Data-based short-term prognostics for proton exchange membrane fuel cells

Prognostics is an important tool in the life and cost management of the proton exchange membrane fuel cells (PEMFCs). In this paper, we propose a data-based short-term prognostics method based on the group method of data handling and the wavelet analysis. In particular, this method first decomposes the original voltage sequence of PEMFCs into multiple sub-waveforms. Then, prognostics are made for the sub-waveforms and are combined for the overall prognostics of PEMFCs. Moreover, the proposed method is validated by the experimental datasets from real aging tests. Simulation results demonstrate that, compared with the existing approaches, this proposed method not only can achieve accurate short-term prognostics for PEMFCs in different load conditions, but also can directly use the original experimental data with large disturbances.