Gas-liquid Two-phase Flow Pattern Recognition Method Based on Convolutional Neural Network

doi:10.16182/j.issn1004731x.joss.19-0619

Abstract

Abstract: Aiming at the low recognition rate and subjectivity in two-phase flow pattern recognition, a method based on Landweber iterative image reconstruction algorithm and convolutional neural network is proposed. Landweber iterative image reconstruction algorithm is used to obtain the flow pattern images and build the flow pattern image database. By means of the flow pattern identification on, different convolution layers in VGG16 network and different size and resolution of the data set samples, the parameters of network frozen convolutional layer and input image are determined.The experimental results show that the combined method of resistance tomography and convolutional neural network makes the flow pattern recognition accuracy reach 95% and the recognition performance is improved.

Key words: flow pattern recognition, electrical resistance tomography, Landweber iteration, image reconstruction algorithm, convolutional neural network

CLC Number:

TP183

Tong Weiguo, Pang Xuechun, Zhu Genghong. Gas-liquid Two-phase Flow Pattern Recognition Method Based on Convolutional Neural Network[J]. Journal of System Simulation, 2021, 33(4): 883-891.

References

[1] 方立军, 刘玉东, 胡月龙. 基于复杂度的双接触式气液两相流流型识别研究[J]. 动力工程学报, 2017, 37(3): 218-223.
Fang Lijun, Liu Yudong, Hu Yuelong.Identification of Gas-Liquid Two-phase Flow Patterns in a Double-contact Absorber Based on Complexity Theory[J]. Journal of Power Engineering, 2017, 37(3): 218-223.
[2] 王莉莉, 刘洪波, 陈德运, 等. 自适应与附加动量BP神经网络的ECT流型辨识[J]. 哈尔滨理工大学学报, 2018, 23(1): 105-110.
Wang Lili, Liu Hongbo, Chen Deyun, et al.Identification of Flow Regimes Based on Adaptive Learning and Additional Momentum BP Neural Network for Electrical Capacitance Tomography[J]. Journal of Harbin University of Science and Technology, 2018, 23(1): 105-110.
[3] Li X N, Liu M Y, Ma Y L.Experiments and Meso-scale Modeling of Phase Holdups and Bubble Behavior in Gas-liquid-solid Mini-fluidized Beds[J]. Chemical Engineering Science (S0009-2509), 2018, 192: 725-738.
[4] 陈露阳, 尹佳雯, 孙志强, 等. 基于EEMD-Hilbert谱的气液两相流钝体绕流流型识别[J]. 仪器仪表学报, 2017, 38(10): 2536-2546.
Chen Luyang, Yin Jiawen, Sun Zhiqiang, et al.Flow Regime Identification of Gas-liquid Two-phase Flow with Flow Around Bluff-body Based on Based on EEMD-Hilbert Spectrum[J]. Chinese Journal of Instrumentation, 2017, 38(10): 2536-2546.
[5] 何永勃, 董玉珊, 薛荣荣. 基于交互式递归分析的两相流流型识别方法[J]. 系统仿真学报, 2019, 31(4): 720-726.
He Yongbo, Dong Yushan, Xue Rongrong.Recognition Method on Two-phase Flow Regime Based on Cross Recursive Analysis[J]. Journal of System Simulation, 2019, 31(4): 720-726.
[6] 翁润滢, 孙斌, 赵玉晓, 等. 基于自适应最优核和卷积神经网络的气液两相流流型识别方法[J]. 化工学报, 2018, 69(12): 5065-5072.
Weng Runying, Sun Bin, Zhao Yuxiao, et al.Identification of Gas-liquid Two-phase Flow Pattern Based on Adaptive Optimal Ker-nel and Convolutional Neural Network[J]. CIESC Journal, 2018, 69(12): 5065-5072.
[7] 高强, 孟格格. 基于卷积神经网络的绝缘子故障识别算法研究[J]. 电测与仪表, 2017, 54(21): 30-36.
Gao Qiang, Meng Gege.Research of a Faulted Insulator Identification Algorithm Based on Convolution Neural Network[J]. Electrical Measurement & Instrumentation, 2017, 54(21): 30-36.
[8] Szegedy C, Liu W, Jia Y, et al.Going Deeper With Convolutions[J]. IEEE Computer Society(S1063-6919), 2014.
[9] 张建国, 马福昌, 窦银科. 层析成像在冰水两相流参数测量中的应用[J]. 光学精密工程, 2013, 21(8): 1981-1987.
Zhang Jianguo, Ma Fuchang, Dou Yinke.Application of Electrical Resistance Tomography to Ice-water Two-phase Flow Parameter Measurement[J]. Optics and Precision Engineering, 2013, 21(8): 1981-1987.
[10] 谭超. 基于多传感器融合的两相流参数测量方法[D]. 天津: 天津大学, 2010.
Tan Chao.Multisensor Fusion Based Measurement on Two-Phase Flow Parameters[D]. Tianjin: Tianjin University, 2010.
[11] 张立峰, 王化祥. 一种修正的电阻层析成像Landweber迭代算法[J]. 计量学报, 2016, 37(3): 271-274.
Zhang Lifeng, Wang Huaxiang.A Modified Landformer Algorithm for Electrical Resistance Tomography[J]. Acta Metrologica Sinica, 2016, 37(3): 271-274.
[12] Simonyan K, Zisserman A.Very Deep Convolutional Networks for Large-Scale Image Recognition[J]. Computer Science (S2333-9721), 2014.
[13] 王枫, 刘青山. 基于双卷积神经网络的行人精细化识别[J]. 中国科技论文, 2017, 12(14) : 1578-1582.
Wang Feng, Liu Qingshan.Fine Pedestrians Recognition Based on Double Convolutional Neural Network[J]. Chinese Journal of Scientific and Technical Papers, 2017, 12(14): 1578-1582.
[14] Lev G, Sadeh G, Klein B, et al.RNN Fisher Vectors for Action Recognition and Image Annotation[J]. Computer Science (S2333-9721), 2016.
[15] 张天琦. 基于深度学习的行人流量统计算法研究[D]. 哈尔滨: 哈尔滨工业大学, 2017.
Zhang Tianqi.Research on Pedestrian Flow Statistics Algorithm Based on Deep Learning[D]. Harbin: Harbin Institute of Technology, 2017.