Adaptive control of air delivery system for PEM fuel cell using backstepping

The proton exchange membrane (PEM) fuel cells have attracted significant attention due to high efficiency and low pollution. The performance and lifetime of the fuel cell power system depend on the heat and water management, gas flow control and pressure regulation. This paper focuses on the oxygen excess ratio regulation for the fuel cell system to improve the performance and extend the lifetime. Firstly, a third-order model of the air delivery subsystem is introduced based on suitable assumption and simplification. Secondly, the third-order model is transformed to the non-affine nonlinear form, and the oxygen excess ratio regulation is reconsidered as load current tracking problem. Using the backstepping technique and neural network, an adaptive controller is proposed for the tracking problem and guarantees the system´s stability in presence of modeling errors, external disturbances and uncertainties. Finally, the simulation illustrates the effectiveness of the adaptive controller.