On-line air supply control of PEM fuel cell by an adaptive neural network

Polymer Electrolyte Membrane Fuel Cells (PEMFC) are a clean and efficient electrical energy source. The PEMFC generates electrical energy by the hydrogen and oxygen chemical reaction. Replenishment of the depleted oxygen avoids the oxygen starvation phenomenon and extends the FC´s life time. This paper exposes an adaptive B-spline neurocontroller, for the optimal oxygen supply into the PEMFC. The B-spline neural network is proposed due to its simple structure, adaptability, and robustness, taking into account the PEMFC´s nonlinearities. The proposed neurocontroller is tested on a detailed nonlinear simulator of the open research. Results of the PEMFC system and the neurocontroller obtained by the hardware-in-the-loop strategy are exhibited. This control strategy has been achieved in real-time using a hardware-in-the-loop strategy.