Data-driven prognostics based on time-frequency analysis and symbolic recurrent neural network for fuel cells under dynamic load

•HHT-based method eliminates dynamic load noise and extracts degradation features.•Symbol-based GRU achieves reliable and efficient long-term prognostics.•Proposed data-driven method provides competitive prognostics horizon and accuracy.•Multiple failure thresholds can assess prognostics consistency...

Full description

Bibliographic Details

Published in:	Reliability engineering & system safety Vol. 233; no. May; p. 109123
Main Authors:	Wang, Chu, Dou, Manfeng, Li, Zhongliang, Outbib, Rachid, Zhao, Dongdong, Zuo, Jian, Wang, Yuanlin, Liang, Bin, Wang, Peng
Format:	Journal Article
Language:	English
Published:	Elsevier Ltd 01.05.2023 Elsevier
Subjects:	Automatic Dynamic load Electric power Empirical mode decomposition Engineering Sciences Proton exchange membrane fuel cell Remaining useful life Symbolic representation gated recurrent unit Time-frequency-energy spectrum Symbolic representation gated recurrent unit Empirical mode decomposition Proton exchange membrane fuel cell Time-frequency-energy spectrum Remaining useful life Dynamic load
ISSN:	0951-8320, 1879-0836
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!