Identification Method of Gas-Liquid Two-phase Flow Regime Based on Image Multi-feature Fusion and Support Vector Machine

Abstract

Abstract: The knowledge of flow regime is very important for quantifying the pressure drop,the stability and safety of two-phase flow systems.Based on image multi-feature fusion and support vector machine,a new method to identify flow regime in two-phase flow was presented.Firstly,gas-liquid two-phase flow images including bubbly flow,plug flow,slug flow,stratified flow,wavy flow,annular flow and mist flow were captured by digital high speed video systems in the horizontal tube.The image moment invariants and gray level co-occurrence matrix texture features were extracted using image processing techniques.To improve the performance of a multiple classifier system,the rough sets theory was used for reducing the inessential factors.Furthermore,the support vector machine was trained by using these eigenvectors to reduce the dimension as flow regime samples,and the flow regime intelligent identification was realized.The test results showed that image features which were reduced with the rough sets theory could excellently reflect the difference between seven typical flow regimes,and successful training the support vector machine could quickly and accurately identify seven typical flow regimes of gas-iquid two-phase flow in the horizontal tube.Image multi-feature fusion method provided a new way to identify the gas-liquid two-phase flow,and achieved higher identification ability than that of single characteristic.The overall identification accuracy was 100%,and an estimate of the image processing time was 8 ms for online flow regime identification.

Key words: flow regime identification, gas-liquid two-phase flow, image processing, multi-feature fusion, support vector machine

摘要： The knowledge of flow regime is very important for quantifying the pressure drop,the stability and safety of two-phase flow systems.Based on image multi-feature fusion and support vector machine,a new method to identify flow regime in two-phase flow was presented.Firstly,gas-liquid two-phase flow images including bubbly flow,plug flow,slug flow,stratified flow,wavy flow,annular flow and mist flow were captured by digital high speed video systems in the horizontal tube.The image moment invariants and gray level co-occurrence matrix texture features were extracted using image processing techniques.To improve the performance of a multiple classifier system,the rough sets theory was used for reducing the inessential factors.Furthermore,the support vector machine was trained by using these eigenvectors to reduce the dimension as flow regime samples,and the flow regime intelligent identification was realized.The test results showed that image features which were reduced with the rough sets theory could excellently reflect the difference between seven typical flow regimes,and successful training the support vector machine could quickly and accurately identify seven typical flow regimes of gas-iquid two-phase flow in the horizontal tube.Image multi-feature fusion method provided a new way to identify the gas-liquid two-phase flow,and achieved higher identification ability than that of single characteristic.The overall identification accuracy was 100%,and an estimate of the image processing time was 8 ms for online flow regime identification.

关键词: flow regime identification, gas-liquid two-phase flow, image processing, multi-feature fusion, support vector machine

ZHOU Yunlong, CHEN Fei, SUN Bin. Identification Method of Gas-Liquid Two-phase Flow Regime Based on Image Multi-feature Fusion and Support Vector Machine[J]. , 2008, 16(6): 932-840.

周云龙, 陈飞, 孙斌. Identification Method of Gas-Liquid Two-phase Flow Regime Based on Image Multi-feature Fusion and Support Vector Machine[J]. , 2008, 16(6): 932-840.

