EUVIMEDEUVIMED entdecken
Crossref

Design and PINN-Kriging assisted multi-objective optimization of a dual-electrical-port in-wheel motor for HEV electromagnetic E-CVT

Zhiliang Zeng, Dejian Meng

Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering · 20.11.2026

DOI: 10.1177/09544070261507314 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, online erschienen am 20.11.2026. Verfasst von Zhiliang Zeng und 1 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben. Gefördert von: The National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Direct-drive in-wheel motors (IWMs) are constrained by low torque density and the unsprung mass penalty associated with size scaling, while geared reductions suffer from inherent gear clearance and NVH degradation. To overcome these limitations, this paper proposes a hybrid-flux dual-electrical-port in-wheel motor (DEP-IWM) designed for electromagnetic electro-stepless transmission (E-CVT) in hybrid electric vehicles. Featuring a coaxial single-stator dual-rotor topology with twin independent windings, the proposed motor achieves seamless electromagnetic power split without mechanical planetary gear sets. The outer rotor employs a tangential flux-concentrating array that functions dual-purpose as a “dynamic magnetic bridge” and a flux-modulation structure. Concurrently, the inner rotor incorporates an eccentric pole-scraping geometry, which effectively eliminates high-order air-gap harmonics while avoiding the manufacturing complexity of Halbach arrays. To address the multi-parameter, strongly coupled optimization inherent to dual-port topologies, a physics-informed surrogate model combining Physics-Informed Neural Networks and Kriging (PINN-Kriging) was constructed by embedding Maxwell partial differential equations into the loss function, followed by multi-objective inverse optimization via NSGA-II algorithm combined with engineering-preference TOPSIS decision-making. Finite element verification demonstrates that the optimized outer-rotor torque density increases by 192.5% compared with conventional dual-drive counterparts, while torque ripples for the outer and inner rotors are suppressed to 4.45% and 3.77%, respectively. This study offers a high-efficiency, ripple-suppression direct-drive solution for high-performance distributed chassis.

Förderung

  • The National Natural Science Foundation of China

Zitieren

APA

Zeng, Z., & Meng, D. (2026). Design and PINN-Kriging assisted multi-objective optimization of a dual-electrical-port in-wheel motor for HEV electromagnetic E-CVT. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering. https://doi.org/10.1177/09544070261507314

Vancouver

Zeng Z, Meng D. Design and PINN-Kriging assisted multi-objective optimization of a dual-electrical-port in-wheel motor for HEV electromagnetic E-CVT. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering. 2026. doi:10.1177/09544070261507314

BibTeX
@article{Zeng2026,
  author = {Zeng, Zhiliang and Meng, Dejian},
  title = {Design and PINN-Kriging assisted multi-objective optimization of a dual-electrical-port in-wheel motor for HEV electromagnetic E-CVT},
  journal = {Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering},
  year = {2026},
  doi = {10.1177/09544070261507314}
}
Kostenlos starten →