An Adaptive Resilient Control Approach for Pressure Control in Proton Exchange Membrane Fuel Cells

This paper introduces a novel controller design for pressure control in the proton exchange membrane (PEM) fuel cells. The proposed controller can control the system under the fault/failure of the actuators. The introduced design uses an artificial neural network for online fault detection and isolation in the pressure valves of the PEM fuel cell (PEMFC). We designed a nonlinear controller based on feedback linearization technique to compensate for the fault effects in real time. We also investigated the stability of the proposed design based on the Lyapunov theory. The simulation and the hardware in the loop results clearly show that the proposed active fault-tolerant control design is able to detect, estimate, and track the PEMFC actuators faults and failure accurately, and to compensate for their negative impacts while keeping the desired control performances in real time.