Proton Exchange Membrane Fuel Cell Prognosis Based on Frequency-Domain Kalman Filter

The degradation seriously affects the durability and cost of proton exchange membrane fuel cell (PEMFC). This article presents a novel model-driven method based on frequency-domain Kalman filter (FDKF) voltage model to predict PEMFC in frequency domain. advantage proposed FDKF is that it can process data groups; thus, computation time be greatly reduced with high accuracy. Two experiments under constant quasi-dynamic currents have been used demonstrate its prognosis performances different conditions training times. Compared traditional time-domain extended literature, has demonstrated one higher accuracy requires much less calculation time.