PEM fuel cell voltage-tracking using artificial neural network

Transients in load and consequently in stack current have a significant impact on the performance and durability of fuel cell. The delay exciting in auxiliary equipments in fuel cell system such as pumps, heaters, back pressures will degrade system performance and lead to problems in controlling tuning parameters including temperature, pressure and flow rate. To overcome this problem, using fast and delay-free systems for predicting control signals is inevitable. Neural network model is proposed to control the stack terminal voltage as a proper constant and improve system performance. This is done through input air pressure control signal. The proposed artificial neural network is constructed based on back propagation network. A fuel cell nonlinear model with and without feed forward control is investigated and compared under random current variations. Simulation results have shown that, applying neural network feed forward control can successfully improve system performance in tracking output voltage. Furthermore consuming less energy and simpler control system are the other advantages of the proposed control algorithm.