Stacked long short-term memory model for proton exchange membrane fuel cell systems degradation

Fu Kwun Wang*, Xiao Bin Cheng, Kai Chun Hsiao

*Corresponding author for this work

Research output: Contribution to journalJournal Article peer-review

53 Scopus citations

Abstract

Proton exchange membrane fuel cell (PEMFC) systems have numerous applications such as transportation, portable power generation, and military. In this study, we propose a stacked long-short term memory (S-LSTM) model for fitting the degradation of a PEMFC system. Moreover, the proposed model provides the remaining useful life (RUL) prediction. A stacked LSTM architecture with dropout parameters can improve the prediction accuracy of the fuel cell degradation. We optimize the hyper parameters of the S-LSTM model using a differential evolution algorithm. The ageing test conditions of two PEMFC systems are carried by a fixed current and a ripple current, respectively. The results indicate that the S-LSTM model outperforms the other models in the RUL prediction of the PEMFC degradation in terms of mean absolute percent error and root mean square error.

Original languageEnglish
Article number227591
JournalJournal of Power Sources
Volume448
DOIs
StatePublished - 01 02 2020
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2019 Elsevier B.V.

Keywords

  • Degradation trend
  • Fuel cells
  • Stacked long short-term memory

Fingerprint

Dive into the research topics of 'Stacked long short-term memory model for proton exchange membrane fuel cell systems degradation'. Together they form a unique fingerprint.

Cite this