Aeroengine Exhaust Gas Temperature Prediction Using Process Neural Network with Time-Varying Threshold Functions

Abstract:

To predict the aeroengine exhaust gas temperature (EGT) more precisely, a process neuron with time-varying threshold function is proposed in this paper, and then the time-varying threshold process neural network model comprised of the presented process neurons is used for EGT prediction. By introducing a group of appropriate orthogonal basis functions, the input functions, the weight functions and the threshold functions of the time-varying threshold process neural network can be expanded as linear combinations of the given orthogonal basis functions, thus to eliminate the integration operation, then to simplify the time aggregation operation. The corresponding learning algorithm is also presented, and the effectiveness of the time-varying threshold process neural network model is evaluated through the prediction of EGT series from practical aeroengine condition monitoring.

• Periodical: Applied Mechanics and Materials (Volumes 423-426)
• Pages: 2341-2346
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.423-426.2341
• Online since: September 2013
• Authors: Gang Ding, Xiong Wei Wang, Da Lei
• Keywords: Exhaust Gas Temperature Prediction, Learning Algorithm, Orthogonal Basis Function, Time-Varying Threshold Function, Time-Varying Threshold Process Neural Network

References

[1] A.K. Jardine, D. Lin, and D. Banjevic, Mechanical systems and signal processing, Vol. 20(2006), pp.1483-1510.

[2] G. Chen, Acta Aeronautica Et Astronautica Sinica, (2007), pp.535-539 (in Chinese).

[3] S S Zhong, Y Li, G Ding, et al, Neural network world, Vol. 16(2007), pp.483-495.

[4] G. Ding, S. S. Zhong: J. of Astronautics, Vol. 27 (2006), pp.645-650.

[5] X.G. He, J.Z. Liang, Engineering Science, Vol. 2(2000), pp.40-44 (in Chinese).