基于盲分离技术的凝析天然气测量数据处理
|
摘要
凝析天然气是一种低含液率的气液两相流,其流量计量属于多相计量的一个分支,是石油天然气工业迫切需要解决的问题之一。目前,结合新型的信号处理技术,基于差压等常规测量信号通过软件的方法解决计量问题,是凝析天然气流量计量发展的一个重要方向。
本文基于课题组自行开发的凝析天然气流量计样机和大量的实验数据,从信号分离的角度对槽式孔板差压信号进行处理。通过采用盲分离范畴内的两种基本方法——时频分析盲分离(TF-BSS)和独立成分分析(ICA),来提取与两相流参数相关的特征量,而后进行必要的分析与处理,完整地实现气液两相流量计量。
论文主要分为三部分,第一部分阐述了基于时频分析盲分离方法的两相流量计量过程;第二部分描述了基于独立成分分析的两相流量计量方法;第三部分对两种分离方法的运用进行对比和分析,以总结出更好的处理方式。
课题组开发的凝析天然气流量计属于双差压组合测量方式,针对上、下游槽式孔板差压信号DP1、DP2,利用时频分析盲分离方法和独立成分分析方法两种方式,均可分离出表征液相作用的分量,同时得到分离分量方差与液相折算速度的定量关系,关系式准确度较高。而后分别基于通过分离方法得到的液相流量,利用槽式孔板相关式计算得到气相流量,其计量准确度也较理想。
结果表明,对于从气液两相流槽式孔板差压信号中提取单相信息,时频分析盲分离和独立成分分析都是较有效的分离方法,同时为凝析天然气各相流量计量提供了一种新的思路。
Wet gas flow is a typical two-phase flow with low liquid fractions. Wet gas metering is a subset of multiphase flow metering, and it is one of the major unsolved problems for oil and gas industry. Recently, more and more signal processing technologies have been used in the data processing of wet gas flow, and it is an important issue for wet gas flow metering.
Based on a self developed prototype of wet gas meter and an experimental data set, differential pressure (DP) signals from slotted orifices have been processed from a view of signal separating. Two Blind Source Separation (BSS) techniques, which are BSS based on Time-Frequency analysis (TF-BSS) and Independent Component Analysis (ICA), have been used to extract characteristic quantity of wet gas flow. Gas and liquid flow are acquired at last.
This thesis consists of three parts. The first part mainly focuses on the two-phase flow metering based on TF-BSS method; The second part elaborates the metering process based on ICA method; The third part is a comparison and an analysis of these two ways, and a conclusion is given in the end.
Based on DP signals from a couple of slotted orifices, TF-BSS (TIFROM algorithm) and ICA (FastICA algorithm) are used to separate different effects respectively. A good relationship between the liquid flow rate and the characteristic quantity of the separated signal is established, and a differential pressure correlation for slotted orifice is applied to calculate the gas flow rate. The calculation results are good with 90% relative errors less than±10%.
The results show that BSS is an effective method to extract the effect of the liquid flow from DP signals of wet gas flow, and this provides a new approach of wet gas flow metering.
本文基于课题组自行开发的凝析天然气流量计样机和大量的实验数据,从信号分离的角度对槽式孔板差压信号进行处理。通过采用盲分离范畴内的两种基本方法——时频分析盲分离(TF-BSS)和独立成分分析(ICA),来提取与两相流参数相关的特征量,而后进行必要的分析与处理,完整地实现气液两相流量计量。
论文主要分为三部分,第一部分阐述了基于时频分析盲分离方法的两相流量计量过程;第二部分描述了基于独立成分分析的两相流量计量方法;第三部分对两种分离方法的运用进行对比和分析,以总结出更好的处理方式。
课题组开发的凝析天然气流量计属于双差压组合测量方式,针对上、下游槽式孔板差压信号DP1、DP2,利用时频分析盲分离方法和独立成分分析方法两种方式,均可分离出表征液相作用的分量,同时得到分离分量方差与液相折算速度的定量关系,关系式准确度较高。而后分别基于通过分离方法得到的液相流量,利用槽式孔板相关式计算得到气相流量,其计量准确度也较理想。
结果表明,对于从气液两相流槽式孔板差压信号中提取单相信息,时频分析盲分离和独立成分分析都是较有效的分离方法,同时为凝析天然气各相流量计量提供了一种新的思路。
Wet gas flow is a typical two-phase flow with low liquid fractions. Wet gas metering is a subset of multiphase flow metering, and it is one of the major unsolved problems for oil and gas industry. Recently, more and more signal processing technologies have been used in the data processing of wet gas flow, and it is an important issue for wet gas flow metering.
