Flow pattern identification method based on multi-feature extraction and GWO-SVM for gas-liquid two-phase flow

doi:10.11949/0438-1157.20240303

Abstract

Abstract:

Flow pattern identification of gas-liquid two-phase flow plays an important role in the improvement of production capacity and efficiency of petrochemical industry. The nonlinear and non-stationary characteristics of conductance fluctuation signal lead to the difficulty of feature extraction and affect the accuracy of flow pattern identification of gas-liquid two-phase flow. Aiming at this problem, a new flow pattern identification method which combines multi-feature extraction with a grey wolf algorithm optimized support vector machine (GWO-SVM) is proposed in this work. In the research, statistical analysis and approximate entropy analysis are used to extract statistical features and normalized approximate entropy features of the conductance fluctuation signals. And the two different kinds of features are combined to form a dataset. Then, to improve the accuracy of flow pattern identification, grey wolf optimization (GWO) algorithm is used to optimize the support vector machine (SVM) model. The gas-liquid two-phase flow pattern recognition experiment showed that the proposed method has higher recognition accuracy than the SVM, PSO-SVM and GA-SVM methods, and the average flow pattern recognition rate reached 98.45%.

Key words: two-phase flow, flow identification, multi-feature extraction, support vector machine

摘要：

气液两相流流型识别对提高石油化工行业产能和生产效率具有重要作用。针对气液两相流电导波动信号的强非线性和非平稳特性导致特征提取困难、影响流型识别精度的问题，提出了一种基于多特征混合与灰狼算法优化支持向量机（GWO-SVM）气液两相流流型识别方法。研究中，分别采用统计分析法和熵分析法对电导波动信号的不同统计特征和归一化近似熵特征进行提取，并将两类特征混合构成数据集，再利用灰狼算法（GWO）对支持向量机（SVM）模型进行优化，以提高流型识别精度。气液两相流流型识别实验表明，所提方法比SVM、PSO-SVM和GA-SVM方法具有更高的识别精度，流型平均识别率达到98.45%。

关键词: 两相流, 流型识别, 多特征提取, 支持向量机

CLC Number:

O 359.1

Yanyan SHI, Zhen YANG, Meng WANG, Jigen XIA. Flow pattern identification method based on multi-feature extraction and GWO-SVM for gas-liquid two-phase flow[J]. CIESC Journal, 2024, 75(10): 3536-3547.

施艳艳, 杨珍, 王萌, 夏济根. 基于多特征混合与GWO-SVM的气液两相流流型识别方法[J]. 化工学报, 2024, 75(10): 3536-3547.

Figures/Tables 14

Fig.1 Gas-liquid two-phase flow in a horizontal pipe based on RSCS

Fig.2 Flow patterns of gas-liquid two-phase flow in a horizontal pipe

Fig.3 Conductance fluctuation signals obtained by RSCS

Fig.4 Statistical feature parameters of the five flow patterns

Table 1 Distribution of statistical feature parameters of the five flow patterns

流型	标准差	振幅因数	波形因数	冲击因数	裕度因数	能量
泡状流	0.01~0.02	1.17~1.24	1.000~1.002	1.17~1.29	3.70~3.98	377~413
长塞流	0.04~0.69	1.16~2.39	1.008~1.136	1.18~2.49	0.62~6.17	423~27221
塞状流	0.02~0.30	1.15~2.19	1.003~1.124	1.15~2.42	3.06~5.75	249~1857
塞状-分层流	0.02~0.62	1.05~1.77	1.000~1.155	1.05~1.87	0.48~3.03	1048~20978
分层流	0.46~0.69	1.27~1.71	1.010~1.030	1.30~1.76	0.41~0.58	36801~45786

Fig.5 Decomposition based on CEEMDAN

Fig.6 Correlation coefficients between IMF components in the CEEMDAN decomposition and original signal

Fig.7 Process of feature fusion

Fig.8 Position update of grey wolf in the GWO algorithm

Fig.9 GWO-SVM model

Table 2 The number of samples of different flow patterns

流型	训练样本	测试样本	样本占比/%
合计	454	194	100
泡状流	95	40	20.8
长塞流	126	54	27.8
塞状流	126	54	27.8
塞状-分层流	76	32	16.7
分层流	31	14	6.9

Fig.10 Identification results of different flow patterns with different feature parameters

