Fault diagnosis for PEMFC systems in consideration of dynamic behaviors and spatial inhomogeneity

Zhongliang Li (1, 2) , Rachid Outbib (3) , Stefan Giurgea (4) , Daniel Hissel (4)

1 LIS - Laboratoire d'Informatique et Systèmes
2 PECASE - Pronostic-Diagnostic Et CommAnde : Santé et Energie
3 LSIS - Laboratoire des Sciences de l'Information et des Systèmes
4 FEMTO-ST - Franche-Comté Électronique Mécanique, Thermique et Optique - Sciences et Technologies (UMR 6174)

In this paper, a data-driven fault diagnostic strategy is designed for Proton Exchange Membrane Fuel Cell (PEMFC) systems. In order to take the system dynamics and spatial inhomogeneity into account, the individual cell voltages measured in a sliding diagnosis window are considered integrally as a diagnostic observation. In the proposed diagnostic approach, a time-series analysis tool, named shapelet transform, is used to extract the discriminative features from the diagnostic observations. The classification tool, named Sphere Shaped Multi-class Support Vector Machine (SSM-SVM), is then carried out in the feature space in order to realize both fault detection and fault isolation. The approach is validated on the experimental testbench. The performance of the approach is evaluated and the necessity of considering both dynamic behaviors and the spatial inhomogeneity is highlighted.

Keywords: SVM classification; shapelet transform; Index Terms-PEMFC systems; data-driven diagnosis; dynam- ics; cell voltages

Domains: Automatic; Electric power

Zhongliang Li, Rachid Outbib, Stefan Giurgea, Daniel Hissel. Fault diagnosis for PEMFC systems in consideration of dynamic behaviors and spatial inhomogeneity. IEEE Transactions on Energy Conversion, 2019, 34 (1), pp.1-1. ⟨10.1109/TEC.2018.2824902⟩. ⟨hal-02004082⟩