基于BP神经网络的集输-立管系统气液两相流流量测量
|
摘要
针对海洋油气采输工业中集输-立管内气液两相流流量测量问题,在大型集输-立管实验环路上采集立管底部、顶部压力波动信号,提取其绝对值均值、绝对值方差、偏态系数、峰态系数,结合本征模函数(IMF)的高、中、低3个频段上的能量分数,构建了一个包含7个特征参数的BP神经网络测量模型。设计了集成化网络结构,在宽广的流型范围内,以最小均方误差算法(LMS)为基础,引入动量因子α和学习率自适应调节进行算法优化。集成网络预测的气相平均相对误差E_(MR)和均方根相对误差E_(RMS)分别为4.67%、4.91%,液相分别为5.83%、5.87%。
To solve the problem of gas-liquid two phase flow metering in pipeline riser system,pressure signals at bottom and top of the riser were measured in large pipeline-riser experimental loop.The Mean of absolute value,variance of absolute value,skewness and kurtosis of pressure signals were calculated as well as the energy fractions of intrinsic mode function(IMF)of high,medium,and low frequency bands to construct a neural network including seven feature vector parameters.Based on least mean square algorithm(LMS),an integrated neural network was designed,which was optimized by momentum factor and an adaptive adjustment learning rate in a wide range of flow regime.The mean relative error(E_(MR)) and the standard error(E_(RMS)) of the integrated network for gas flow rate were 4.67% and 4.91%,respectively.For liquid flow,they were 5.83% and 5.87%,respectively.
To solve the problem of gas-liquid two phase flow metering in pipeline riser system,pressure signals at bottom and top of the riser were measured in large pipeline-riser experimental loop.The Mean of absolute value,variance of absolute value,skewness and kurtosis of pressure signals were calculated as well as the energy fractions of intrinsic mode function(IMF)of high,medium,and low frequency bands to construct a neural network including seven feature vector parameters.Based on least mean square algorithm(LMS),an integrated neural network was designed,which was optimized by momentum factor and an adaptive adjustment learning rate in a wide range of flow regime.The mean relative error(E_(MR)) and the standard error(E_(RMS)) of the integrated network for gas flow rate were 4.67% and 4.91%,respectively.For liquid flow,they were 5.83% and 5.87%,respectively.
引文
[1] 许晓英,赵庆凯,陈丰波,等.多相流量计在国内市场的应用及发展趋势[J].石油与天然气化工,2016,46(9):99-104.XU Xiao-ying,ZHAO Qing-kai,CHEN feng-bo,et al.Application and developments trend of multiphase flow meter in the domestic market[J].Petroleum and Natural Gas Industry,2016,46(9):99-104.
[2] PIROUZPANAH S,?EVIK M,MORRISON G L.Multi-phase flow measurement using coupled slotted orifice plate and swirl flow meter[J].Flow Measurement and Instrumentation,2014,40:157-161.
[3] LEEUNGCULSATIEN T,LUCAS G P.Measurement of velocity profiles in multiphase flow using a multi-electrode electromagnetic flow meter[J].Flow Measurement and Instrumentation,2013,31:86-95.
[4] DROBKOV V P,MEL'NIKOV V I.Ultrasonic flowmeter and velocity meter for the components of a multiphase stream[J].Measurement Techniques,2002,45(12):1254-1255.
[5] HAMAD F A,Khan M K,BRUUN H H.Experimental study of kerosene-water two-phase flow in a vertical pipe using hot-film and dual optical probes[J].Canadian Journal of Chemical Engineering,2013,91:7.
[6] 岳鹏飞.油水两相流阵列电导探针测量方法设计与研究[D].大庆:东北石油大学,2015.YUE Peng-fei.Research and design of array conductance probe measurement method of oil water two phase flow[D].Daqing:Northeast Petroleum University,2015.
[7] 只伟.基于GLCC技术的油气水三相流测量技术研究与应用[D].天津:天津大学,2011.ZHI Wei.Research and application of the oil gas water measuring technique based on GLCC[D].Tianjin:Tianjin University,2011.
[8] 王栋,林益,林宗虎.利用T型三通测量气液两相流体的流量和干度[J].热能动力工程,2002,17(4):336-338.WANG Dong,LIN Yi,LIN Zong-hu.Measurement of flow rate and dryness of a vapor-liquid two-phase fluid by using a T-junction[J].Journal of Engineering for Thermal Energy and Power,2002,17(4):336-338.
[9] 周云龙,王强,孙斌,等.基于希尔伯特—黄变换与Elman神经网络的气液两相流流型识别方法[J].中国电机工程学报,2007,27(11) :50-56.ZHOU Yun-long,WANG Qiang,SUN Bin,et al.Applied study of Hilbert-huang transform and Elman neutral network on flow regime identification for gas-liquid two-phase flow[J].Proceedings of the CSEE,2007,27(11):50-56.
[10] 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 Li-li,LIU Hong-bo,CHEN De-yun,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.
[11] 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 Yun-long,GU Yang-yang.Flow regime identification of gas/liquid two-phase flow based ICA and RBF neural networks[J].CIESC Jourrnal,2012,63(3) :796-799.
[12] HU H L,DONG J,ZHANG J,et al.Identification of gas/solid two-phase flow regimes using electrostatic sensors and neural network techniques[J].Flow Measurement and Instrumentation,2011(22):482-487.
[13] 王强,周云龙,程思勇,等.基于小波和Elman神经网络的气液两相流流型识别方法[J].热能动力工程,2007,22(2):168-171.WANG Qiang,ZHOU Yun-long,CHENG Si-yong,et al.A method for discriminating gas-liquid two phase flow patterns based on wavelets and Elman neural networks[J].Journal of Engineering for Thermal Energy and Power,2007,22(2):168-171.