References

1 Dong, F., Jiang, Z.X., Qiao, X.T., Xu, L.A., “Application of electrical resistance tomography to two-phase flow parameters measurement”, Flow Meas. Instrum., 14, 183-192(2003).
2 Sun, B., Zhang, H.J., Chen, L., Zhao, Y.X., “Flow regime identification of gas-liquid two-phase flow based on HHT”, Chin. J. Chem. Eng., 14(1), 24-30(2006).
3 Mi, Y., Ishii, M., Tsoukalas, L.H., “Flow regime identification methodology with neural network and two-phase flow models”, Nucl. Eng. Des., 204(1), 87-100(2001).
4 Wu, H.J., Zhou, F.D., Wu, Y.Y., “Intelligent identification system of flow regime of oil-gas-water multiphase flow”, Int. J. Multiphase Flow, 27(3), 459-475(2001).
5 Liu, W.H., Guo, L.J., Wu, T.J., Zhang, X.M., “An experimental study on the flow characteristics of oil-water two-phase flow in horizontal straight pipes”, Chin. J. Chem. Eng., 11(5), 491-496(2003).
6 Sun, B., Zhou, Y.L., “Identification method of gas-liquid two-phase flow regime based on support vector machine and wavelet packet energy feature”, Proceedings of the CSEE, 25(17), 93-99(2005).(in Chinese)
7 Jia, Z.H., Niu, G., Wang, J., “Identification of gas-liquid flow regimes in a horizontal flow using neural network”, J. Hydrodyn. Ser. B, 17(1), 66-73(2005).
8 Zhou, Y.L., Wang, Q., Yang Z.H., Sun, B., Chen, X.B., Wang, L.Y., “Identification of gas-liquid two-phase flow pattern based on wavelet energy feature”, J. Chem. Ind. Eng.(China), 58(8), 1948-1954(2007).(in Chinese)
9 Hu, Z.H., Yang, Y.H., Liu, L., Zhou, F.D., “Local flow regime transition criteria of gas-liquid two-phase flow in vertical upward tube with a horizontal rod”, Chin. J. Chem. Eng., 14(4), 442-449(2006).
10 Jones, O.C., Zuber, N., “The interrelation between void fraction fluctuations and flow patterns in two-phase flow”, Int. J. Multiphase Flow, 2(3), 273-306(1975).
11 Vince, M.A., Lahey, R.T., “On the development of an objective flow regime indicator”, Int. J. Multiphase Flow, 8(12), 93-124(1982).
12 Costigan, G., Whalley, P.B., “Slug flow regime identification from dynamic void fraction measurements in vertical air-water flows”, Int. J. Multiphase Flow, 23(2), 263-282(1997).
13 Hulin, J.P., Fierfort, C., Condol, R., “Experimental study of vortex emission behind bluff obstacles in a gas liquid vertical two phase flow”, Int. J. Multiphase Flow, 8, 475-490(1982).
14 Yang, T., Cheng, Y.Y., Yuan, Y.S., “Local void fraction profile measuring by a capacitance probe under dense pulverized coal jet conditions for MHD combustor”, In:Proceedings of 1st International Symposium on Measurement Techniques for Multiphase Flows, Nanjing, 44-48(1995).
15 Bruun, H.H., Samways, A.L., “Hot-film measurements techniques in the two-phase flow”, In:Proceedings of 1st International Symposium on Measurement Techniques for Multiphase Flows, Nanjing, 49-56(1995).
16 Yang, Y.Z., Li, G.J., Zhou, F.D., Chen, X.J., “The effect of sudden change in pipe diameter on flow patterns of air-water two-phase flow in vertical pipe(I) Sudden-contraction cross-Section”, Chin, J. Chem. Eng., 9(1), 116-119(2001).
17 Xiao, N., Jin, N.D., “Research on flow pattern classification method of two phase flow based on chaotic attractor morphological characteristic”, Acta Phys. Sin., 56(9), 5149-5157(2007).
18 Dyakowski, T., “Process tomography applied to multi-phase flow measurement”, Meas. Sci. Tech., 7, 343-353(1996).
19 Banerjee, S., Lahey, R.T., “Advances in two-phase flow instrumentation”, Adv. Nucl. Sci. Tech., 13, 227-414(1981).
20 Kumar, R.A., Cook, R.L., Norton, O.P., Okhaysen, W.O., “Laser based cross-correlation technique for the determination of flow velocities in multiphase flows”, In:Proceedings of 1st International Symposium on Measurement Techniques for Multiphase Flows, Nanjing, 386-398(1995).
