神经网络在油气层横向预测和地震道编辑中的应用
|
摘要
本文绘出了用多层感知器（MLP）作油气层横向预测及地震道自动编辑的方法。作油气层横向预测时，只需给网络提供叠偏地震剖面数据和标定井油气信息，对原始数据无其它要求。经塔里木盆地和中原油田实际地震资料检验表明，网络预测结果与钻井等资料相吻合。作自动编辑时，由于用监督学习型网络MLP作分类器，使系统具有良好的适应性，并能充分反映用户的意愿。华北实际地震资料的计算结果表明，编辑精度达96．5％。
Using multilayer perceptron (MLP ) for rcservoir lateral prediction and seismic trace editing is presented in this paper. All one has to do in lateral prediction for reservoir is to input stacked migrated seismic data and calibrated well data into a network. The tests on real data ftom the Tarim Basin and Zhongyuan oil fleld exhibit that the predictions resulting from the neural network are in agreement with thc drilling data. As for trace editing,since a supervised learning network MLP is used as a classifier, the systcm is then provided with good applicability to meet user's needs. Calculations using data from Huabei Area show that the editing precision is as high as 96.5%.
Using multilayer perceptron (MLP ) for rcservoir lateral prediction and seismic trace editing is presented in this paper. All one has to do in lateral prediction for reservoir is to input stacked migrated seismic data and calibrated well data into a network. The tests on real data ftom the Tarim Basin and Zhongyuan oil fleld exhibit that the predictions resulting from the neural network are in agreement with thc drilling data. As for trace editing,since a supervised learning network MLP is used as a classifier, the systcm is then provided with good applicability to meet user's needs. Calculations using data from Huabei Area show that the editing precision is as high as 96.5%.
引文
[1]钱绍新,应用模式识别方法预测油气储集层,《地球物理学报》,1992年,第5期。
[2]Lippmann R. P., An introduction to computing with neural nets, IEEE. ASSP Magazine,1987, 4: 4-22.
[3]Rumelhart D- E. and McClelland J. L.,Parallel distributed ptocessing:Explorations in themicrostructure of cognition,MIT. Press. 1986, 318-330.
[4]McCormack M D.,Neural comphting in geophysics,The Leading Edge, 1991, 10(1), 11-15
[5]Uphom W. and Cary P.,Comparison of linear and nonlinear neural networks for seismictrace editting, Presented at the 6lst Ann. Internat. Mtg., Soc. Expl. Geophys., ExpandedAbstracts, 1991, 293-294.
[6]Huang Kou-Yuan, Yang H. Z. and Lin C. M., Connectionist expert system for seismicinterpretations, Presented at the 60th Ann. Internat, Mtg., Soc. Expl- Geophys., ExpandedAbstracts, 1990,310-312.
[7]Poulton M M,Glass C. E. and Sternberg B. K.,RecoSnizing EM ellipticity patterns withneural networks,Presented at the 59th Ann. Internat. M tg., Soc. Expl. Geophys-,ExpandcdAbstracts, 1989, 208-212.
[8]Pearson W. C., DeRidder P. and Jack M. J. et al., Acromagnetic structural interpretationusing neural networks:A Case Study from the Northern Denver-Julcsberg Basin,Presentedat the 60th Ann. Internat. Mtg-,Soc- Expl.Geophys.,Expanded Abstracts, 1990, 587-590.
[9]Taylor C. L.,and Vasco W.,Inversion of gravity gradiometry data using a neural network,Presented at the 6oth Ann. Internat. Mtg.,Soc. Expl. Geophys.,Expanded Abstracts, 1990,591-593.
[10]Epping W. J. M., and L'Istelle A. R., Data compression of seismic images by neuralnetworks,Rcvue de L Anstitut Francais du P,etrole. 1992, 47(3) , 423-430.
[11]赵改善,基于模拟退火学习的多层感知器模型及其应用,中国地球物理学会第八届年会,1992年,昆明。
[12]Huang Kou-Yuan, Chang W. R. I., and Yen H. T., Self-organizing neural network forpicking seisrnic horizons, Presented at the 60th Ann. Internat. Mtg., Soc. Expl. , Geophys.Expanded Abstracts, 1990, 31 3-315.
