Fault diagnosis and novel fault type detection for PEMFC system based on Spherical-Shaped Multiple-class Support Vector Machine
| Affiliation auteurs | !!!! Error affiliation !!!! |
| Titre | Fault diagnosis and novel fault type detection for PEMFC system based on Spherical-Shaped Multiple-class Support Vector Machine |
| Type de publication | Conference Paper |
| Year of Publication | 2014 |
| Auteurs | Li Z, Giurgea S, Outbib R, Hissel D |
| Conference Name | 2014 IEEE/ASME INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS (AIM) |
| Publisher | IEEE; ASME; ICS; DSC; IEEE Robot Automat Soc; Robot Soc Japan; JSPE; IEEJ; JSME; Femto St Sci & Technol; Labe Act; SICE; GDR MACS; Univ Franche Comte; Univ Technologie Belfort Montbeliard; ENSMM; SFMC; CNRS |
| Conference Location | 345 E 47TH ST, NEW YORK, NY 10017 USA |
| ISBN Number | 978-1-4799-5736-1 |
| Résumé | 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. |