基于卷积神经网络与门控循环单元的气液两相流流型识别方法

doi:10.3969/j.issn.1000-1158.2022.10.10

摘要
图/表
参考文献(17)
相关文章 (15)

全文: PDF (103131 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要提出了一种基于卷积神经网络(CNN)与门控循环单元(GRU)的垂直管道气液两相流流型识别方法。该方法基于电阻层析成像(ERT)系统的重建图像,对其填充处理后进行离散余弦变换(DCT),求取最大、最小 DCT 系数的差值,选取一定帧数长度数据作为网络输入,对流型进行识别。分析了输入序列长度对CNN-GRU、CNN 及 GRU 网络分类准确的影响,确定了最佳输入向量维度分别为 60、65 及 50,使用实验数据对3种网络进行训练、测试,结果表明,CNN-GRU网络分类准确率最高,平均流型识别准确率可达 99.40%。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	张立峰
	王智
	吴思橙

Abstract：The method for identifying the flow pattern of gas-liquid two-phase flow in a vertical pipeline based on convolutional neural network (CNN) and gated recurrent unit (GRU) is presented in this paper. Based on the reconstructed image by the electrical resistance tomography (ERT) system, the discrete cosine transform (DCT) is performed after the filling processing. The difference between the maximum and minimum DCT coefficients is calculated, and a certain frame length data are selected as the network input to identify the flow pattern. The influence of the length of the input sequence on the accuracy of CNN-GRU, CNN and GRU network classification is analyzed, and the optimal input vector dimensions are determined to be 60, 65 and 50. Using experimental data to train and test the CNN-GRU network, and compare it with the GRU and CNN networks, the results show that the CNN-GRU network has the highest classification accuracy, and the average flow pattern recognition accuracy rate can reach 99.40%.

Key words： metrology flow pattern recognition discrete cosine transform convolutional neural network gated recurrent unit electrical resistance tomography

PACS:	计量学
	流型识别
	离散余弦变换
	卷积神经网络
	门控循环单元
	电阻层析成像

基金资助:国家自然科学基金(61973115)

作者简介: 张立峰(1979-), 男, 江西临川人, 华北电力大学副教授, 博士, 主要从事多相流检测及电学层析成像技术方面的工作。Email:lifeng.zhang@ncepu.edu.cn

引用本文:

张立峰,王智,吴思橙. 基于卷积神经网络与门控循环单元的气液两相流流型识别方法[J]. 计量学报, 2022, 43(10): 1306-1312.
ZHANG Li-feng,WANG Zhi,WU Si-cheng. Flow Pattern Recognition of Gas-liquid Two-phase Flow Based on Convolutional Neural Network and Gated Recurrent Unit. Acta Metrologica Sinica, 2022, 43(10): 1306-1312.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2022.10.10 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2022/V43/I10/1306

