Fault diagnosis and novel fault type detection for PEMFC system based on Spherical-Shaped Multiple-class Support Vector Machine

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

1 PECASE - Pronostic-Diagnostic Et CommAnde : Santé et Energie
2 FEMTO-ST - Franche-Comté Électronique Mécanique, Thermique et Optique - Sciences et Technologies (UMR 6174)
3 UPVM - Université Paul Verlaine - Metz

In this paper, a data-based strategy is proposed for PEMFC (polymer electrolyte membrane fuel cell) diagnosis. In the strategy, the feature extraction method Fisher Discriminant Analysis (FDA) is used firstly to extract the features from individual cell voltages. After that, the classification method Spherical-Shaped Multiple-class Support Vector Machine (SSM-SVM) is used to classify the extracted features to various classes related to health states. The potential novel failure mode can be detected in the procedure. Experiments on a 40-cell stack are dedicated to verify the approach.

Domaines: Energie électrique; Automatique / Robotique

Zhongliang Li, Stefan Giurgea, Rachid Outbib, Daniel Hissel. Fault diagnosis and novel fault type detection for PEMFC system based on Spherical-Shaped Multiple-class Support Vector Machine. 2014 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), Jul 2014, Besacon, France. pp.1628-1633, ⟨10.1109/AIM.2014.6878317⟩. ⟨hal-02476369⟩