft Magnetic Material on Design of High-Speed Permanent-Magnet Machines
(2016)
Journal Article
Downloadable Citations
About Repository@Nottingham
Administrator e-mail: discovery-access-systems@nottingham.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search