Based on a self developed prototype of wet gas meter and an experimental data set, differential pressure (DP) signals from slotted orifices have been processed from a view of signal separating. Two Blind Source Separation (BSS) techniques, which are BSS based on Time-Frequency analysis (TF-BSS) and Independent Component Analysis (ICA), have been used to extract characteristic quantity of wet gas flow. Gas and liquid flow are acquired at last.
This thesis consists of three parts. The first part mainly focuses on the two-phase flow metering based on TF-BSS method; The second part elaborates the metering process based on ICA method; The third part is a comparison and an analysis of these two ways, and a conclusion is given in the end.
Based on DP signals from a couple of slotted orifices, TF-BSS (TIFROM algorithm) and ICA (FastICA algorithm) are used to separate different effects respectively. A good relationship between the liquid flow rate and the characteristic quantity of the separated signal is established, and a differential pressure correlation for slotted orifice is applied to calculate the gas flow rate. The calculation results are good with 90% relative errors less than±10%.
The results show that BSS is an effective method to extract the effect of the liquid flow from DP signals of wet gas flow, and this provides a new approach of wet gas flow metering.
引文
[1]耿艳峰,冯叔初,郑金吾等.凝析天然气计量技术[J].自动化仪表,2005,26(8):1-3
[2]林宗虎.变换流动的科学——多相流体力学[M].清华大学出版.
[3]林宗虎,王树众,王栋.气液两相流和沸腾传热[M].西安:西安交通大学出版社
[4] Britton C, Seidl W, Kinney J. Experimental Wet Gas Data for a Herschel Style Venturi [C]. 5th International Symposium on Fluid Flow Measurement. Colorado, USA: 2002
[5] Steward D., Steven R.. Wet Gas Metering with V-CONE Meters. North Sea Flow Measurement Workshop, 2002
[6] Steven R., Peters RJW.. Wet Gas Metering with V-CONE Meters. 3rd International SE Asia Hydrocarbon Flow Measurement Workshop, 2004
[7] Agar J., Farchy D.. Wet Gas Metering Using Dissimilar Flow Sensors: Theory and Field Trial Results. SPE77349, 2002
[8] Steward D., Brown G., Hodges D.. Wet Gas Venturing Metering. SPE 77350, 2002
[9] Ahmed B., Steve G.. Field Testing of Multiphase Meters. SPE 56583, 1999
[10]丁浩,黄志尧,李海青.气液两相流差压波动信号的Hilbert-Huang变换特性[J].化工学报,2005,56(12):2294-2302
[11] Jun Han, Feng Dong. Mass flow rate measurement of Gas/liquid two-phase flow in horizontal pipe based on V-cone flow meter and adaptive wavelet network[C]. Instrumentation and Measurement Technology Conference, 2009, I2MTC '09, IEEE
[12] Yanbin Xu, Ziqiang Cui, Huaxiang Wang, Feng Dong, Xiaoyan Chen, and Wuqiang Yang. Independent component analysis of interface fluctuation of gas/liquid two-phase flows---experimental study[J]. Flow Measurement and Instrumentation 20, 2009, pp.220-229
[13]杜运成,王化祥.基于电容层析成像的气液两相流流型聚类分析[J].中国电机工程学报,2009,29(29):72-76
[14] Ji Haifeng, Fu Yongfeng, Huang Zhiyao, Li Haiqing. Flow regime detection of mini-pipe gas-liquid two-phase flow based on PCA and SVM[C]. 2010 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2010
[15]张宏建,岳伟挺,马龙博,周洪亮.文丘里管中气液两相流差压波动信号与空隙率关系[J].化工学报,2005, 56(11):2102-2107
