Review of surrogate model assisted multi-objective design optimization of electrical machines: New opportunities and challenges

This paper overviews surrogate model-assisted multi-objective design optimization techniques of electrical machines for efficient, accurate, and robust design optimization to ease design issues due to unprecedentedly increasing machine performance requirements. Firstly, the mechanism of surrogate-as...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Renewable & sustainable energy reviews Ročník 215; s. 115609
Hlavní autoři: Liu, Liyang, Li, Zequan, Kang, Haoyu, Xiao, Yang, Sun, Lu, Zhao, Hang, Zhu, Z.Q., Ma, Yiming
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.06.2025
Témata:
Design of experiments
Electrical machine
Multi-objective optimization algorithms
Optimization design
Surrogate model
Surrogate model
Electrical machine
Design of experiments
Optimization design
Multi-objective optimization algorithms
ISSN:1364-0321
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This paper overviews surrogate model-assisted multi-objective design optimization techniques of electrical machines for efficient, accurate, and robust design optimization to ease design issues due to unprecedentedly increasing machine performance requirements. Firstly, the mechanism of surrogate-assisted modeling is introduced by comparing it with conventional physical modeling approaches. The relevant techniques are then categorized and subsequently reviewed in terms of the design of experiments, surrogate model construction, and multi-objective optimization algorithms. The potential application prospects for machine design optimization are highlighted. Finally, three surrogate-assisted modeling methods, i.e., transfer learning-based models, gradient sampling-based multi-fidelity models, and search space decay-based surrogate models, are quantitively compared by applying them to the design optimization of a five-phase permanent magnet synchronous machine. •A comprehensive review of recent advancements in data-driven design optimization for electrical machines.•Categorization and analysis of various techniques, offering a thorough perspective.•A concise overview of the potential applications of surrogate-assisted optimization in electrical machines, covering multi-physics simulations, driving cycle-based designs, robustness enhancement, and topology optimization.•Quantitative assessment of three surrogate-assisted modeling techniques applied to a five-phase permanent magnet synchronous machine.
ISSN:1364-0321
DOI:10.1016/j.rser.2025.115609