On the issue of the PEMFC operating fault identification: Generic analysis tool based on voltage pointwise singularity strengths. (21st June 2018)

• Record Type: Journal Article
• Authors: Benouioua, D.; Candusso, D.; Harel, F.; Picard, P.; François, X.
• Is Part Of: International journal of hydrogen energy. Volume 43:Number 25(2018)
• Page Start: 11606
• Page End: 11613
• Publication Date: 2018-06-21
• Subjects: PEMFC stacks -- Automotive application -- μCHP application -- Diagnostic -- Voltage singularity spectrum -- Machine learning; Hydrogen as fuel -- Periodicals; Hydrogène (Combustible) -- Périodiques; Hydrogen as fuel; Periodicals; 665.81
• DOI: 10.1016/j.ijhydene.2017.09.177
• Languages: English
• ISSNs: 0360-3199

Abstract

Abstract: The purpose of this article is to study the portability of a non-intrusive and free of any external/internal disturbance diagnosis tool devoted to the monitoring of the State of Health (SoH) of PEM Fuel Cell (PEMFC) stack. The tool is based on a thorough analysis of the stack voltage signal using a multifractal formalism and wavelet leaders. It offers well-suited signatures indicators on the SoH of the Fuel Cell. Some relevant descriptors extracted from these patterns (singularity features) are used in the frame of Machine Learning approaches to allow the PEMFC fault identification. The proposed diagnosis strategy is evaluated with two different PEMFC stacks. The first one is designed for automotive applications and the second one is dedicated to stationary use (micro combined heat and power - μCHP application). The classification results obtained for the both stacks indicate that the proposed PEMFC diagnosis tool allows identifying simple operating faults as well as more complicated operating situations combining several fault types. Highlights: Two PEMFC stack technologies are operated in various fault condition scenarios. Stack voltage morphologies are described with singularity spectra signatures. Fault identifications are performed using machine learning approaches. For both stacks, single faults and combined operating faults can be identified. Portability of the diagnosis tool is shown by high rates of fault classification.