PROJECT TITLE :

Robust Model-Based Fault Diagnosis for PEM Fuel Cell Air-Feed System

ABSTRACT:

During this paper, the look of a nonlinear observer-primarily based fault diagnosis approach for polymer electrolyte membrane (PEM) fuel cell air-feed systems is presented, taking under consideration a fault scenario of sudden air leak within the air supply manifold. Primarily based on a simplified nonlinear model proposed within the literature, a modified super-twisting (ST) sliding mode algorithm is used to the observer design. The proposed ST observer can estimate not only the system states, however additionally the fault signal. Then, the residual signal is computed online from comparisons between the oxygen excess ratio obtained from the system model and therefore the observer system, respectively. Equivalent output error injection using the residual signal is able to reconstruct the fault signal, that is essential in both fuel cell control style and fault detection. Finally, the proposed observer-based mostly fault diagnosis approach is implemented on the MATLAB/Simulink setting so as to verify its effectiveness and robustness in the presence of load variation.