Robust adaptive neural network control for PEM fuel cell
MetadataShow full item record
Abbaspour, Alireza; Khalilnejad, Arash; Chen, Zheng. 2016. Robust adaptive neural network control for PEM fuel cell. International Journal of Hydrogen Energy, vol. 41:no. 44, 26 November 2016:pp 20385–20395
This paper presents a robust neural network adaptive control for polymer electrolyte membrane (PEM) fuel cells (FCs). Since deviations between the partial pressure of hydrogen and oxygen in PEMFCs lead to serious membrane damage, it is desirable to have a robust and adaptive control to stabilize the partial pressure, which can significantly lengthen their lifetime. Due to inherent nonlinearities in PEMFC dynamics and variations of the system parameters, a linear control with fixed gains cannot control the PEMFC system properly. Therefore, a neural network adaptive control with feedback linearization is developed for this system. With a feedback linearization control only, the performance is deviated in the presence of unknown dynamics and disturbances. Thus, a robust adaptive neural network control is added to the feedback linearization control to reduce the deviation. Simulation results show that the proposed control can significantly enhance the output performance as well as reject the disturbances.
Click on the DOI link to access the article (may not be free).