Diagnostic of fuel cell air supply subsystems based on pressure signal records and statistical pattern recognition approach. (11th November 2021)

• Record Type: Journal Article
• Authors: Benouioua, D.; Harel, F.; Candusso, D.
• Is Part Of: International journal of hydrogen energy. Volume 46:Number 78(2021)
• Page Start: 38809
• Page End: 38826
• Publication Date: 2021-11-11
• Subjects: Fuel cell -- Air supply subsystem -- Compressor -- Diagnosis -- Supervised machine-learning; Hydrogen as fuel -- Periodicals; Hydrogène (Combustible) -- Périodiques; Hydrogen as fuel; Periodicals; 665.81
• DOI: 10.1016/j.ijhydene.2021.09.147
• Languages: English
• ISSNs: 0360-3199

Abstract

Abstract: A data-driven and application-oriented diagnosis tool is developed for Fuel Cell (FC) air supply subsystems. A bench emulating a FC air line is built to study normal and abnormal operations (clogged inlet, air leakage, error in compressor speed control) and data are collected using the air pressure transducer, which is usually implemented in FC generators. A pattern recognition approach is then applied to statistical features extracted from the pressure signal. The performance of the diagnosis strategy is evaluated from confusion matrices, associated to graphs and performance indicators. Two examples of compressors, air subsystem managements, and data records are considered to examine the method portability. Best classification rates (>95%) are obtained on test profiles, when the pressure regulation is disabled; fault stamps can thus be found in the pressure signal morphology. Regarding the frequency of data logging, both 1 kHz and 100 Hz values are found effective for fault isolations. Highlights: A data-driven diagnostic tool is developed for the air supply subsystem of fuel cells. The input to the algorithm is the signal from the pressure sensor (at 1000 or 100 Hz). Fault scenarios are: air leak, compressor speed control fault, clogged air inlet. The portability of the method is shown with 2 compressors and 2 air control modes. Highest classification rate (97%) is reached with the pressure regulation disabled.