Adaptive Neural Control Based on PEMFC Hybrid Modeling

Fuel cell stack breathing control system is important to avoid degradation of the proton exchange membrane fuel cell (PEMFC) stack voltage, and to maintain high efficiency and long stack life. This paper propose a new control technique for fuel cell stack breathing control system based on hybrid model, which combines space state equation with neural network black-box model. PEMFC stack process is represented with space state equation, the output of PEMFC stack voltage is modeled with neural network which consists of an input layer, a hidden layer and an output layer. Then adaptive neural controller is designed to control fuel cell breathing system based on hybrid model. The simulation results demonstrate that the proposed hybrid model and the adaptive neural controller have good performance