Title: Comparison study of different non-linear feed-forward controllers for oxygen starvation control of PEM fuel cell stacks

Authors: Omar Ragb; Dong-Ya Zhao; Ding-Li Yu; Quan Min Zhu

Addresses: Control Systems Research Group, School of Engineering, Liverpool John Moores University, Byrom Street, Liverpool, L3 3AF, UK ' Department of Chemical Industrial Equipment and Control Engineering, College of Chemical Engineering, China University of Petroleum, Qingdao, 266580, China ' Control Systems Research Group, School of Engineering, Liverpool John Moores University, Byrom Street, Liverpool, L3 3AF, UK ' Bristol Institute of Technology, University of the West of England, Frenchay Campus, Coldharbour Lane, Bristol, BS16 1QY, UK

Abstract: Feed-forward and feedback control is developed in this work for PEM fuel cell stacks. The feed-forward control is achieved using different methods including look-up table, fuzzy logic and neural network, to improve the regulation of fuel cell stack breathing and avoid the problem of oxygen starvation. Firstly, the feed-forward controller is used to generate directly an input voltage of the air compressor according to the current demand. Then, a PID feedback controller is used to adjust the difference between the requested and the actual oxygen ratio by compensating the feed-forward controller output. The designed systems are evaluated using a benchmark of non-linear simulation of fuel cell stacks. The proposed feed-forward controllers with PID feedback control all achieved a good control performance. The simulations showed the effectiveness of the control strategies. By comparison, it is concluded that the neural network feed-forward controller gave the minimal response to disturbances.

Keywords: fuel cell stacks; FCSs; breathing control; oxygen starvation; feedforward control; fuzzy logic; neural networks; nanotechnology; nonlinear simulation; polymer electrolyte membrane; PEM fuel cells; comparison; PID control; feedback control; fuzzy control.

DOI: 10.1504/IJMIC.2013.055653

International Journal of Modelling, Identification and Control, 2013 Vol.19 No.4, pp.352 - 360

Published online: 27 Sep 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article