[16]孙斌,王二朋,郑永军.气液两相流波动信号的时频谱分析研究[J].物理学报,2011,60(1)
[17] Cardoso J F. Blind beam forming for non-gaussian signals[J]. IEEE Proceedings-F,1993,140(6):224-230
[18] Comom P. Independent component analysis, a new concept?[J]. Signal Processing,1994,36(3):287-314
[19] A. Hyv?rinen, E. Oja. Independent component analysis: algorithms and applications. Neural Networks 13 (2000) 411–430
[20] A. Hyv?rinen. Survey on Independent Component Analysis [J].Neural Computing Surveys (S1093-7609). 1999, 2:94–128
[21] A. Hyv?rinen, Juha Karhunen, Erkki Oja. Independent Component Analysis [M]. New York: John Wiley & Sons, 2001
[22] A. Hyv?rinen and E. Oja. Simple neuron models for independent component analysis[J]. Int. J. of Neural Systems, 7(6):671–687, 1996
[23] A. Hyv?rinen and E. Oja. A fast fixed-point algorithm for independent component analysis[J]. Neural Computation, 9(7):1483–1492, 1997. Reprinted in Unsupervised Learning, G. Hinton and T. J. Sejnowski, eds., MIT Press, 1999
[24]何继爱,王维芳,李力舟.盲源信号分离方法研究[J].无线通信技术,2009,4:4-14
[25]耿艳峰,冯叔初,郑金吾等.基于槽式孔板的凝析天然气计量技术[J].仪器仪表学报,2006,27(8):873-876
[26] Morrison G.L., Hall K.R., Holste J.C., et al. Comparison of Orifice and Slotted Plate Flowmeters [J]. Flow Measurement and Instrumentation, 1994, 5(2): 71-77
[27] Morrison G.L., Terracina D., Brewer C., et al. Response of a Slotted Orifice Flow Meter to an Air/Water Mixture [J]. Flow Measurement and Instrumentation, 2001, 12(3): 175-180
[28] Macek M.L.. A Slotted Orifice Plate Used as a Flow Measurement Device [D]. Texas A&M University, College Station, 1993
[29] Geng Yanfeng, Li Yuxing, Feng Shuchu. Study on a New Type of Sensor for Wet Gas Meter [A]. Advances in Multiphase Flow, Hangzhou. 2004: 536-541
[30]孙淮青,王建中.流量测量节流装置设计手册[M].第二版.北京:化学工业出版社,2005:4-5
[31]郑金吾,耿艳峰.海上含液天然气流量计开发[J].化工自动化及仪表,2006,33(3): 74-77
[32] Geng Yanfeng, Zheng Jinwu, Shi Tianming, et al. Wet Gas Meter Development Based on Slotted Orifice Couple and Neural Network Techniques [J]. Chinese Journal of Chemical Engineering, 2007, 15(2):281-285
[33]何利民,郭烈锦,陈学俊.测量水平管道液塞速度和长度的差压波动分析法[J].化工学报,2003,54(2):192-198
[34]何利民,赵庆军,陈振瑜.水平管段塞流液塞速度波动的非线性分析[J].中国电机工程学报,2003,23(12):189-193
[35]江延明,李玉星,冯叔初.气液两相流流量变化的瞬态特性[J].化工学报,2003, 54(3):321-326
[36] A. Belouchrani, M. Amin. Blind source separation based on time-frequency signal representations[J]. IEEE Transactions on Signal Processing 46 (11) (1998) 2888-2897
[37] A. Holobar, C. Fevotte, C. Doncarli, D. Zazula. Single autoterms selection for blind source separation in time-frequency plane[C]. Proceedings of the 11th European Signal Processing Conference (EUSIPCO 2002), Toulouse, France, September 3-6, 2002
[38] C. Fvétte, C. Doncarli. Two contributions to blind source separation using time-frequency distributions [J]. IEEE Signal Processing Letters 11 (3) (2004) 386-389
[39] A. Jourjine, S. Rickard, O. Yilmaz. Blind separation of disjoint orthogonal signals: demixing N sources from 2 mixtures[C]. Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2000), vol. 5, IEEE Press, Istanbul, Turkey, June 5-9, 2000, pp. 2985-2988
