D12.8 - Equivalent Circuit Model Analysis for Data-Driven Oriented Diagnosis of High-Level CO in HT-PEMFC with EIS

Different equivalent circuit models(ECM) of Electrochemical impedance spectroscopy (EIS) were analyzed in terms of parameter identification as features for machine learning model in online diagnosis of CO in the high temperature proton exchanged membrane fuel cell (HT-PEMFC). Parameter identification was performed and the features for machine learning model training were analyzed based on EIS data tested under 1-1.5% CO and 5-100A load current on a 10-cell short fuel cell stack. Anode reaction(1000-100Hz) and diffusion(100-5Hz) influenced by CO were suggested as two factors for performance assessment of the ECM in EIS fitting and parameter identification. The ECM 4 (Rs-(R1//CPE1)-(R2//CPE2)) exhibited great potential in online diagnosis of high-level CO due to its better fitting performance in the aimed frequency and obvious parameter deviations between normal and faulty conditions. This work contributes to the selection of ECM and the interpretation of machine learning methods for online diagnosis on HT-PEMFC with EIS.