Self-adaptive digital twin of fuel cell for remaining useful lifetime prediction

Abstract

Accurate prediction of the remaining useful life (RUL) of proton exchange membrane fuel cells (PEMFCs) is essential for maximizing their operational lifespan. However, existing methods often face limitations in two key areas: long-term prediction (beyond 168 h, or one week) and adaptability to varying operating conditions. To address these challenges, we propose a novel self-adaptive digital twin (SADT) model for RUL prediction of PEMFCs. Our approach uniquely integrates a deep convolutional neural network to generate robust health indicators (HIs) that maintain consistent monotonicity across diverse operating conditions. Additionally, we introduce a novel quantile Huber loss (QH-loss) function to enhance prediction accuracy and incorporate a transfer learning technique to improve adaptability under varying operational scenarios. Experimental results on PEMFC degradation datasets demonstrate that our method outperforms state-of-the-art techniques in long-term prediction accuracy, highlighting its potential to significantly extend fuel cell lifetimes.

Publication DOI: https://doi.org/10.1016/j.ijhydene.2024.09.266
Divisions: College of Engineering & Physical Sciences > School of Engineering and Technology > Mechanical, Biomedical & Design
College of Engineering & Physical Sciences > School of Infrastructure and Sustainable Engineering > Chemical Engineering & Applied Chemistry
College of Engineering & Physical Sciences
College of Engineering & Physical Sciences > Energy and Bioproducts Research Institute (EBRI)
College of Engineering & Physical Sciences > Smart and Sustainable Manufacturing
College of Engineering & Physical Sciences > School of Computer Science and Digital Technologies > Applied AI & Robotics
Aston University (General)
Funding Information: This work was supported by Innovate UK project DIATOMIC (Digital InnovAtion TransfOrMatIve Change), UK with grant number 10055175. The authors would like to appreciate the financial support provided through EPSRC IAA 2022-23, UK Impact Builder Award.
Additional Information: Copyright © 2024 The Authors. Published by Elsevier Ltd on behalf of Hydrogen Energy Publications LLC. This is an open access article under the CC BY license (https://creativecommons.org/licenses/by/4.0/).
Uncontrolled Keywords: Degradation prediction,Digital twins,Fuel cells,Transfer learning,Useful lifetime,Renewable Energy, Sustainability and the Environment,Fuel Technology,Condensed Matter Physics,Energy Engineering and Power Technology
Publication ISSN: 1879-3487
Last Modified: 21 Nov 2024 17:22
Date Deposited: 10 Oct 2024 12:46
Full Text Link:
Related URLs: https://www.sci ... 360319924039752 (Publisher URL)
http://www.scop ... tnerID=8YFLogxK (Scopus URL)
PURE Output Type: Article
Published Date: 2024-11-04
Published Online Date: 2024-10-01
Accepted Date: 2024-09-19
Authors: Zhang, Ming (ORCID Profile 0000-0001-5202-5574)
Amiri, Amirpiran (ORCID Profile 0000-0001-7838-3249)
Xu, Yuchun (ORCID Profile 0000-0001-6388-813X)
Bastin, Lucy (ORCID Profile 0000-0003-1321-0800)
Clark, Tony (ORCID Profile 0000-0003-3167-0739)

Download

[img]

Version: Published Version

License: Creative Commons Attribution

| Preview

Export / Share Citation


Statistics

Additional statistics for this record