[14] 梁法春,王栋,林宗虎.基于神经网络的水平管三相分层流相分率测量[J].西安交通大学学报,2004,38(7):750-753.LIANG Fa-chun,WANG Dong,LIN Zong-hu.Study to determine phase fraction of three phase stratified flow in horizontal pipeline with neural network[J].Journal of Xi’an Jiaotong University,2004,38(7):750-753.
[15] MERIBOUT M,AL-RAWAHI N,AL-NAAMANY A.Integration of impedance measurements with acoustic measurements for accurate two phase flow metering in case of high water-cut[J].Flow Measurement and Instrumentation,2010,21:8-19.
[16] VINCE M,LAHEY Jr R.On the development of an objective flow regime indicator[J].International Journal of Multiphase Flow,1982,8(2):93-124.
[17] 周宏亮,郭烈锦,闫瀚,等.集输立管内流型分类及流型控制实验研究[J].工程热物理学报,2016,37(3):562-566.ZHOU Hong-liang,GUO Lie-jin,YAN Han,et al.Experimental study of flow pattern classification and severe slugging control in a pipeline riser system[J].Journal of Engineering Thermalophysics,2016,37(3):562-566.
[2] PIROUZPANAH S,?EVIK M,MORRISON G L.Multi-phase flow measurement using coupled slotted orifice plate and swirl flow meter[J].Flow Measurement and Instrumentation,2014,40:157-161.
[3] LEEUNGCULSATIEN T,LUCAS G P.Measurement of velocity profiles in multiphase flow using a multi-electrode electromagnetic flow meter[J].Flow Measurement and Instrumentation,2013,31:86-95.
[4] DROBKOV V P,MEL'NIKOV V I.Ultrasonic flowmeter and velocity meter for the components of a multiphase stream[J].Measurement Techniques,2002,45(12):1254-1255.
[5] HAMAD F A,Khan M K,BRUUN H H.Experimental study of kerosene-water two-phase flow in a vertical pipe using hot-film and dual optical probes[J].Canadian Journal of Chemical Engineering,2013,91:7.
[6] 岳鹏飞.油水两相流阵列电导探针测量方法设计与研究[D].大庆:东北石油大学,2015.YUE Peng-fei.Research and design of array conductance probe measurement method of oil water two phase flow[D].Daqing:Northeast Petroleum University,2015.
[7] 只伟.基于GLCC技术的油气水三相流测量技术研究与应用[D].天津:天津大学,2011.ZHI Wei.Research and application of the oil gas water measuring technique based on GLCC[D].Tianjin:Tianjin University,2011.
[8] 王栋,林益,林宗虎.利用T型三通测量气液两相流体的流量和干度[J].热能动力工程,2002,17(4):336-338.WANG Dong,LIN Yi,LIN Zong-hu.Measurement of flow rate and dryness of a vapor-liquid two-phase fluid by using a T-junction[J].Journal of Engineering for Thermal Energy and Power,2002,17(4):336-338.
[9] 周云龙,王强,孙斌,等.基于希尔伯特—黄变换与Elman神经网络的气液两相流流型识别方法[J].中国电机工程学报,2007,27(11) :50-56.ZHOU Yun-long,WANG Qiang,SUN Bin,et al.Applied study of Hilbert-huang transform and Elman neutral network on flow regime identification for gas-liquid two-phase flow[J].Proceedings of the CSEE,2007,27(11):50-56.
[10] 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 Li-li,LIU Hong-bo,CHEN De-yun,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.
[11] 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 Yun-long,GU Yang-yang.Flow regime identification of gas/liquid two-phase flow based ICA and RBF neural networks[J].CIESC Jourrnal,2012,63(3) :796-799.
[12] HU H L,DONG J,ZHANG J,et al.Identification of gas/solid two-phase flow regimes using electrostatic sensors and neural network techniques[J].Flow Measurement and Instrumentation,2011(22):482-487.
[13] 王强,周云龙,程思勇,等.基于小波和Elman神经网络的气液两相流流型识别方法[J].热能动力工程,2007,22(2):168-171.WANG Qiang,ZHOU Yun-long,CHENG Si-yong,et al.A method for discriminating gas-liquid two phase flow patterns based on wavelets and Elman neural networks[J].Journal of Engineering for Thermal Energy and Power,2007,22(2):168-171.
[14] 梁法春,王栋,林宗虎.基于神经网络的水平管三相分层流相分率测量[J].西安交通大学学报,2004,38(7):750-753.LIANG Fa-chun,WANG Dong,LIN Zong-hu.Study to determine phase fraction of three phase stratified flow in horizontal pipeline with neural network[J].Journal of Xi’an Jiaotong University,2004,38(7):750-753.
[15] MERIBOUT M,AL-RAWAHI N,AL-NAAMANY A.Integration of impedance measurements with acoustic measurements for accurate two phase flow metering in case of high water-cut[J].Flow Measurement and Instrumentation,2010,21:8-19.
[16] VINCE M,LAHEY Jr R.On the development of an objective flow regime indicator[J].International Journal of Multiphase Flow,1982,8(2):93-124.
[17] 周宏亮,郭烈锦,闫瀚,等.集输立管内流型分类及流型控制实验研究[J].工程热物理学报,2016,37(3):562-566.ZHOU Hong-liang,GUO Lie-jin,YAN Han,et al.Experimental study of flow pattern classification and severe slugging control in a pipeline riser system[J].Journal of Engineering Thermalophysics,2016,37(3):562-566.