21 Lynch, G.F., Segal, S.L., “Direct measurement of the void fraction of a two-phase fluid by nuclear magnetic resonance”, Int. J. Mass Transfer, 20, 7-14(1977).
22 Dong, F., Liu, X.P., Deng, X., Xu, L.J., Xu, L.A., “Identification of two-phase flow regimes in horizontal, inclined and vertical pipes”, Meas. Sci. Tech., 12, 1069-1075(2001).
23 Kandlikar, S.G., Tian, S., Steinke, M.E., Campbell, L.A., “High-speed photographic observation of flow boiling of water in parallel mini-channels”, In:Proceedings of NHTC.01, 35th National Heat Transfer Conference, Anaheim, California, 1-10(2001).
24 Zhou, Y.L., Chen, F., Sun, B., “Identification method of gas-liquid two-phase flow regime based on gray level co-occurrence matrix and support vector machine”, J. Chem. Ind. Eng.(China), 58(9), 2232-2237(2007).(in Chinese)
25 Chen, F., Zhou, Y.L., Li, H.W., “Identification method of gas-liquid two-phase flow based on image moment invariants and SVM”, In:7th Int. Symp. Test & Measurement, Beijing, 2, 1318-1321(2007).
26 Zhou, Y.L., Chen, F., Liu, C., “Identification method of gas-liquid two-phase flow regime based on images processing and Elman neural network”, Proc. Chin. Soc. Elec. Eng., 27(29), 108-112(2007).(in Chinese)
27 Zhou, Y.L., Sun, B., “Identification method of gas-liquid two-phase flow patterns based on neural network and D-S evidential theory”, J. Chem. Ind. Eng.(China), 57(3), 607-613(2006).(in Chinese)
28 Hang, L.B., Zhang, H.J., Zhou, H.L., He, Q., “Flow regime identification of oil-water two-phase flow based on HHT and SVM”, J. Chem. Ind. Eng.(China), 58(3), 617-622(2007).(in Chinese)
29 Ha, Y.J., Ltu, Z.C., Hanratty, T.J., “A backlighted imaging technique for particle size measurements in two-phase flows”, Exp. Fluids, 25, 226-232(1998).
30 Shi, L.L., Cai, J.H., Zhou, Z.K., “Gas-liquid two-phase flow pattern identification based on image processing”, J. Zhejiang University(Eng. Sci., China), 39(8), 1128-1131(2005).(in Chinese)
31 Gonzalez, R.C., Woods, R.E., Digital Image Processing, 2nd edition, Prentice Hall, Upper Saddle River, N.J.(2002).
32 Hu, M.K., “Visual pattern recognition by moment invariants”, IEEE Trans. Info. Theory, 8, 179-187(1962).
33 Prokop, R.J., Reeves, A.P., “A survey of moment based techniques for unoccluded object representation and recognition”, Graph. Models Image Process., 54, 438-460(1992).
34 Haralick, R.M., Shanmugam, K., Dinstein, I., “Textural features for image classification”, IEEE Trans. Systems Man Cabernets, 3(6), 610-621(1973).
35 Haralick, R.M., “Statistical and structural approaches to texture”, Proc. IEEE, 67(5), 786-804(1979).
36 Pawlak, Z., “Rough sets”, Int. J. Comp. Sci., 11(5), 341-356(1982).
37 Pawlak, Z., Rough Sets:Theoretical Aspects of Reasoning about Data, Kluwer Academic Publishers, Boston(1991).
38 Li, C.B., Song, J.P., “A method of attribute reduction based on rough set”, J. Elec. Sci. Tech. China, 3(3), 234-237(2005).
39 Vapnik, V.N., The Nature of Statistical Learning Theory, Springer-Verlag, New York, 157-173(1995).
40 Cristianini, N., Shawe, T.J., Support Vector Machines and Other Kernel-Based Learning Methods, Cambridge University Press, England, 254-269(2000).
41 Hsu, C.W., Lin, C.J., “A comparison of methods for multiclass support vector machines”, IEEE Trans. Neural Networks, 13, 415-425(2002).
42 Kohonen, T., Oja, E., Simula, O., Visa, A., Kangas, J., “Engineering applications of the self-organizing map”, Proc. IEEE, 84(10), 1358-1384(1996).
43 Li, Q.H., Parameters and Application of Two-phase Flow, Zhejiang University Press, Hangzhou, 36-37(1991).(in Chinese).

