Abstract
According to the non-stationary characteristics of differential pressure fluctuation signals, a flow regime identification method based on wavelet packet energy feature and probabilistic neural network (PNN) is put forward in this paper. Firstly, original differential pressure fluctuation signals are decomposed into a finite number of different frequency band signals, and then the concept of wavelet packet energy entropy is proposed. The analysis results from wavelet packet energy entropy of different differential pressure fluctuation signals show that the energy of differential pressure fluctuation signals will change in different frequency bands when bearing flow regimes. Therefore, to identify flow regimes, energy feature extracted from a number of frequency band signals that contained the most dominant flow regime information could served as input probabilistic neural network. The analysis results form air-water two-phase flow in horizontal pipe four flow regimes show that the identify approach of PNN based on wavelet packet transform extracting the energy of different frequency bands as features can identify flow regimes accurately and effectively.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Mi, Y., Ishii, M.: Vertical Two-Phase Flow Recognition Using Advanced Instrumentation and Neural Networks. Nuclear Engineering and Design 184, 409–420 (1998)
Wu, H.-J., Zhou, F.-D., Wu, Y.-Y.: Intelligent identification system of flow regiem of oil-gas-water multiphasw flow. International Journal of Multiphase Flow 27(3), 459–475 (2001)
Jones, O.C., Zuber, N.: The interrelation between void fraction fluctuations and flow patterns in two-phase flow. International Journal of Multiphase Flow 2(3), 273–306 (1975)
Vince, M.A., Lahey, R.T.: On the development of and objective flow regime indicator. International Journal of Multiphase Flow 8(12), 93–124 (1982)
Costigan, G., Whalley, P.B.: Slug flow regime identification from dynamic void fraction measurements in vertical air-water flows. International Journal of Multiphase Flow 23(2), 263–282 (1997)
Lefeeri, H., Tsoukalas, M.I., Mi, Y.: A neurofuzzy methodology for impedance-based multiphase flow identification. Engineering Application Artificial Intelligence 10(6), 545–555 (1997)
He, Y.-Z., Shen, S., Ying, H.-Q., Liu, Z.-S.: Application of Wavelet Packet Decomposition and Its Energy Spectrum on The Fault Diagnosis of Reciprocation Machinery. Journal Vibration Engineering 14, 72–75 (2001)
Zhou, X.-K., Yan, P.-Q.: New Method Diagnosis of Railway Roller Bearing Based on The Wavelet Analysis. Journal of Tsinghua University(Sci. & Tech.) 36, 29–33 (1996)
Specht, D.F.: Probabilistic neural network. Neural Networks 31, 109–118 (1990)
Zhang, J.-H., Hou, G.-L., Sun, X., et al.: Research on Turbo generator Fault Diagnosis Using Probabilistic Neural Networks. Power Engineering 25(5), 698–701 (2005)
Ye, Z.-F., Sun, J.-G.: Probabilistic neural networks based engine fault diagnosis. Acta Aeronautica et Astronautica Sinica 23(2), 155–157 (2002)
Mao, K.Z., Tan, K.C., Ser, W.: Probabilistic neural network structure determination for pattern classification. IEEE Transactions on Neural Networks 11(4), 1009–1016 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bin, S., Hong, W. (2011). Identification Method of Gas-Liquid Two-Phase Flow Regime Based on Wavelet Packet Energy Feature and PNN. In: Jiang, L. (eds) Proceedings of the 2011 International Conference on Informatics, Cybernetics, and Computer Engineering (ICCE2011) November 19–20, 2011, Melbourne, Australia. Advances in Intelligent and Soft Computing, vol 112. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25194-8_71
Download citation
DOI: https://doi.org/10.1007/978-3-642-25194-8_71
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25193-1
Online ISBN: 978-3-642-25194-8
eBook Packages: EngineeringEngineering (R0)