Table 3 Identification accuracy of different classifier

分类器	识别率/%
SVM	91.75
GA-SVM	96.91
PSO-SVM	96.39
GWO-SVM	98.45

Fig.11 Confusion matrix of different classifiers

References 36

1	谭超, 董峰. 多相流过程参数检测技术综述[J]. 自动化学报, 2013, 39(11): 1923-1932.
	Tan C, Dong F. Parameters measurement for multiphase flow process[J]. Acta Automatica Sinica, 2013, 39(11): 1923-1932.
2	Zenner A, Fiaty K, Bellière-Baca V, et al. Effective heat transfers in packed bed: experimental and model investigation[J]. Chemical Engineering Science, 2019, 201: 424-436.
3	何万媛, 陈一宇, 朱春英, 等. 阵列凸起微通道内气液两相传质特性研究[J]. 化工学报, 2023, 74(2): 690-697.
	He W Y, Chen Y Y, Zhu C Y, et al. Study on gas-liquid mass transfer characteristics in microchannel with array bulges[J]. CIESC Journal, 2023, 74(2): 690-697.
4	姚添, 郭烈锦, 徐强, 等. 基于压差信号融合特征的集输立管流型识别研究[J]. 工程热物理学报, 2020, 41(12): 3014-3019.
	Yao T, Guo L J, Xu Q, et al. Investigation on flow regimes recognition in pipeline-riser based on fusion features of differential pressure signals[J]. Journal of Engineering Thermophysics, 2020, 41(12): 3014-3019.
5	Li X Y, Li L X, Ma W M, et al. Two-phase flow patterns identification in porous media using feature extraction and SVM[J]. International Journal of Multiphase Flow, 2022, 156: 104222.
6	杨蕊, 朱宝锦, 吕超, 等. 脉动条件下旋流场内气液两相流流型及其转变机理[J]. 化工学报, 2022, 73(10): 4389-4398.
	Yang R, Zhu B J, Lyu C, et al. Study on flow pattern and transition mechanism of gas-liquid two-phase flow in swirl field under pulsating flow[J]. CIESC Journal, 2022, 73(10): 4389-4398.
7	Tan C, Dong F, Wu M M. Identification of gas/liquid two-phase flow regime through ERT-based measurement and feature extraction[J]. Flow Measurement and Instrumentation, 2007, 18(5/6): 255-261.
8	Li W S, Xu Q, Wang Y, et al. Intelligent identification of two-phase flow patterns in a long pipeline-riser system[J]. Flow Measurement and Instrumentation, 2022, 84: 102124.
9	Abbagoni B M, Yeung H. Non-invasive classification of gas-liquid two-phase horizontal flow regimes using an ultrasonic Doppler sensor and a neural network[J]. Measurement Science and Technology, 2016, 27(8): 084002.
10	Liu W L, Tan C, Dong F. Doppler spectrum analysis and flow pattern identification of oil-water two-phase flow using dual-modality sensor[J]. Flow Measurement and Instrumentation, 2021, 77: 101861.
11	Manjrekar O N, Dudukovic M P. Identification of flow regime in a bubble column reactor with a combination of optical probe data and machine learning technique[J]. Chemical Engineering Science: X, 2019, 2: 100023.
12	孙斌, 段晓松, 周云龙. 双谱核主元分析在气液两相流流型识别中的应用[J]. 化工学报, 2009, 60(4): 855-863.
	Sun B, Duan X S, Zhou Y L. Application of bispectrum KPCA in identification of gas-liquid two-phase flow regime[J]. CIESC Journal, 2009, 60(4): 855-863.
13	Wu B, Ribeiro A S, Firouzi M, et al. Use of pressure signal analysis to characterise counter-current two-phase flow regimes in annuli[J]. Chemical Engineering Research and Design, 2020, 153: 547-561.
14	孙庆明, 张博, 张海. 基于复杂网络的气液两相流流型识别与动力学特性分析[J]. 大连理工大学学报, 2015, 55(5): 470-477.
	Sun Q M, Zhang B, Zhang H. Flow pattern identification and dynamics characteristics analyses for gas-liquid two-phase flow in complex network[J]. Journal of Dalian University of Technology, 2015, 55(5): 470-477.
15	朱军, 刘嘉勇, 张腾飞, 等. 基于情感词典和集成学习的情感极性分类方法[J]. 计算机应用, 2018, 38(S1): 95-98, 107.
	Zhu J, Liu J Y, Zhang T F, et al. Sentiment polarity classification method based on sentiment dictionary and ensemble learning[J]. Journal of Computer Applications, 2018, 38(S1): 95-98, 107.
16	Gui R Z, Chen T J, Nie H. Classification of task-state fMRI data based on circle-EMD and machine learning[J]. Computational Intelligence and Neuroscience, 2020, 2020: 7691294.
17	赵翰学, 张咪, 郭岩宝, 等. 基于机器学习的管道金属损失缺陷识别方法[J]. 石油机械, 2020, 48(12): 138-145.
	Zhao H X, Zhang M, Guo Y B, et al. Recognition method of pipeline metal loss defects based on machine learning[J]. China Petroleum Machinery, 2020, 48(12): 138-145.
