Enhancing Prognostics of PEM Fuel Cells with a Dual-Attention LSTM Network for Remaining Useful Life Estimation: A Deep Learning Model

Abstract

The Proton Exchange Membrane Fuel Cell (PEMFC) presents itself as a viable and effective technology to consider for transportation purposes. An essential aspect in the realm of electric vehicles is the crucial evaluation of the deterioration of the PEMFC stack. This paper proposed a data-driven deep learning framework that combines a Long Short-Term Memory (LSTM), self-attention, and scaled dot-product attention mechanism in order to enhance the precision of Remaining Useful Life (RUL) prediction for Proton Exchange Membrane Fuel Cells (PEMFCs). The LSTM enables the model to comprehend intricate temporal patterns and produce more abstract data representations. The self-attention mechanism is utilized to detect correlations among various time points. The scaled dot-product attention mechanism is employed to focus on the most crucial features. The effectiveness of the proposed model was evaluated by utilizing the 2014 PHM Data Challenge Dataset and comparing it with different Deep Learning models to showcase its efficacy. The findings from the experiments suggest that DA-LSTM proves to be a reliable choice for predicting the RUL of PEMFCs, as it demonstrated superior performance compared to all other models examined.