[40] S. Rickard, R. Balan, J. Rosca. Real-time time-frequency based blind source separation [C]. Proceedings of the Third International Symposium on Independent Component Analysis and Blind Signal Separation (ICA 2001), San Diego, USA, December 9-13, 2001, pp. 651-656
[41] S. Rickard, O. Yilmaz. On the approximate W-disjoint orthogonality of speech[C]. Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2002), Orlando, USA, May 13-17, 2002
[42] R. Balan, J. Rosca, S. Rickard. Non-square blind source separation under coherent noiseby beamforming and time-frequency masking[C]. Proceedings of the Fourth International Symposium on Independent Component Analysis and Blind Signal Separation (ICA 2003), Nara, Japan, April 2003, pp. 313-318
[43] M. Baeck, U. Z?lder. Performance analysis of a source separation algorithm[C]. Proceedings of the Fifth Digital Audio Effects (DAFx-02), Hamburg, Germany, September 26-28, 2002, pp. 207-210
[44] F. Abrard, Y. Deville, P. White. A new source separation approach based on time-frequency analysis for instantaneous mixtures[C]. Proceedings of the Fifth International Workshop on Electronics, Control, Modeling, Measurement and Signals (ECM2S 2001), Toulouse, France, May 30-June 1, 2001, pp. 259-267
[45] Y. Deville, M. Puigt, B. Albouy. Time-frequency blind signal separation: extended methods, performance evaluation for speech sources[C]. Proceedings of the International Joint Conference on Neural Networks (IJCNN 2004), Budapest, Hungary, July 25-29, 2004, pp. 255-260, IEEE Catalog Number: 04CH37541C, ISBN: 0-7803-8360-5
[46] F. Abrard, Y. Deville, and Paul White. Form blind source separation to blind source cancellation in the underdetermined case: A new approach based on time-frequency analysis, unpublished
[47] F. Abrard and Y. Deville. A time-frequency blind signal separation method applicable to underdetermined mixtures of dependent sources[J]. Signal Processing 85, 2005, pp.1389-1403
[48] Y. Deville. Temporal and time-frequency correlation-based blind source separation methods[C]. Proceedings of the Fourth International Symposium on Independent Component Analysis and Blind Signal Separation (ICA 2003), Nara, Japan, April 1-4, 2003, pp. 1059-1064
[49] Y. Deville, M. Puigt. Temporal and time-frequency correlation-based blind source separation methods. Part I: linear instantaneous mixtures[J]. Signal Processing, submitted
[50] D. Smith, J. Lukasiak, I. Burnett. Two channel, block adaptative audio separation using the cross correlation of time frequency information[C]. Proceedings on the Fifth International Symposium on Independent Component Analysis and Blind Signal Separation (ICA 2004), Granada, Spain, September 22-24, 2004
[51] B. Albouy, Y. Deville. A time-frequency blind source separation method based on segmented coherence function, in: J. Mira, J.R. Alvarez (Eds.) [C]. Proceedings of the Seventh International Work-Conference on Artificial and Natural Neural Networks (IWANN 2003), Special Session, vol. 2, Springer, Mao, Menorca, Spain, June 3-6, 2003, pp. 289-296