18	Liang F C, Hang Y, Yu H, et al. Identification of gas-liquid two-phase flow patterns in a horizontal pipe based on ultrasonic echoes and RBF neural network[J]. Flow Measurement and Instrumentation, 2021, 79: 101960.
19	Chu W J, Liu Y, Pan L Q, et al. Identification of boiling flow pattern in narrow rectangular channel based on TFA-CNN combined method[J]. Flow Measurement and Instrumentation, 2022, 83: 102086.
20	王云辉, 王丹丹, 王彬, 等. 基于机器学习模型的气液两相流流型识别技术研究[J]. 石油工程建设, 2023, 49(6): 53-58.
	Wang Y H, Wang D D, Wang B, et al. Research on gas-liquid two-phase flow pattern identification technology based on machine learning model[J]. Petroleum Engineering Construction, 2023, 49(6): 53-58.
21	张立峰, 王智, 张启亮. 基于多层加权复杂网络的气液两相流流型分析[J]. 计量学报, 2023, 44(5): 735-742.
	Zhang L F, Wang Z, Zhang Q L. Gas-liquid two-phase flow pattern analysis based on multilayer weighted complex network[J]. Acta Metrologica Sinica, 2023, 44(5): 735-742.
22	Trafalis T B, Oladunni O, Papavassiliou D V. Two-phase flow regime identification with a multiclassification support vector machine (SVM) model[J]. Industrial & Engineering Chemistry Research, 2005, 44(12): 4414-4426.
23	Nnabuife S G, Pilario K E S, Lao L Y, et al. Identification of gas-liquid flow regimes using a non-intrusive Doppler ultrasonic sensor and virtual flow regime maps[J]. Flow Measurement and Instrumentation, 2019, 68: 101568.
24	Li K, Wang L Y, Wu J J, et al. Using GA-SVM for defect inspection of flip chips based on vibration signals[J]. Microelectronics Reliability, 2018, 81: 159-166.
25	Van M, Hoang D T, Kang H J. Bearing fault diagnosis using a particle swarm optimization-least squares wavelet support vector machine classifier[J]. Sensors, 2020, 20(12): 3422.
26	Ying S S, Sun Y C, Fu C T, et al. Grey wolf optimization based support vector machine model for tool wear recognition in fir-tree slot broaching of aircraft turbine discs[J]. Journal of Mechanical Science and Technology, 2022, 36(12): 6261-6273.
27	Tan C, Dai W, Wu H, et al. A conductance ring coupled cone meter for oil-water two-phase flow measurement[J]. IEEE Sensors Journal, 2014, 14(4): 1244-1252.
28	施艳艳, 董峰, 谭超. 两相流测量中环形电导传感器特性研究[J]. 中国电机工程学报, 2010, 30(17): 62-66.
	Shi Y Y, Dong F, Tan C. Characteristic of ring-shaped conductance sensor in two-phase flow measurement[J]. Proceedings of the CSEE, 2010, 30(17): 62-66.
29	周云龙, 孙斌, 陈飞. 气液两相流型智能识别理论及方法[M]. 北京: 科学出版社, 2007: 27-31.
	Zhou Y L, Sun B, Chen F. Theory and Method of Intelligent Identification of Gas-Liquid Two-Phase Flow Pattern[M]. Beijing: Science Press, 2007: 27-31.
30	Dong F, Zhang S, Shi X W, et al. Flow regimes identification-based multidomain features for gas-liquid two-phase flow in horizontal pipe[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 7502911.
31	李昕, 蔡二娟, 田彦秀, 等. 一种改进脑电特征提取算法及其在情感识别中的应用[J]. 生物医学工程学杂志, 2017, 34(4): 510-517, 528.
	Li X, Cai E J, Tian Y X, et al. An improved electroencephalogram feature extraction algorithm and its application in emotion recognition[J]. Journal of Biomedical Engineering, 2017, 34(4): 510-517, 528.
32	Li H Q, Feng X L, Cao L, et al. A new ECG signal classification based on WPD and ApEn feature extraction[J]. Circuits, Systems, and Signal Processing, 2016, 35(1): 339-352.
33	肖俊青, 金江涛, 李春, 等. 基于CEEMDAN模糊熵CNN轴承故障诊断研究[J]. 机械强度, 2023, 45(1): 26-33.
	Xiao J Q, Jin J T, Li C, et al. Research on bearing fault diagnosis based on ceemdan fuzzy entropy and convolutional neural network[J]. Journal of Mechanical Strength, 2023, 45(1): 26-33.
34	Shu L, Deng H B, Liu X M, et al. A comprehensive working condition identification scheme for rolling bearings based on modified CEEMDAN as well as modified hierarchical amplitude-aware permutation entropy[J]. Measurement Science and Technology, 2022, 33(7): 075111.
35	Yang Y, Li S S, Li C, et al. Research on ultrasonic signal processing algorithm based on CEEMDAN joint wavelet packet thresholding[J]. Measurement, 2022, 201: 111751.
36	Mirjalili S, Mirjalili S M, Lewis A. Grey wolf optimizer[J]. Advances in Engineering Software, 2014, 69: 46-61.

