气力提升装置流型对气液流动特性及提升系统性能均有很大的影响，但由于气液两相交界面形态以及截面含气率动态变化、气液两相速度复杂难测等原因，致使提升管流型亦交替变化且不易识别。针对这一难题，提出了基于小波包分析与Elman神经网络的流型辨识策略：利用小波包分析方法提取提升装置压差信号各频带能量特征值，借助Elman神经网络辨识技术，以各频带能量为Elman网络输入变量，以流型为输出变量，通过对Elman神经网络进行大量数据训练。从而对提升系统流型进行辨识。实验结果表明，该方法对流型辨识精度达到了92.6%，比BP 网络高6.5%，能有效对提升管流型进行辨识。
Abstract
Airlift device’s flow pattern has great influence on the performance of gas-liquid flow and the lifting system. However, because of the unpredictable gas-liquid speed and the dynamic interface morphology , section gas ratio, the flow pattern in the lift pipe alternate changes and becomes very difficult to identify. Considering about this problem, a flow pattern identification strategy was put forward based on wavelet packet and Elman neural network: the pressure signal’s frequency band energy eigenvalues were extracted by wavelet packet analysis. Then, with the help of Elman neural network identification technology, the frequency band energy was taken as the network’s input variable, the flow pattern was taken as the output variable. After that, a lot of experimental data were used to train the Elman neural network. At last, the flow pattern were effectively identified by this neural network. Experimental results show that, this method’s identification accuracy reached 92.6%, 6.5% higher than the BP network. All of these proved that this method can effectively identify the flow pattern .
关键词
提升装置； /
流型； 辨识； /
小波包； Elman神经网络
{{custom_keyword}} /
Key words
Airlift device; /
Flow pattern; /
Identification; /
Wavelet packet ; /
Elman neural network
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 胡东,唐川林,张风华等.钻孔水力开采用气力提升装置模型的建立及实验研究[J].煤炭学报，2012.37(3):522-527.
HU Dong,TANG Chuan-lin,ZHANG Feng-hua.Theoretical model and experimental research of airlift device in borehole hydraulic jet mining[J]. Journal of China Coal Society, 2012.37(3):522-527.
[2] 赵德喜,曹学文.基于超声波技术的水平管气液两相流流型识别方法[J].油气储运,2014,33(2):165~171
ZHAO Dexi,CAO Xuewen.Identification method of gas-liquid two-phase flow pattern of horizontal pipe based on ultrasonic technology[J].Oil & Gas Storage and Transportation, 2014,33(2):165~171.
[3] Saisorn S, Wongwises S. Flow pattern, void fraction and pressure drop of two-phase air-water flow in a horizontal circular micro-channel[J]. Experimental Thermal and Fluid Science. 2008, 32(3): 748-760.
[4] Triplett K A,Ghiaasiaan S M, Abdel-khalik S I, et al. Gas-liquid two-phase flow in microchannels Part II: void fraction and pressure drop [J]. International Journal of Multiphase Flow. 1999, 25(3):395-410.
[5] 肖荣鸽，魏炳乾，沙海涛等.气液两相段塞流的PSD和PDF特征分析[J].西安石油大学学报（自然科学报）,2012,27(5):58-62.
XIAO Rong-ge,WEI Bing-qian, SHA Hai-tao.Analysis of the PSD and PDF characteristics of gas-liquid slug flow[J].Journal of Xi’an Shiyou University(Natural Science Edition), 2012,27(5):58-62.
[6] 李文升, 郭烈锦.集输立管内气水两相流压差信号的特征分析[J].工程热物理学报,2015,36(6):1247~1251.
LI Wen-Sheng,GUO Lie-Jin.Analysis on the Signal Features of Differential Pressure for Air-Water Two Phase Flow in Pipeline-Riser System[J].Journal of Engineering Thermophysics, 2015,36(6):1247~1251.
[7] 李常伟,曹夏昕,孙立成.竖直窄矩形通道气液两相流流型识别研究[J].原子能科学技术,2012,46(9):1055~1060.
LI Chang-wei, CAO Xia-xin, SUN Li-cheng. Identification and Study of Flow Patterns in Narrow Vertical Rectangular Channel[J].Atomic Energy Science and Technology,2012,46(9):1055~1060.
[8] 孙斌,刘彤,赵鹏.基于EEMD气液两相流差压信号时频分析[J].实验流体力学,2014,28(5):47~52.
Sun Bin,Liu Tong,Zhao Peng.Time-frequency analysis on differential pressure signal of two-phase flow based on EEMD[J].Journal of Experiments in Fluid Mechanics,2014,28(5):47~52.
[9] 周云龙,顾杨杨.基于独立分量分析和RBF神经网络的气液两相流流型识别[J].化工学报,2012,63(3):796~799.
ZHOU Yunlong,GU Yangyang.Flow regime identification of gas/liquid two-phase flow based ICA and RBF neural networks[J].CIESC Journal, 2012,63(3):796~799.
[10] 胡东,唐川林,张凤华.进气方式增强气力提升作用的研究[J].水动力学研究与进展A辑,2012,27(4):456-463.
HU Dong,TANG Chuan-lin,ZHANG Feng-hua.Effect of air admission way on improving airlift[J].Chinese Journal of Hydrodynamics,2012,27(4):456-463.
[11] 张华,刘玥波.基于小波包和支持向量机的ERT系统流型识别[J].吉林建筑工程学院学报,2012,29(1):83-85.
ZHANG Hua, LIU Yue-bo.Flow Regime Identification of Electrical Resistance Tomography System Based on Wavelet Packet and Support Vector Machine[J].Journal of Jilin Architectural and Civil Engineering,2012,29(1):83-85.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(2129 KB)
