Modeling and control for PEMFC hydrogen management subsystem based on neural network compensation and prescribed tracking accuracy

The hydrogen management subsystem plays an important role in fuel cell automobiles as it impacts the output performance of the polymer electrolyte membrane fuel cell (PEMFC). This paper investigates the design and implementation of the neural network-based control for anode pressure and hydrogen excess ratio (HER). Firstly, the coupled nonlinear multiple-input-multiple-output (MIMO) system is transformed into canonical form one by using input–output linearization. Secondly, the neural network control scheme is proposed to regulate the anode pressure and HER without using the exact prior knowledge of the system. Moreover, a prescribed performance function (PPF) is proposed to guarantee the overshoot and steady-state tracking errors within the quantitative boundaries. To avoid the laborious parameter selection, the restriction that the initial error is within the performance function bound is relaxed by proposing a tuning function. Finally, the Lyapunov stability theory, numerical simulations and hardware-in-loop (HIL) experiments show the effectiveness of the proposed controller. Simulation and HIL experiment results show that the proposed control strategy is effective in realizing quantitative adjustment of tracking error while showing the best performance indexes including the root mean square error (RMSE) and minimum deviation of tracking error (DTE) compared with the neural network controller (NNC) and traditional prescribed performance controller (TPPC).