Improving accuracy of long-term prognostics of PEMFC stack to estimate remaining useful life

摘要: Proton Exchange Membrane Fuel cells (PEMFC) are energy systems that facilitate electrochemical reactions to create electrical from chemical of hydrogen. PEMFC promising source renewable can operate on low temperature and have the advantages high power density pollutant emissions. However, technology is still in developing phase, its large-scale industrial deployment requires increasing life span fuel decreasing their exploitation costs. In this context, Prognostics Health Management an emerging field, which aims at identifying degradation early stages estimating Remaining Useful Life (RUL) for cycle management. Indeed, due prognostics capability, accurate estimates RUL enables safe operation equipment timely decisions prolong span. This paper contributes data-driven by ensemble constraint based Summation Wavelet-Extreme Learning Machine (SW-ELM) algorithm improve accuracy robustness long-term prognostics. The SW-ELM used modeling enhanced applicability real applications as compared conventional algorithms. proposed model validated run-to-failure data stack, had 1750 hours. results confirm capability achieve estimates.