[52] Murdock J. W.. Two-phase Flow Measurement with Orifices[J]. Journal of Basic Engineering, 1962, 84 (4):419-433
[53] Chisholm D.. Flow of Incompressible Two-phase Mixtures through Sharp-edged Orifices[J].Journal of Mechanical Engineering Science,1974,16(5):353-355
[54] Lin Z. H.. Two-phase Flow Measurements with Sharp-edged Orifice[J]. International Journal of Multiphase Flow, 1992, 8(6):683-693
[55]王晓智.基于槽式孔板和旋进漩涡流量计的凝析天然气计量算法研究[D].硕士学位论文
[56] (芬)海韦里恩等.独立成分分析[M].北京:电子工业出版社,2007.6
[57] T. P. Jung, C. Humphries, T.-W. Lee, S. Makeig, M. J. McKeown, V. Iragui, and T. Sejnowski. Extended ICA removes artifacts from electroencephalographic recordings[J]. In Advances in Neural Information Processing Systems, volume 10. MIT Press, 1998
[58] R. Vig?rio. Extraction of ocular artifacts from EEG using independent component analysis[J]. Electroenceph. Clin. Neurophysiol. , 103(3):395-404, 1997
[59] R. Vig?rio, V. Jousm?ki, M. H?m?l?inen, and E. Oja. Independent component analysis for identification of artifacts in magneto encephalographic recordings[J]. In Advances in Neural Information Processing Systems, volume 10, pages 229-235. MIT Press, 1998
[60] J. Joutsensalo and T. Ristaniemi. Learning algorithms for blind multiuser detection in CDMA downlink[C]. In Proc. IEEE 9th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC’98), pages 267-270, Boston, Massachusetts, 1998
[61] T. Ristaniemi and J. Joutsensalo. On the performance of blind source separation in CDMA downlink[C]. In Proc. Int. Workshop on Independent Component Analysis and Blind Source Separation (ICA’99), pages 437-441, Aussois, France, January 1999
[62] R. Cristescu, T. Ristaniemi, J. Joutsensalo, and J. Karhunen. Delay estimation in CDMAcommunications using a FastICA algorithm[C]. In Proc. Int. Workshop on Independent Component Analysis and Blind Source Separation (ICA2000), pages 105-110, Helsinki, Finland, 2000
[63] A. D. Back and A. S. Weigend. A first application of independent component analysis to extracting structure from stock returns[C]. Int. J. on Neural Systems, 8(4):473-484, 1997
[64] K. Kiviluoto and E. Oja. Independent component analysis for parallel financial time series [C]. In Proc. Int. Conf. on Neural Information Processing (ICONIP’98), pages 895-898, Tokyo, Japan, 1998
[65] K. Torkkola. Blind separation for audio signals-are we there yet? [C] In Proc. Int. Workshop on Independent Component Analysis and Blind Source Separation (ICA’99), pages 239-244, Aussois, France, January 1999
[66] F.M. Ham and N.A. Faour. Infrasound signal separation using independent component analysis[C]. In Proc. 21st Seismic Research Symposium: Technologies for Monitoring the Comprehensive Nuclear-Test-Ban Treaty, Las Vegas, Nevada, 1999.
[67] Qiangwei Li. De-noising of differential pressure signal of two-phase flow based on ICA[C]. Fourth International Conference on Natural Computation
[68]彭佩星,王保良,李海青.基于ICA和ES-SVM的油气两相流空隙率测量[J].化工自动化及仪表,2007,34(4):60-62
[69]吴新杰,石玉珠,陈跃宁等.独立成分分析在两相流速度测量中的应用[J].仪器仪表学报,2006,27(2):115-117
[70]杨福生,洪波.独立分量分析的原理与应用[M].北京:清华大学出版社,2006:178
[2]林宗虎.变换流动的科学——多相流体力学[M].清华大学出版.