［1］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. Study on flow pattern identification of gathering and transportation Riser Based on fusion characteristics of differential pressure signal［J］. Journal of Engineering Thermophysics, 2020, 41 (12): 3014-3019.
［2］李凯, 史宝成, 廖锐全, 等.基于脱离速度的垂直气液两相管流流型识别［J］. 机械设计, 2020, 37 (10): 53-58.
Li K, Shi B C, Liao R Q, et al. Flow pattern identification of vertical gas-liquid two-phase pipe flow based on separation velocity［J］. Mechanical design, 2020, 37 (10): 53-58.
［3］张立峰, 朱炎峰. 基于MO-PLP-ELM及电容层析成像的两相流流型辨识［J］. 计量学报, 2021, 42 (3): 334-338.
Zhang L F, Zhu Y F. Two phase flow pattern identification based on MO-PLP-ELM and electrical capacitance tomography［J］. Acta Metrologica Sinica, 2021,42 (3): 334-338.
［4］张立峰, 朱炎峰. 基于粒子群优化极限学习机及电容层析成像的两相流流型及其参数预测［ J］. 计量学报, 2020, 41 (12): 1488-1493.
Zhang L F, Zhu Y F. Two phase flow pattern and parameter prediction based on Particle Swarm Optimization Extreme Learning Machine and electrical capacitance tomography［J］. Acta metrologica Sinica, 2020,41 (12): 1488-1493.
［5］仝卫国, 朱赓宏. 基于多层感知器的气液两相流流型识别方法［J］. 热能动力工程, 2020, 35 (6): 116-122.
Tong W G, Zhu G H. Identification method of gas-liquid two-phase flow pattern based on multilayer perceptron［J］. Thermal power engineering, 2020,35 (6): 116-122.
［6］王小鑫, 王博, 陈阳正, 等. 基于电容层析成像技术重构图像的两相流流型识别［J］.计量学报, 2020, 41 (08): 942-946.
Wang X X, Wang B, Chen Y Z, et al. Two phase flow pattern recognition based on reconstructed image of electrical capacitance tomography［J］. Acta Metrologica Sinica, 2020, 41 (8): 942-946.
［7］马敏,孙颖,范广永. 基于深度信念网络的ECT图像重建算法［J］.计量学报, 2021, 42 (4): 0476-0482.
Ma M, Sun Y, Fan G Y. ECT Image Reconstruction Algorithm Based on Depth Belief Network［J］. Acta Metrologica Sinica, 2021, 42 (4): 0476-0482.
［8］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 W G, Pang X C, Zhu G H. Identification method of gas-liquid two-phase flow pattern based on convolution neural network［J］. Journal of system simulation, 2021, 33 (4): 883-891.
［9］Affonso R R W,Dam R S F, Salgado W L, et al. Flow regime and volume fraction identification using nuclear techniques, artificial neural networks and computational fluid dynamics［J］. Applied Radiation and Isotopes, 2020, 159: 109103.
［10］Zhang Y, Azman A N, Xu K W, et al. Two-phase flow regime identification based on the liquid-phase velocity information and machine learning ［J］. Experiments in Fluids, 2020, 61 (10): 212.
［11］Godfrey S N, Kuang B Y, Whidborne J F, et al. Nonintrusive classification of gas-liquid flow regimes in an S-shaped pipeline riser using a Doppler ultrasonic sensor and deep neural networks［J］. Chemical Engineering Journal, 2021, 403: 126401.
［12］张立峰, 王化祥. 基于SVM及电容层析成像的两相流流型识别［J］. 仪器仪表学报, 2009, 30 (04): 812-816.
Zhang L F, Wang H X. Two phase flow pattern recognition based on SVM and electrical capacitance tomography［J］. Journal of instrumentation, 2009,30 (4): 812-816.
［13］Salgado W L, Dam R S F, Salgado C M. Optimization of a flow regime identification system and prediction of volume fractions in three-phase systems using gamma-rays and artificial neural network［J］. Applied Radiation and Isotopes, 2021, 169: 109552.
［14］肖竹, 钱鑫, 蒋洪波, 等.基于双向RNN的私家车轨迹重构算法［J］.通信学报, 2020, 41 (12): 171-181.
Xiao Z, Qian X, Jiang H B, et al. Trajectory recons-truction algorithm of private car based on bidirectional RNN［J］. Acta communication Sinica, 2020,41 (12): 171-181.
［15］赵兵, 王增平, 纪维佳, 等.基于注意力机制的CNN-GRU短期电力负荷预测方法［J］. 电网技术, 2019, 43 (12): 4370-4376.
Zhao B, Wang Z P, Ji W J, et al. CNN-GRU short term power load forecasting method based on attention mechanism［J］. Power grid technology, 2019,43 (12): 4370-4376.
［16］林峰, 郭鹏, 刘旭斌. 基于叶片表面污垢预处理与CNN的风电机组叶片表面损伤识别［J］. 动力工程学报, 2020, 40 (12): 975-981.
Lin F, Guo P, Liu X B. Identification of wind turbine blade surface damage based on pretreatment of blade surface fouling and CNN ［J］. Journal of power engineering, 2020, 40 (12): 975-981.
［17］张立峰,戴力. 基于鲁棒正则化极限学习机的电容层析成像图像重建［J］.计量学报, 2022, 43 (8): 1044-1049.
Zhang L F, Dai L. Image Reconstruction Based on Robust Regularized Extreme Learning Machine for Electrical Capacitance Tomography［J］. Acta Metrologica Sinica, 2022, 43 (8): 1044-1049.