[13]张学工,李衍达,用神经网络聚类方法分析地震道横向变化,中国地球物理学会第八届年会,1992年,昆明。
[14]Zhao X. F., and Mendel J. M., Minimum-variance deconvolution using artificial neuralnetworks, Presented at the 58th Ann- Internat. Mtg., Soc. Expl. oeophys., ExpandedAbstracts, 1988, 738-741.
[15]Huang Kou-Yuan, Liu W. H., and Chang I. C., Hopfield model of neural networks fordetection of bright spots, Presented at the 59th Ann. Internat. Mtg.,Soc. Expl. Geophys.,Expanded Abstrscts, 1989, 444-446.
[16]Wang Li-Xin, and Mendel J. M., Adaptive minimum prediction-crror deconvolution andsource wavelet estimation using Hopfield neural networks, Geophysics, 1992, 57 (4 ) 670-679.
[2]Lippmann R. P., An introduction to computing with neural nets, IEEE. ASSP Magazine,1987, 4: 4-22.
[3]Rumelhart D- E. and McClelland J. L.,Parallel distributed ptocessing:Explorations in themicrostructure of cognition,MIT. Press. 1986, 318-330.
[4]McCormack M D.,Neural comphting in geophysics,The Leading Edge, 1991, 10(1), 11-15
[5]Uphom W. and Cary P.,Comparison of linear and nonlinear neural networks for seismictrace editting, Presented at the 6lst Ann. Internat. Mtg., Soc. Expl. Geophys., ExpandedAbstracts, 1991, 293-294.
[6]Huang Kou-Yuan, Yang H. Z. and Lin C. M., Connectionist expert system for seismicinterpretations, Presented at the 60th Ann. Internat, Mtg., Soc. Expl- Geophys., ExpandedAbstracts, 1990,310-312.
[7]Poulton M M,Glass C. E. and Sternberg B. K.,RecoSnizing EM ellipticity patterns withneural networks,Presented at the 59th Ann. Internat. M tg., Soc. Expl. Geophys-,ExpandcdAbstracts, 1989, 208-212.
[8]Pearson W. C., DeRidder P. and Jack M. J. et al., Acromagnetic structural interpretationusing neural networks:A Case Study from the Northern Denver-Julcsberg Basin,Presentedat the 60th Ann. Internat. Mtg-,Soc- Expl.Geophys.,Expanded Abstracts, 1990, 587-590.
[9]Taylor C. L.,and Vasco W.,Inversion of gravity gradiometry data using a neural network,Presented at the 6oth Ann. Internat. Mtg.,Soc. Expl. Geophys.,Expanded Abstracts, 1990,591-593.
[10]Epping W. J. M., and L'Istelle A. R., Data compression of seismic images by neuralnetworks,Rcvue de L Anstitut Francais du P,etrole. 1992, 47(3) , 423-430.
[11]赵改善,基于模拟退火学习的多层感知器模型及其应用,中国地球物理学会第八届年会,1992年,昆明。
[12]Huang Kou-Yuan, Chang W. R. I., and Yen H. T., Self-organizing neural network forpicking seisrnic horizons, Presented at the 60th Ann. Internat. Mtg., Soc. Expl. , Geophys.Expanded Abstracts, 1990, 31 3-315.
[13]张学工,李衍达,用神经网络聚类方法分析地震道横向变化,中国地球物理学会第八届年会,1992年,昆明。
[14]Zhao X. F., and Mendel J. M., Minimum-variance deconvolution using artificial neuralnetworks, Presented at the 58th Ann- Internat. Mtg., Soc. Expl. oeophys., ExpandedAbstracts, 1988, 738-741.
[15]Huang Kou-Yuan, Liu W. H., and Chang I. C., Hopfield model of neural networks fordetection of bright spots, Presented at the 59th Ann. Internat. Mtg.,Soc. Expl. Geophys.,Expanded Abstrscts, 1989, 444-446.
[16]Wang Li-Xin, and Mendel J. M., Adaptive minimum prediction-crror deconvolution andsource wavelet estimation using Hopfield neural networks, Geophysics, 1992, 57 (4 ) 670-679.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心