[1]	Wenjuan Bai, Dianming Chu, Kuanxin Tang, Lei Geng, Yan Li, Yan He. The motion mechanism and characteristic of bubble in a pseudo-2D tapered fluidized bed [J]. Chinese Journal of Chemical Engineering, 2022, 46(6): 255-270.
[2]	Songsong Wang, Qiuxiang Bu, Deyu Luan, Ying Zhang, Longbin Li, Zhaorui Wang, Wenhao Shi. Study on gas-liquid flow characteristics in stirred tank with dual-impeller based on CFD-PBM coupled model [J]. Chinese Journal of Chemical Engineering, 2021, 38(10): 63-75.
[3]	Kexin Bi, Tong Qiu. An intelligent SVM modeling process for crude oil properties prediction based on a hybrid GA-PSO method [J]. Chinese Journal of Chemical Engineering, 2019, 27(8): 1888-1894.
[4]	Mohammad Mesbah, Ebrahim Soroush, Mashallah Rezakazemi. Development of a least squares support vector machine model for prediction of natural gas hydrate formation temperature [J]. , 2017, 25(9): 1238-1248.
[5]	Xing Wang, Jiao Sun, Jie Zhao, Wenyi Chen. Experimental detection of bubble-wall interactions in a vertical gas-liquid flow [J]. , 2017, 25(7): 838-847.
[6]	Jian Tang, Tianyou Chai, Zhuo Liu, Wen Yu. Selective ensemble modeling based on nonlinear frequency spectral feature extraction for predicting load parameter in ball mills [J]. Chin.J.Chem.Eng., 2015, 23(12): 2020-2028.
[7]	Kai Feng, Jiangang Lu, Jinshui Chen. Nonlinearmodel predictive control based on support vectormachine and genetic algorithm [J]. Chin.J.Chem.Eng., 2015, 23(12): 2048-2052.
[8]	Juan Chen, Xiaoyi Huang, Yanlei Qi, Xin Qi, Qing Guo. Process Optimization of Ultrasonic Extraction of Puerarin Based on Support Vector Machine [J]. Chin.J.Chem.Eng., 2014, 22(7): 735-741.
[9]	LI Shaobai, MA Youguang, ZHU Chunying, FU Taotao, LI Huaizhi. Turbulent Characteristic of Liquid Around a Chain of Bubbles in Non-Newtonian Fluid [J]. Chin.J.Chem.Eng., 2012, 20(5): 883-888.
[10]	FENG Xuying, YU Tao, WANG Jianlin. NonliNonlinear GPC with In-place Trained RLS-SVM Model for DOC Control in a Fed-batch Bioreactor^* [J]. Chin.J.Chem.Eng., 2012, 20(5): 988-994.
[11]	WANG Jianlin, FENG Xuying, YU Tao. A Geometric Approach to Support Vector Regression and Its Application to Fermentation Process Fast Modeling [J]. Chin.J.Chem.Eng., 2012, 20(4): 715-722.
[12]	HUA Chenquan, WANG Changming, GENG Yanfeng, SHI Tianming. Noninvasive Flow Regime Identification for Wet Gas Flow Based on Flow-induced Vibration [J]. , 2010, 18(5): 795-803.
[13]	LI Hongwei, ZHOU Yunlong, SUN Bin, YANG Yue. Multi-scale Chaotic Analysis of the Characteristics of Gas-Liquid Two-phase Flow Patterns [J]. , 2010, 18(5): 880-888.
[14]	WANG Jianlin, ZHAO Liqiang, YU Tao. On-line Estimation in Fed-batch Fermentation Process Using State Space Model and Unscented Kalman Filter [J]. , 2010, 18(2): 258-264.
[15]	GAO Xuejin, WANG Pu, QI Yongsheng, ZHANG Yating, ZHANG Huiqing, YAN Aijun. An Optimal Control Strategy Combining SVM with RGA for Improving Fermentation Titer [J]. , 2010, 18(1): 95-101.