基于卷积神经网络的气液两相流流型识别方法

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

系统仿真学报 ›› 2021, Vol. 33 ›› Issue (4): 883-891.doi: 10.16182/j.issn1004731x.joss.19-0619

基于卷积神经网络的气液两相流流型识别方法

仝卫国, 庞雪纯, 朱赓宏

华北电力大学自动化系,河北保定 071000

收稿日期:2019-11-26 修回日期:2020-01-28 出版日期:2021-04-18 发布日期:2021-04-14
作者简介:仝卫国(1967-),男,博士,副教授,研究方向为先进流量测量。E-mail：twg1018@163.com

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

Tong Weiguo, Pang Xuechun, Zhu Genghong

Department of Automation, North China Electric Power University, Baoding 071000, China

Received:2019-11-26 Revised:2020-01-28 Online:2021-04-18 Published:2021-04-14

摘要/Abstract

摘要： 针对两相流流型识别率不高且存在主观性的问题,提出一种基于Landweber迭代图像重建算法和卷积神经网络相结合的流型识别方法。利用Landweber迭代图像重建算法来获取流型图像并构建出流型图像数据库,通过对VGG16网络中不同的卷积层层数和不同尺寸及分辨率的数据集样本进行流型识别,确定了网络冻结卷积层和输入图片的参数。实验结果表明：采用电阻层析成像与卷积神经网络相结合的方法,使得流型识别准确率达到了95%,识别性能得到了提高。

关键词: 流型识别, 电阻层析成像, Landweber迭代, 图像重建算法, 卷积神经网络

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

中图分类号:

TP183

仝卫国, 庞雪纯, 朱赓宏. 基于卷积神经网络的气液两相流流型识别方法[J]. 系统仿真学报, 2021, 33(4): 883-891.

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.

参考文献

[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.

基于卷积神经网络的气液两相流流型识别方法

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

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张立峰, 王会忍. 基于卷积神经网络及有限元仿真的电容层析成像图像重建[J]. 系统仿真学报, 2022, 34(4): 712-718.
[2]	敖邦乾, 杨莎, 令狐金卿, 叶振环. 基于级联神经网络疲劳驾驶检测系统设计[J]. 系统仿真学报, 2022, 34(2): 323-333.
[3]	赵瑛, 陆耀, 张健, 梁启弟, 龙炜. 基于深度神经网络的多视角人体动作识别[J]. 系统仿真学报, 2021, 33(5): 1019-1030.
[4]	马榕, 陈秋瑞, 张晗, 梅铮, 王锐, 魏伟. 基于单目深度估计的低功耗视觉里程计[J]. 系统仿真学报, 2021, 33(12): 3001-3011.
[5]	黄欣, 方钰, 顾梦丹. 基于卷积神经网络的X线胸片疾病分类研究[J]. 系统仿真学报, 2020, 32(6): 1188-1194.
[6]	樊名鲁, 王艳, 纪志成. 基于特征生成的轴承不均衡数据故障诊断[J]. 系统仿真学报, 2020, 32(12): 2438-2448.
[7]	王红军, 黎邹邹, 邹湘军. 基于Adaboost与CNN的木材表面缺陷检测[J]. 系统仿真学报, 2019, 31(8): 1636-1645.
[8]	卢裕秋, 孙金玉, 马世伟. 基于深度卷积神经网络的运动目标检测方法[J]. 系统仿真学报, 2019, 31(11): 2275-2280.
[9]	石祥滨, 钟健, 刘翠微, 刘芳, 张德园. 小样本高光谱遥感图像深度学习方法[J]. 系统仿真学报, 2018, 30(7): 2744-2752.
[10]	夏旻, 申茂阳, 王舰锋, 王阳光. 基于卷积神经网络的卫星云图云量计算[J]. 系统仿真学报, 2018, 30(5): 1623-1630.
[11]	廖鹰, 易卓, 胡晓峰, 田园, 陶九阳. 基于三维卷积神经网络的战场聚集行为预测[J]. 系统仿真学报, 2018, 30(3): 801-808.
[12]	吴昀璞, 金炜东, 黄颖坤. 基于多域融合CNN的高速列车转向架故障检测[J]. 系统仿真学报, 2018, 30(11): 4492-4497.
[13]	高尚兵, 颉正, 潘志庚, 覃方哲, 李锐. 一种新的路面裂缝自动检测算法[J]. 系统仿真学报, 2017, 29(9): 2009-2015.
[14]	王松, 刘复昌, 黄骥, 许威威, 董洪伟. 基于卷积神经网络的深度图姿态估计算法研究[J]. 系统仿真学报, 2017, 29(11): 2618-2623.
[15]	朱丰, 胡晓峰, 贺筱媛, 孔亦思, 杨璐. 一种基于CNN的样本不足战场包围态势认知方法[J]. 系统仿真学报, 2017, 29(10): 2291-2300.