Adaptive feed-forward and feedback control using neural networks for oxygen ratio in fuel cell stacks

  • Authors:

  • Omar Ragb;Karl Jones;Dingli Yu;J Barry Gomm

  • Affiliations:

  • Liverpool John Moores University (LJMU), UK;LJMU;Control Systems Research group at LJMU;Intelligent control systems at LJMU, UK

  • Venue:
  • Proceedings of the 12th International Conference on Computer Systems and Technologies
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Automatic control of fuel cell stacks (FCS) using non-adaptive and adaptive radial basis function (RBF) neural network methods are investigated in this paper. The neural network inverse model is used to estimate the compressor voltage for fuel cell stack control at different current demands and 30% reduction in the compressor gain in order to prevent the oxygen starvation. A PID controller is used in the feedback to adjust the difference between the requested and the actual oxygen ratio by compensating the neural network inverse model output. Furthermore, the RBF inverse model is made adaptive to cope with the significant parameter uncertainty, disturbances and environment changes. Simulation results show the effectiveness of the adaptive control strategy.