Autocorrelation standard deviation and root mean square frequency analysis of polymer electrolyte membrane fuel cell to monitor for hydrogen and air undersupply

Evaluation Method for Feature Selection in Proton Exchange Membrane Fuel Cell Fault Diagnosis

“…Since PEMFC voltage can directly represent the PEMFC performance change, in previous studies, various features extracted from PEMFC voltage have been used to identify different PEMFC faults. These features include time-domain features like principal component analysis (PCA) [14][15][16], fisher discriminant analysis (FDA) [7,17], and autocorrelation standard deviation (ACSD) [18]; frequency-domain features such as root mean square frequency (RMSF) and frequency power spectrum [19]; time-frequency domain features from wavelet transform (WT) [20][21][22][23][24][25][26][27][28] and wavelet packet transform (WPT) [29][30][31][32].…”

“…Hua et al [14] investigated the effectiveness of detecting PEMFC sensor network failure using PCA method. Kim et al [18] extracted ACSD from PEMFC voltage for diagnosing insufficient reactant gas issue. In [25], high air stoichiometry ratio was identified by extracting features from PEMFC voltage with WT analysis.…”

Polymer electrolyte membrane fuel cell fault diagnosis and sensor abnormality identification using sensor selection method

“…From the results different PEM fuel cell faults, including high current pulse, cooling water stop, high/low air stoichiometry, and CO poisoning, could be identified. Kim et al [13] analysed the frequency components in the PEM fuel cell voltage at different hydrogen and air supply rates, from which relationship between root mean square frequency (RMSF), autocorrelation standard deviation (ACSD) and hydrogen/air supply rates were determined for PEM fuel cell state monitoring. Liu et al [14] proposed a PEM fuel cell diagnostic method using extreme learning machine and Dempster-Shafer evidence theory, where multiple measurements such as hydrogen and air flow rate, pressure, temperature were used in the diagnosis.…”

Optimization of proton exchange membrane fuel cell’s end plates

“…In this study PEM 1 fuel cells have been investigated. PEM fuel cell's Components such as MEA, GDL 2 and bipolar plate should be put together with the proper contact pressure from end plates to avoid the leakage and also to minimize the contact resistance of the cells [4][5][6]. Many studies have been done in the area of investigation of fuel cell's end plates and it's components to optimize efficiency.…”