Journal
IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION
Volume 8, Issue 1, Pages 420-431Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TTE.2021.3121179
Keywords
Degradation; Discrete wavelet transforms; Predictive models; Training; Voltage; Steady-state; Genetic algorithms; Data-driven; degradation; echo state network (ESN); fuel cells; genetic algorithm (GA); prognostic; wavelet transform
Funding
- EIPHI Graduate School [ANR-17-EURE-0002]
- European Commission H2020 Grant PANDA [H2020-LC-GV-2018]
- EU [824256]
- ANR Project BIPHOPROC_2 [ANR-14-OHRI-0018]
- Agence Nationale de la Recherche (ANR) [ANR-14-OHRI-0018] Funding Source: Agence Nationale de la Recherche (ANR)
Ask authors/readers for more resources
In this study, a data-driven approach is proposed to improve the remaining useful life (RUL) prediction performance of proton exchange membrane fuel cells. The proposed approach uses discrete wavelet transform (DWT) to compress historical data and predicts the approximation components using echo state network (ESN) in the compressed space. The key parameters of ESN are optimized using genetic algorithm (GA). Finally, the inverse DWT is used to reconstruct the coming data, and the performance of the proposed approach is evaluated through experimental tests.
Limited durability is one of the major issues that hinder the large-scale commercialization of the proton exchange membrane fuel cells system. Based on the prognostic technique, predicting the remaining useful life (RUL) efficiently and accurately can help prolong its residual life, especially on the long-term horizon and under different mission profiles. Thus, a data-driven approach of discrete wavelet transform-echo state network-genetic algorithm (DWT-ESN-GA) is proposed to improve the RUL prediction performance. First, the historical datasets are compressed by the DWT. Second, the approximation components of the original data are predicted in the compressed space by ESN. Rather than predicting the degradation data themselves, their shortened coefficients are evaluated to decrease the prediction data points, i.e., from 2016 data points to 253 data points. Besides, a GA is used to optimize the key parameters of ESN, and it can further increase the prediction accuracy. Finally, the inverse DWT is utilized to reconstruct the coming data based on the estimated approximation components. The performance of the proposed approach is evaluated by three different experimental tests under steady-state, quasi-dynamic, and full dynamic operating conditions separately.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available