[3]林宗虎,王树众,王栋.气液两相流和沸腾传热[M].西安:西安交通大学出版社
[4] Britton C, Seidl W, Kinney J. Experimental Wet Gas Data for a Herschel Style Venturi [C]. 5th International Symposium on Fluid Flow Measurement. Colorado, USA: 2002
[5] Steward D., Steven R.. Wet Gas Metering with V-CONE Meters. North Sea Flow Measurement Workshop, 2002
[6] Steven R., Peters RJW.. Wet Gas Metering with V-CONE Meters. 3rd International SE Asia Hydrocarbon Flow Measurement Workshop, 2004
[7] Agar J., Farchy D.. Wet Gas Metering Using Dissimilar Flow Sensors: Theory and Field Trial Results. SPE77349, 2002
[8] Steward D., Brown G., Hodges D.. Wet Gas Venturing Metering. SPE 77350, 2002
[9] Ahmed B., Steve G.. Field Testing of Multiphase Meters. SPE 56583, 1999
[10]丁浩,黄志尧,李海青.气液两相流差压波动信号的Hilbert-Huang变换特性[J].化工学报,2005,56(12):2294-2302
[11] Jun Han, Feng Dong. Mass flow rate measurement of Gas/liquid two-phase flow in horizontal pipe based on V-cone flow meter and adaptive wavelet network[C]. Instrumentation and Measurement Technology Conference, 2009, I2MTC '09, IEEE
[12] Yanbin Xu, Ziqiang Cui, Huaxiang Wang, Feng Dong, Xiaoyan Chen, and Wuqiang Yang. Independent component analysis of interface fluctuation of gas/liquid two-phase flows---experimental study[J]. Flow Measurement and Instrumentation 20, 2009, pp.220-229
[13]杜运成,王化祥.基于电容层析成像的气液两相流流型聚类分析[J].中国电机工程学报,2009,29(29):72-76
[14] Ji Haifeng, Fu Yongfeng, Huang Zhiyao, Li Haiqing. Flow regime detection of mini-pipe gas-liquid two-phase flow based on PCA and SVM[C]. 2010 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2010
[15]张宏建,岳伟挺,马龙博,周洪亮.文丘里管中气液两相流差压波动信号与空隙率关系[J].化工学报,2005, 56(11):2102-2107
[16]孙斌,王二朋,郑永军.气液两相流波动信号的时频谱分析研究[J].物理学报,2011,60(1)
[17] Cardoso J F. Blind beam forming for non-gaussian signals[J]. IEEE Proceedings-F,1993,140(6):224-230
[18] Comom P. Independent component analysis, a new concept?[J]. Signal Processing,1994,36(3):287-314
[19] A. Hyv?rinen, E. Oja. Independent component analysis: algorithms and applications. Neural Networks 13 (2000) 411–430
[20] A. Hyv?rinen. Survey on Independent Component Analysis [J].Neural Computing Surveys (S1093-7609). 1999, 2:94–128
[21] A. Hyv?rinen, Juha Karhunen, Erkki Oja. Independent Component Analysis [M]. New York: John Wiley & Sons, 2001
[22] A. Hyv?rinen and E. Oja. Simple neuron models for independent component analysis[J]. Int. J. of Neural Systems, 7(6):671–687, 1996
[23] A. Hyv?rinen and E. Oja. A fast fixed-point algorithm for independent component analysis[J]. Neural Computation, 9(7):1483–1492, 1997. Reprinted in Unsupervised Learning, G. Hinton and T. J. Sejnowski, eds., MIT Press, 1999
[24]何继爱,王维芳,李力舟.盲源信号分离方法研究[J].无线通信技术,2009,4:4-14
[25]耿艳峰,冯叔初,郑金吾等.基于槽式孔板的凝析天然气计量技术[J].仪器仪表学报,2006,27(8):873-876
[26] Morrison G.L., Hall K.R., Holste J.C., et al. Comparison of Orifice and Slotted Plate Flowmeters [J]. Flow Measurement and Instrumentation, 1994, 5(2): 71-77
[27] Morrison G.L., Terracina D., Brewer C., et al. Response of a Slotted Orifice Flow Meter to an Air/Water Mixture [J]. Flow Measurement and Instrumentation, 2001, 12(3): 175-180
[28] Macek M.L.. A Slotted Orifice Plate Used as a Flow Measurement Device [D]. Texas A&M University, College Station, 1993
[29] Geng Yanfeng, Li Yuxing, Feng Shuchu. Study on a New Type of Sensor for Wet Gas Meter [A]. Advances in Multiphase Flow, Hangzhou. 2004: 536-541
[30]孙淮青,王建中.流量测量节流装置设计手册[M].第二版.北京:化学工业出版社,2005:4-5
[31]郑金吾,耿艳峰.海上含液天然气流量计开发[J].化工自动化及仪表,2006,33(3): 74-77
[32] Geng Yanfeng, Zheng Jinwu, Shi Tianming, et al. Wet Gas Meter Development Based on Slotted Orifice Couple and Neural Network Techniques [J]. Chinese Journal of Chemical Engineering, 2007, 15(2):281-285
