JZUS - Journal of Zhejiang University SCIENCE

Journal of Zhejiang University SCIENCE A

Accepted manuscript available online (unedited version)

Real-time degradation modeling for automotive PEMFC stacks: a multi-scale fusion network validated on an industrial 215-channel system

Author(s): Zifei WANG^1, ², Xiangxian ZHU³, Congxin LI⁴, Daidai CHEN³, Zhitao LIU², Longhua MA¹, Jili TAO¹, Hongye SU²
Affiliation(s): ¹NingboTech University, Ningbo 315100, China ²State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027, China ³Ningbo Joyson Electronic Corp, Ningbo 315040, China ⁴Ningbo Green Power Hydrogen Technology Research Institute Co., Ltd. Zhejiang 315033, China
Corresponding email(s): Jili TAO, taojili@nbt.edu.cn
Key Words: Large-scale PEMFC stacks; Multi-scale bidirectional fusion network; Degradation prediction; Automotive scenarios

Share this article to： More <<< Previous Paper \|Next Paper >>>

Zifei WANG^1,², Xiangxian ZHU³, Congxin LI⁴, Daidai CHEN³, Zhitao LIU², Longhua MA¹, Jili TAO¹, Hongye SU². Real-time degradation modeling for automotive PEMFC stacks: a multi-scale fusion network validated on an industrial 215-channel system[J]. Journal of Zhejiang University Science A,in press.Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/jzus.A2500337

@article{title="Real-time degradation modeling for automotive PEMFC stacks: a multi-scale fusion network validated on an industrial 215-channel system",
author="Zifei WANG^1,², Xiangxian ZHU³, Congxin LI⁴, Daidai CHEN³, Zhitao LIU², Longhua MA¹, Jili TAO¹, Hongye SU²",
journal="Journal of Zhejiang University Science A",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/jzus.A2500337"
}

%0 Journal Article
%T Real-time degradation modeling for automotive PEMFC stacks: a multi-scale fusion network validated on an industrial 215-channel system
%A Zifei WANG^1
%A²
%A Xiangxian ZHU³
%A Congxin LI⁴
%A Daidai CHEN³
%A Zhitao LIU²
%A Longhua MA¹
%A Jili TAO¹
%A Hongye SU²
%J Journal of Zhejiang University SCIENCE A
%P
%@ 1673-565X
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/jzus.A2500337"

TY - JOUR
T1 - Real-time degradation modeling for automotive PEMFC stacks: a multi-scale fusion network validated on an industrial 215-channel system
A1 - Zifei WANG^{1
A1 -}²
A1 - Xiangxian ZHU³
A1 - Congxin LI⁴
A1 - Daidai CHEN³
A1 - Zhitao LIU²
A1 - Longhua MA¹
A1 - Jili TAO¹
A1 - Hongye SU²
J0 - Journal of Zhejiang University Science A
SP -
EP -
%@ 1673-565X
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/jzus.A2500337"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: Accurately predicting long-term degradation patterns in proton exchange membrane fuel cell stacks (PEMFCs) under automotive operating conditions remains challenging. Prediction methods are largely constrained by laboratory-scale experiments and limited stack sizes, resulting in insufficient accuracy and generalization capability. To address these limitations, in this paper we propose a multi-scale bidirectional fusion network (MBFNet) tailored for an industrial 215-channel PEMFC stack, enabling accurate degradation prediction under accelerated real-world dynamic conditions using gas-heat-electricity (GHE) co-simulation data. A channel-joint adaptive noise correlation threshold (NCT) algorithm is introduced to account for variable correlations across sensors and operating conditions without relying on prior physical modeling. A multi-scale decomposition module captures degradation dynamics at different temporal scales, while a bidirectional fusion module integrates global trends and local details into the final prediction. Experimental results showed that MBFNet achieved 18.5% lower prediction error and 36.8% fewer parameters than the LSTM-Attention benchmark under real operating scenarios. In multi-step prediction tasks, MBFNet reduced error by 9% relative to LSTM-Attention and by 40.5% relative to 1D-CNN, better satisfying automotive application requirements. Moreover, MBFNet exhibits strong physical interpretability, making it efficient to implement and promising for practical deployment.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference