Wavelets-based approach for online Fuel Cells Remaining Useful lifetime Prediction

Abstract

Prognostics and Health Management (PHM) techniques for Proton Exchange Membrane Fuel Cell (PEMFC) systems are of great importance for increasing their reliability and sustainability. PEMFC systems suffer from relatively poor longterm performance and durability, and prediction and prognosis can give early indications about when components should be fixed or replaced. Prognostics modelling needs to take account of a number of phenomena, including degradation mechanisms that are not easily measured. A number of works are currently investigating PHM in fuel cell systems, as well as the problem of estimating Remaining Useful Lifetime (RUL). Any reduction in the volume of data required for making predictions is clearly advantageous. In this work, a univariate prognostic approach based on signal processing, namely Discrete Wavelet Transform (DWT) is proposed. The proposed approach aims at achieving an online prognostic for PEMFC systems. DWT is first introduced, and then the predictions are built using the power signals of two different PEMFC stacks in two different scenarios, namely static and dynamic operating conditions. Results show that the method is reliable for online prediction of power, with prediction errors less than 3%.

Adaptive Prognostic of Fuel Cells by Implementing Ensemble Echo State Networks in Time-Varying Model Space

“…The evolution of the model parameters is tracked by jointing a group of particle filters. To reach a more precise shortterm or medium-term prediction of stack voltage evolution, wavelet analysis, combined with some regression methods is also proposed [15], [16].…”

Prognostics of a multistack PEMFC system with multiagent modeling

“…Among the different fuel cells types, Proton Exchange Membrane Fuel Cell (PEMFC) is the most developed one and is not far from large‐scale deployment . The chemical reaction between the hydrogen and oxygen in PEMFC produces electricity, heat, and water, with no poisonous gases emission …”

“…Unfortunately, PEMFC suffers a short life span, which makes it unsuitable for many applications . The lifetime ranges from 1500 to 3000 hours, whereas the requirements of mobile and stationary applications are around 5000 and 10 000 hours, respectively .…”

“…The lifetime ranges from 1500 to 3000 hours, whereas the requirements of mobile and stationary applications are around 5000 and 10 000 hours, respectively . Besides mechanical and electronic improvements of PEMFCs, Prognostics and Health Management (PHM) can contribute to avoid irreversible degradation, extend lifetime, optimize service quality, and reduce maintenance costs …”

A review on prognostics and health monitoring of proton exchange membrane fuel cell

“…An ensemble structure of SW-ELM with a new incremental learning scheme was applied to µCHP to estimate the SOH of the stack under variable load conditions for a a year [159]. A constraint based ensemble was proposed for real time prognostics of PEMFC [161].…”