[1]	He ZHU, Yi ZHANG, Nana QI, Kai ZHANG. Effect of particle viscosity in two-fluid model on homogeneous liquid-solid fluidization under Euler-Euler framework [J]. CIESC Journal, 2024, 75(9): 3103-3112.
[2]	Hao TANG, Dinghua HU, Qiang LI, Xuanchang ZHANG, Junjie HAN. Numerical and visualization study on dynamic behavior of bubbles in anti-acceleration double tangent arc channel [J]. CIESC Journal, 2024, 75(9): 3074-3082.
[3]	Liang ZHAO, Yuqiao LI, De ZHANG, Shengqiang SHEN. Experimental study of internal and external field characteristics of spiral nozzle [J]. CIESC Journal, 2024, 75(8): 2777-2786.
[4]	Yanxi LI, Yechun WANG, Xiangdong XIE, Jinzhi WANG, Jiang WANG, Yu ZHOU, Yingxiu PAN, Wentao DING, Liejin GUO. Study on separation characteristics and structure optimization of a volute type multi-channel gas-liquid cyclone separator [J]. CIESC Journal, 2024, 75(8): 2875-2885.
[5]	Qingjie YU, Honghai YANG, Yuhao LIU, Haizhou FANG, Weiqi HE, Jun WANG, Xincheng LU. Wavelet analysis and flow pattern identification in pulsating heat pipes based on temperature signals [J]. CIESC Journal, 2024, 75(7): 2497-2504.
[6]	Xiaoping LUO, Yuntian HOU, Yijie FAN. Flow boiling heat transfer and temperature uniformity in micro-channel with countercurrent phase separation structure [J]. CIESC Journal, 2024, 75(7): 2474-2485.
[7]	Zhicheng DENG, Shifeng XU, Qidong WANG, Jiarui WANG, Simin WANG. Process and energy consumption analysis of high salt and high COD wastewater treatment by submerged combustion [J]. CIESC Journal, 2024, 75(3): 1000-1008.
[8]	Xiaobin ZHAN, Huibin WANG, Yalong JIANG, Tielin SHI. Research on power consumption characteristics of high viscosity fluid mixing in acoustic resonance mixer [J]. CIESC Journal, 2024, 75(2): 531-542.
[9]	Shirong SONG, Hongchen LIU, Xiaotian MI, Chao XU, Mei YANG, Chaoqun YAO. Experimental investigation of droplet formation in coaxial microchannels with different geometries of inner channel [J]. CIESC Journal, 2024, 75(2): 566-574.
[10]	Haoran ZHAO, Siluo HUANG, Mei LIN. Sedimentation characteristics of the bottom surface of the inlet pipe box of a waste heat boiler [J]. CIESC Journal, 2024, 75(10): 3464-3476.
[11]	Yizhou CUI, Chengxiang LI, Linxiao ZHAI, Shuyu LIU, Xiaogang SHI, Jinsen GAO, Xingying LAN. Comparative study on the flow and mass transfer characteristics of sub-millimeter bubbles and conventional bubbles in gas-liquid two-phase flow [J]. CIESC Journal, 2024, 75(1): 197-210.
[12]	Yao ZHOU, Xiaoping YANG, Yicheng NI, Jiping LIU, Jinjia WEI, Junjie YAN. Numerical simulation of two-phase steam ejector applied in novel loop heat pipe [J]. CIESC Journal, 2024, 75(1): 268-278.
[13]	Shaohua ZHOU, Feilong ZHAN, Guoliang DING, Hao ZHANG, Yanpo SHAO, Yantao LIU, Zheming GAO. Experimental study of flow noise in short tube throttle valve and noise reduction measures [J]. CIESC Journal, 2023, 74(S1): 113-121.
[14]	Mingkun XIAO, Guang YANG, Yonghua HUANG, Jingyi WU. Numerical study on bubble dynamics of liquid oxygen at a submerged orifice [J]. CIESC Journal, 2023, 74(S1): 87-95.
[15]	Kaijie WEN, Li GUO, Zhaojie XIA, Jianhua CHEN. A rapid simulation method of gas-solid flow by coupling CFD and deep learning [J]. CIESC Journal, 2023, 74(9): 3775-3785.