https://www.newmaterials.ca/wp-content/uploads/2026/04/Art8-JNMES-Jan26-pp79-87.pdf

Today, the PEM fuel cell is one of the most important renewable energy sources for energy supply.Given the significance of timely fault detection to enhance reliability, safety, and economic efficiency, and considering the nonlinear dynamics of the PEM system caused by electrochemical reactions, this paper introduces a novel technique based on a nonlinear input observer for timely and accurate fault detection in PEM fuel cell systems.The proposed observer is developed using the nonlinear matrix inequality approach and incorporates an adaptive technique, enabling it to estimate system states and accurately detect faults in each state, even in the presence of disturbances and uncertainties within the PEM system.The asymptotic stability of the error dynamics and the designed nonlinear input observer is demonstrated using the Lyapunov concept, ensuring the convergence of the state estimation error.Simulation results in the MATLAB environment, along with fault error criteria evaluation, confirm the effectiveness of the proposed fault detection method.