Applications of Wavelet Neural Network for Prediction of CHF

Abstract:

In this study, a wavelet neural network (WNN) model for predicting critical heat flux (CHF) is set up. The WNN mode combining the properties of the wavelet transform and the advantages of Artificial Neural Networks (ANN) has some advantages of its globe optimal searching, quick convergence speed and solving non-linear problem. The database used in the analysis is from the 1960’s, including 126 data points which cover these parameter ranges: pressure P=100–1,000 kPa, mass flow rate G=40–500 kgm^-2s^-1, inlet subcooling ΔT_sub=0–35^◦C and heat flux Q=20–8,000 kWm^-2. The WNN prediction results have a good agreement with experimental data. Simulation and analysis results show that the network model can effectively predict CHF.

• Periodical: Applied Mechanics and Materials (Volumes 58-60)
• Pages: 1282-1286
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.58-60.1282
• Online since: June 2011
• Authors: Hui Ming Wei, Yuan Tian, Jun Zhong, Xuan Zhang
• Keywords: CHF (Critical Heat Flux), Prediction, Wavelet Analysis, Wavelet Neural Network (WNN)

References

[1] M. Cannon, J.J.E. Slotine: Neurocomputing Vol. 9 (1995), p.293.

[2] J. Chen, D.D. Bruns: Ind. Eng. Chem. Res. Vol. 34 (1995), p.4420.

[3] S. Mukherjee, S.K. Nayar: Pattern Recognition Vol. 29 (1996), p.1369.

[4] Y.C. Pati, P.S. Krishnaprasad: IEEE Trans. Neural Networks Vol. 4 (1993), p.73.

[5] A. Sureshbabu, J.A. Farrell: IEEE Trans. Autom. Control Vol. 44 (1999), p.412.

[6] J. Zhang, G.G. Walter, W. N.W. Lee: IEEE Trans. Signal Process. Vol. 43 (1995), p.1485.

[7] Q.H. Zhang: IEEE Trans. Neural Networks Vol. 8 (1997), p.227.

[8] Q.H. Zhang, A. Benveniste: IEEE Trans. Neural Networks Vol. 3 (1992), p.889.

[9] Z.Y. Lou, Z.K. Shi: Proceedings of the Fourth International Conference on Machine Learning and Cybernetics, Guangzhou, August 18-21 (2005).

[10] T. Khayamian, M. Esteki: J. of Supercritical Fluids Vol. 32 (2004), p.73.

[11] J. Li, D.F. Liu, X.R. Dai, Z. Zou, F.Q. Ding: Trans. Nonferrous Met. Soc. China Vol. 17 (2007), P. 1052.

[12] W.Z. Cui, C.C. Zhu, H.P. Zhao: Thin Solid Films Vol. 473 (2005), p.224.

[13] X.Y. Zhang, J.H. Qi, R.S. Zhang, M.C. Liu, Z.D. Hu, H.F. Xue, B.T. Fan: Computers and Chemistry Vol. 25 (2001), p.125.

[14] W.J. Chen, Y. Lee, D.C. Groeneveld: Int. J. Heat Mass Transfer Vol. 22 (1979), p.973.

[15] H.S. Ragheb, S.C. Cheng, D.C. Groeneveld: Int. J. Heat Mass Transfer Vol. 24 (1981), p.1127.

[16] S.T. Wang, R.A. Seban: Int. J. Heat Mass Transfer Vol. 31 (1988), p.1189.

[17] X.C. Huang, G. Bartsch, D. Schroeder-richter: Int. J. Heat Mass Transfer Vol. 37 (1994), p.803.

[18] H.S. Ragheb, S.C. Cheng: J. Heat Transfer Vol. 101 (1979), p.381.

[19] X.C. Huang, G. Bartsch: Int. J. Heat Mass Transfer Vol. 36 (1993), p.2601.

[20] X.C. Huang, P. Weber, G. Bartsch: Int. Commun. Heat Mass Transfer Vol. 20 (1993), p.383.

[21] S.C. Cheng, K.T. Heng, W. Ng: Int. J. Multiphase Flow Vol. 3 (1977), P. 495.

[22] S.C. Cheng, W.W.L. Ng, K.T. Heng: Int. J. Heat Mass Transfer Vol. 21 (1978), P. 1385.

[23] S.C. Cheng, W.W.L. Ng, K.T. Heng, D.C. Groeneveld: J. Heat Transfer Vol. 100 (1978), P. 382.

[24] G.W. He: Master thesis of Xi'an Jiaotong University (1989).

[25] Y.B. Qian, Z.W. Yu, D.N. Jia: Nucl. Sci. Eng. Vol. 14 (1994), p.213.

[26] Z. R. Yuan: Artificial Neural Network and its Applications, Tsinghua University Press, Beijing, (2000), pp.118-119.