Wet Gas Flow Regime Identification Based on WPT and PNN

Abstract:

A novel noninvasive approach to the online flow regime identification for wet gas flow in a horizontal pipeline is proposed. Research into the flow-induced vibration response for the wet gas flow was conducted, with the conditions of pipe diameter 50 mm, pressure from 0.25 MPa to 0.35 MPa, Lockhart-Martinelli parameter from 0.02 to 0.6, and gas Froude Number from 0.5 to 2.7. The flow-induced vibration signals were measured by a vibration transducer installed by outside wall of pipe, and then the normalized energy features from different frequency bands in the vibration signals were extracted through 4-scale wavelet package transform (WPT) with mother wavelet db7. A probabilistic neural network (PNN) classifier with the extracted features as inputs was developed to identify the three typical flow regimes including stratified wavy flow, annular mist flow, and slug flow for wet gas flow. The results show that the method can identify effectively flow regimes and its identification accuracy arrives at above 92.1%. The noninvasive measurement approach has great application prospect in online flow regime identification.

• Periodical: Applied Mechanics and Materials (Volumes 58-60)
• Pages: 262-267
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.58-60.262
• Online since: June 2011
• Authors: Chen Quan Hua, Yan Feng Geng
• Keywords: Flow Regime Identification, Flow-Induced Vibration, Probabilistic Neural Network, Wavelet Package Transform, Wet Gas Flow

References

[1] Richard Steven, Wet Gas Flow Metering With Gas Meter Technologies, Colorado Engineering Experiment Station, Inc., 2007: 1-40.

[2] G. Falcone, G.F. Hewitt, Multiphase Flow Metering: Current Trends and Future Developments, SPE 71474, 2001: 1-12.

DOI: 10.2118/71474-ms

[3] W.H. Liu, L.J. Guo, T.J. Wu. An experimental study on the flow characteristics of oil-water two-phase flow in horizontal straight pipes. Chinese Journal of Chemical Engineering, 2003, 11 (5): 491-496.

[4] B. Sun, H.J. Zhang, L. Chen, Y.X. Zhao. Flow regime identification of gas-liquid two-phase flow based on HHT. Chinese Journal of Chemical Engineering, 2006, 14 (1): 24-30.

DOI: 10.1016/s1004-9541(06)60033-5

[5] Y.L. Zhou, F. Chen, B. Sun. Identification Method of Gas-Liquid Two-phase Flow Regime Based Image Multi-feature Fusion and Support Vector Machine. Chinese Journal of Chemical Engineering, 2008, 16(6): 832-840.

DOI: 10.1016/s1004-9541(09)60002-1

[6] T. Tambouratzis a, I. Pázsit. Non-invasive on-line two-phase flow regime identification employing artificial neural networks. Annals of Nuclear Energy, 2009: 1-6.

DOI: 10.1016/j.anucene.2008.12.002

[7] C. Tan, F. Dong, M.M. Wu. Identification of gas/liquid two-phase flow regime through ERT-based measurement and feature extraction. Flow Measurement and Instrumentation, 2007(18): 255–261.

DOI: 10.1016/j.flowmeasinst.2007.08.003

[8] D.B. Robert, 1990, Flow Induced Vibrations, Van Nostrand Reihold, Second Edition, New York.

[9] A. Sengur, I. Turkoglu, M. Cevdet. Wavelet packet neural networks for texture classification. Expert Systems with Applications, 2007(32): 527-533.

DOI: 10.1016/j.eswa.2005.12.013

[10] H. Xiao, Z.Z. Wang, X.M. Ren. Classification of surface EMG signal using relative wavelet packet energy. Computer Methods and Programs in Biomedicine, 2005(79): 189-195.

DOI: 10.1016/j.cmpb.2005.04.001

[11] D.F. Specht. Probabilistic neural networks. Neural Networks, 1990(3): 109-118.

[12] T. Masters. Advanced Algorithms for Neural Networks. Wiley, New York, (1995).