Real-Time Qualitative Model for Estimate Water Content in PEM Fuel Cell

To maintain optimum performance of the electrical response of a fuel cell, a real-time identification of the malfunction situations is required. Critical fuel cell states depend, among others, on the variable demand of electric load and are directly related to the membrane hydration level. The real-time perception of relevant states in the PEM fuel cell states space is still a challenge for the PEM fuel cell control systems. Current work presents the design and implementation of a methodology based upon fuzzy decision techniques that allow real-time characterization of the dehydration and flooding degree of the membrane of a PEM fuel cell. Real-time content water estimation is accomplished through a perturbation-perception process on the PEM fuel cell and further on voltage oscillation analysis. The real-time implementation of the perturbation-perception algorithm to detect PEM fuel cell the critical humidification degree is a novelty and a step forwards the control of the PEM fuel cell to reach and maintain optimal performance.