Neural network control of a gas turbine
- 123 Downloads
In this paper we explore the practical use of neural networks for controlling complex non-linear systems. The system used to demonstrate this approach is a simulation of a gas turbine engine typical of those used to power commercial aircraft. The novelty of the work lies in the requirement for multiple controllers which are used to maintain system variables in safe operating regions as well as governing the engine thrust.
KeywordsCorrelation tests Model following Neurocontrol
Unable to display preview. Download preview PDF.
- 1.Werbos PJ. Backpropagation and neurocontrol: A review and prospectus. In: IJCNN Washington, vol. 1, 1989; 209–216Google Scholar
- 2.Åstrom KJ, Wittenmark B. Adaptive Control. Addison-Wesley, Reading, MA, 1989Google Scholar
- 3.Campbell S. Connet: Simulation of engine and fuel system with conventional control. Technical report, Dowty Controls Ltd., 1992Google Scholar
- 4.Lightbody G, Wu QH, Irwin GW. Control applications for feedforward networks. In: KJ Warwick, GW Irwin, KJ Hunt, editors, Neural Networks for Control and Systems, vol. 46, IEE Control Engineering Series, Chap. 4. IEE, 1992Google Scholar
- 5.Nguyen DH, Widrow B. Neural networks for self learning control systems. IEEE Control Systems Magazine 1990; 18–23, AprilGoogle Scholar
- 6.Cressy DC, Nabney IT, Simper AM. Neural control of a batch distillation. Neural Computing and Applications 1993; 1:115–123Google Scholar
- 7.Bishop CM. Neural Networks for Pattern Recognition. Clarendon Press, Oxford, 1995Google Scholar
- 8.Billings SA, Voon WSF. Correlation based model validity tests for non-linear models. International Journal of Control 1986; 44:235–244Google Scholar
- 9.Billings, SA, Chen S. Neural networks and system identification. In: Warwick KJ, Irwin GW, Hunt KJ, editors. Neural Networks for Control and Systems, vol. 46, IEE Control Engineering Series, Chap. 9. IEE, 1992Google Scholar