Optimising linear regression for modelling the dynamic thermal behaviour of electrical machines using NSGA-II, NSGA-III and MOEA/D.

Banda, Tiwonge Msulira; Zăvoianu, Alexandru-Ciprian; Petrovski, Andrei; Wöckinger, Daniel; Bramerdorfer, Gerd

Abstract

For engineers to create durable and effective electrical assemblies, modelling and controlling heat transfer in rotating electrical machines (such as motors) is crucial. In this paper, we compare the performance of three multi-objective evolutionary algorithms, namely NSGA-II, NSGA-III, and MOEA/D in finding the best trade-offs between data collection costs/effort and expected modelling errors when creating low-complexity Linear Regression (LR) models that can accurately estimate key motor component temperatures under various operational scenarios. The algorithms are integrated into a multi-objective thermal modelling strategy that aims to guide the discovery of models that are suitable for microcontroller deployment. Our findings show that while NSGA-II and NSGA-III yield comparably good optimisation outcomes, with a slight, but statistically significant edge for NSGA-II, the results achieved by MOEA/D for this use case are below par.

Citation

BANDA, T.M., ZĂVOIANU, A.-C., PETROVSKI, A., WÖCKINGER, D. and BRAMERDORFER, G. 2024. Optimising linear regression for modelling the dynamic thermal behaviour of electrical machines using NSGA-II, NSGA-III and MOEA/D. In Stratulat, S., Marin, M., Negru, V. and Zaharie, D. (eds.) Proceedings of the 25th International symposium on symbolic and numeric algorithms for scientific computing (SYNASC 2023), 11-14 September 2023, Nancy, France. Los Alamitos: IEEE Computer Society [online], pages 186-193. Available from: https://doi.org/10.1109/SYNASC61333.2023.00032

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 25th International symposium on symbolic and numeric algorithms for scientific computing (SYNASC 2023)
• Start Date: Sep 11, 2023
• End Date: Sep 14, 2023
• Acceptance Date: Nov 17, 2023
• Online Publication Date: May 10, 2024
• Publication Date: Dec 31, 2023
• Deposit Date: Mar 21, 2024
• Publicly Available Date: May 13, 2024
• Publisher: IEEE Computer Society
• Peer Reviewed: Peer Reviewed
• Pages: 186-193
• Series ISSN: 2470-881X; 2470-8801
• ISBN: 9798350394139
• DOI: https://doi.org/10.1109/SYNASC61333.2023.00032
• Keywords: Heat transfer; Electronics; Multi-criteria decision making; Linear regression; Optimisation
• Public URL: https://rgu-repository.worktribe.com/output/2279070