ECT and LS-SVM Based Void Fraction Measurement of Oil-Gas Two-Phase Flow

Document Type : Research Article


1 School of Mechatronics Engineering, Lanzhou Jiaotong University, Lanzhou 730070, CHINA

2 School of Mechatronics Engineering, Lanzhou Jiaotong University, School of Mechatronics Engineering, Lanzhou Jiaotong University, Lanzhou 730070, CHINA730070, CHINA


A method based on Electrical Capacitance Tomography (ECT) and an improved Least Squares Support Vector Machine (LS-SVM) is proposed for void fraction measurement of oil-gas two-phase flow. In the modeling stage, to solve the two problems in LS-SVM, pruning skills are employed to make LS-SVM sparse and robust; then the Real-Coded Genetic Algorithm is introduced to solve the difficult problem of parameters selection in LS-SVM then. In the measurement process, the flow pattern of oil-gas two-phase flow is identified by using fast back-projection image reconstruction and a fuzzy pattern recognition technique and the void fraction is computed using the void fraction model corresponding to the identified flow pattern. Experimental results demonstrate that both the improvement of LS-SVM and the parameter optimization are effective. The results also show that the real-time performance of the proposed void fraction measurement method is good, and the measurement precision can satisfy the application requirement.  


Main Subjects

[1] Hewitt G.F., “Measurement of two phase flow parameters”, Academic Press,London, (1978).
[2] Huang Z.Y., Wang B.L. and Li H. Q., Application of Electrical Capacitance Tomography to the Void Fraction Measurement of Two-Phase Flow, IEEE Transactions on Instrumentation and Measurement, 52 ,p. 7 (2003).
[3] Vapnik V.N., “Statistical learning theory”, Wiley,New York, (1998).
[4] Suykens J.A.K. and Vandwalle J., Least Squares Support Vector Machine Classifiers, Neural Processing Letters, 9, p. 290 (1999).
[5] Cao L.J. and H Tay F.E., Support Vector Machine with Adaptive Parameters in Financial Time Series Forecasting, IEEE Transactions on neural networks, 14, p. 1506 (2003). 
[6] Wang B.L., Ji H.F., Huang Z.Y., Li H.Q., A High-Speed Data Acquisition System for ECT Based on the Differential Sampling Method, IEEE Sensors Journal, 5, p. 308 (2005).
[7] Xie D.L., Huang Z.Y., Ji H.F., Li H.Q., An Online Flow Pattern Identification System for Gas-Oil Two-Phase Flow Using Electrical Capacitance Tomography. IEEE Trans., Instrum. Meas., 55, p. 1833 (2006)
[8] Suykens J.A.K., De Brabanter J., Lukas L., Vandewalle J., Weighted Least Squares Support Vector Machines: Robustness and Sparse Approximation, Neurocomputing,48, p. 85 (2002).
[9] Chapelle O., Vapnik V.N., Bousquet O., Mukherjee S., Choosing Multiple Parameters for Support Vector Machines, Machine Learning, 46, p.131 (2002).
[10] Michalewicz, Z., “Genetic Algorithms + Data Structures = Evolution Programs”, Springer, Verlag (1992).
[11] Chuang C.C.,  Su S.F.,  Robust  Support  Vector Regression Networks for Function Approximation with Outliers, IEEE Transaction on Neural Networks, 13, P. 1322 (2002).
[12] Hwang J.N., Martin S.H., Martin M. R., Schimer J., Regression Modeling in Back-Propagation and Projection Pursuit Learning, IEEE Transactions on Neural Network, 5, p. 342 (1994).