A data-driven digital-twin prognostics method for proton exchange membrane fuel cell remaining useful life prediction

Safa Meraghni,Labib Sadek Terrissa,Meiling Yue,Jian Ma,Samir Jemei,Noureddine Zerhouni

doi:10.1016/j.ijhydene.2020.10.108

Abstract

Prognostics and health management of proton exchange membrane fuel cell (PEMFC) systems have driven increasing research attention in recent years as the durability of PEMFC stack remains as a technical barrier for its large-scale commercialization. To monitor the health state during PEMFC operation, digital twin (DT), as a smart manufacturing technique, is applied in this paper to establish an ensemble remaining useful life prediction system. A data-driven DT is constructed to integrate the physical knowledge of the system and a deep transfer learning model based on stacked denoising autoencoder is used to update the DT with online measurement. A case study with experimental PEMFC degradation data is presented where the proposed data-driven DT prognostics method has applied and reached a high prediction accuracy. Furthermore, the predicted results are proved to be less affected even with limited measurement data.

Highlights

In an era of accelerating change, the imperative to limit climate change and achieve sustainable growth is strengthening the momentum of the global energy transformation
A prognostics method based on particle filtering (PF) approach using an exponential empirical model has been realized according to Jouin et al [42]
The prediction performance of the proposed method rarely depends on the prediction horizon, i.e. even at the beginning of the test, the prediction accuracy is superior to that of PF prognostics method

Summary

Introduction

In an era of accelerating change, the imperative to limit climate change and achieve sustainable growth is strengthening the momentum of the global energy transformation. A “hydrogen economy era” is coming into the human's horizon towards establishing a cleaner energy system [1]. In this context, fuel cells are regarded as the technology of choice to maximise the potential benefits of hydrogen in terms of efficiency [2]. Proton exchange membrane fuel cell (PEMFC) is currently the leading technology for light-duty vehicles and materials handling vehicles, and to a less extent for stationary and other applications [3]. The unsatisfied durability and reliability of the current PEMFC systems can be associated with the high maintenance cost [5], while non-optimized operation could be a critical reason leading to the unexpected shutdowns and further degradation of the components [6]. Efforts have been made to improve its durability: working on the materials, reducing the causes of degradation, improving the structural design, implementing new supervision and management designs, etc

Results

Discussion

Conclusion