[33]何利民,郭烈锦,陈学俊.测量水平管道液塞速度和长度的差压波动分析法[J].化工学报,2003,54(2):192-198
[34]何利民,赵庆军,陈振瑜.水平管段塞流液塞速度波动的非线性分析[J].中国电机工程学报,2003,23(12):189-193
[35]江延明,李玉星,冯叔初.气液两相流流量变化的瞬态特性[J].化工学报,2003, 54(3):321-326
[36] A. Belouchrani, M. Amin. Blind source separation based on time-frequency signal representations[J]. IEEE Transactions on Signal Processing 46 (11) (1998) 2888-2897
[37] A. Holobar, C. Fevotte, C. Doncarli, D. Zazula. Single autoterms selection for blind source separation in time-frequency plane[C]. Proceedings of the 11th European Signal Processing Conference (EUSIPCO 2002), Toulouse, France, September 3-6, 2002
[38] C. Fvétte, C. Doncarli. Two contributions to blind source separation using time-frequency distributions [J]. IEEE Signal Processing Letters 11 (3) (2004) 386-389
[39] A. Jourjine, S. Rickard, O. Yilmaz. Blind separation of disjoint orthogonal signals: demixing N sources from 2 mixtures[C]. Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2000), vol. 5, IEEE Press, Istanbul, Turkey, June 5-9, 2000, pp. 2985-2988
[40] S. Rickard, R. Balan, J. Rosca. Real-time time-frequency based blind source separation [C]. Proceedings of the Third International Symposium on Independent Component Analysis and Blind Signal Separation (ICA 2001), San Diego, USA, December 9-13, 2001, pp. 651-656
[41] S. Rickard, O. Yilmaz. On the approximate W-disjoint orthogonality of speech[C]. Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2002), Orlando, USA, May 13-17, 2002
[42] R. Balan, J. Rosca, S. Rickard. Non-square blind source separation under coherent noiseby beamforming and time-frequency masking[C]. Proceedings of the Fourth International Symposium on Independent Component Analysis and Blind Signal Separation (ICA 2003), Nara, Japan, April 2003, pp. 313-318
[43] M. Baeck, U. Z?lder. Performance analysis of a source separation algorithm[C]. Proceedings of the Fifth Digital Audio Effects (DAFx-02), Hamburg, Germany, September 26-28, 2002, pp. 207-210
[44] F. Abrard, Y. Deville, P. White. A new source separation approach based on time-frequency analysis for instantaneous mixtures[C]. Proceedings of the Fifth International Workshop on Electronics, Control, Modeling, Measurement and Signals (ECM2S 2001), Toulouse, France, May 30-June 1, 2001, pp. 259-267
[45] Y. Deville, M. Puigt, B. Albouy. Time-frequency blind signal separation: extended methods, performance evaluation for speech sources[C]. Proceedings of the International Joint Conference on Neural Networks (IJCNN 2004), Budapest, Hungary, July 25-29, 2004, pp. 255-260, IEEE Catalog Number: 04CH37541C, ISBN: 0-7803-8360-5
[46] F. Abrard, Y. Deville, and Paul White. Form blind source separation to blind source cancellation in the underdetermined case: A new approach based on time-frequency analysis, unpublished
[47] F. Abrard and Y. Deville. A time-frequency blind signal separation method applicable to underdetermined mixtures of dependent sources[J]. Signal Processing 85, 2005, pp.1389-1403
[48] Y. Deville. Temporal and time-frequency correlation-based blind source separation methods[C]. Proceedings of the Fourth International Symposium on Independent Component Analysis and Blind Signal Separation (ICA 2003), Nara, Japan, April 1-4, 2003, pp. 1059-1064
[49] Y. Deville, M. Puigt. Temporal and time-frequency correlation-based blind source separation methods. Part I: linear instantaneous mixtures[J]. Signal Processing, submitted
[50] D. Smith, J. Lukasiak, I. Burnett. Two channel, block adaptative audio separation using the cross correlation of time frequency information[C]. Proceedings on the Fifth International Symposium on Independent Component Analysis and Blind Signal Separation (ICA 2004), Granada, Spain, September 22-24, 2004
