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

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.

Authors

Institutions

Publication Details

Journal
Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering
Published
2026-11-20
DOI
https://doi.org/10.1177/09544070261507314
Primary Topic
Electric Motor Design and Analysis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

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

Dejian Meng, Zhiliang Zeng
Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering
Electric Motor Design and Analysis
article

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

Dejian Meng, Zhiliang Zeng
article en

Abstract

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.

Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering
Tongji University (CN)
Electric Motor Design and Analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
Design and PINN-Kriging assisted multi-objective optimization of a dual-electrical-port in-wheel motor for HEV electromagnetic E-CVT — Dejian Meng, Zhiliang Zeng · Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering (2026) | TGRS Research Map | TGRS