[51] B. Albouy, Y. Deville. A time-frequency blind source separation method based on segmented coherence function, in: J. Mira, J.R. Alvarez (Eds.) [C]. Proceedings of the Seventh International Work-Conference on Artificial and Natural Neural Networks (IWANN 2003), Special Session, vol. 2, Springer, Mao, Menorca, Spain, June 3-6, 2003, pp. 289-296
[52] Murdock J. W.. Two-phase Flow Measurement with Orifices[J]. Journal of Basic Engineering, 1962, 84 (4):419-433
[53] Chisholm D.. Flow of Incompressible Two-phase Mixtures through Sharp-edged Orifices[J].Journal of Mechanical Engineering Science,1974,16(5):353-355
[54] Lin Z. H.. Two-phase Flow Measurements with Sharp-edged Orifice[J]. International Journal of Multiphase Flow, 1992, 8(6):683-693
[55]王晓智.基于槽式孔板和旋进漩涡流量计的凝析天然气计量算法研究[D].硕士学位论文
[56] (芬)海韦里恩等.独立成分分析[M].北京:电子工业出版社,2007.6
[57] T. P. Jung, C. Humphries, T.-W. Lee, S. Makeig, M. J. McKeown, V. Iragui, and T. Sejnowski. Extended ICA removes artifacts from electroencephalographic recordings[J]. In Advances in Neural Information Processing Systems, volume 10. MIT Press, 1998
[58] R. Vig?rio. Extraction of ocular artifacts from EEG using independent component analysis[J]. Electroenceph. Clin. Neurophysiol. , 103(3):395-404, 1997
[59] R. Vig?rio, V. Jousm?ki, M. H?m?l?inen, and E. Oja. Independent component analysis for identification of artifacts in magneto encephalographic recordings[J]. In Advances in Neural Information Processing Systems, volume 10, pages 229-235. MIT Press, 1998
[60] J. Joutsensalo and T. Ristaniemi. Learning algorithms for blind multiuser detection in CDMA downlink[C]. In Proc. IEEE 9th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC’98), pages 267-270, Boston, Massachusetts, 1998
[61] T. Ristaniemi and J. Joutsensalo. On the performance of blind source separation in CDMA downlink[C]. In Proc. Int. Workshop on Independent Component Analysis and Blind Source Separation (ICA’99), pages 437-441, Aussois, France, January 1999
[62] R. Cristescu, T. Ristaniemi, J. Joutsensalo, and J. Karhunen. Delay estimation in CDMAcommunications using a FastICA algorithm[C]. In Proc. Int. Workshop on Independent Component Analysis and Blind Source Separation (ICA2000), pages 105-110, Helsinki, Finland, 2000
[63] A. D. Back and A. S. Weigend. A first application of independent component analysis to extracting structure from stock returns[C]. Int. J. on Neural Systems, 8(4):473-484, 1997
[64] K. Kiviluoto and E. Oja. Independent component analysis for parallel financial time series [C]. In Proc. Int. Conf. on Neural Information Processing (ICONIP’98), pages 895-898, Tokyo, Japan, 1998
[65] K. Torkkola. Blind separation for audio signals-are we there yet? [C] In Proc. Int. Workshop on Independent Component Analysis and Blind Source Separation (ICA’99), pages 239-244, Aussois, France, January 1999
[66] F.M. Ham and N.A. Faour. Infrasound signal separation using independent component analysis[C]. In Proc. 21st Seismic Research Symposium: Technologies for Monitoring the Comprehensive Nuclear-Test-Ban Treaty, Las Vegas, Nevada, 1999.
[67] Qiangwei Li. De-noising of differential pressure signal of two-phase flow based on ICA[C]. Fourth International Conference on Natural Computation
[68]彭佩星,王保良,李海青.基于ICA和ES-SVM的油气两相流空隙率测量[J].化工自动化及仪表,2007,34(4):60-62
[69]吴新杰,石玉珠,陈跃宁等.独立成分分析在两相流速度测量中的应用[J].仪器仪表学报,2006,27(2):115-117
[70]杨福生,洪波.独立分量分析的原理与应用[M].北京:清华大学出版社,2006:178
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |