ΔLogR技术与BP神经网络在复杂岩性致密层有机质评价中的应用
|
摘要
本文系统分析ΔLogR技术应用于复杂岩性致密层有机质评价中存在两方面的局限性:参数选取方面,测井曲线选取过于单一,无法有效削弱致密层段复杂岩性和孔隙度等因素对计算有机碳含量的影响;构建模型方面,人为剔除异常点存在随机性与偶然性误差,影响建模准确性.针对上述问题,本文建立了BP神经网络模型,并将其应用于柳河盆地柳参1井下桦皮甸子组烃源岩有机质评价.研究结果表明,在不剔除异常点情况下,BP神经网络模型计算TOC值和实测116组TOC值相关性达到0.886,显示建模效果良好.分别应用BP神经网络和ΔLogR模型,计算研究区致密层纵向上连续的TOC曲线,BP神经网络模型的计算TOC曲线与实测TOC数据基本吻合,而ΔLogR模型的计算TOC曲线吻合度较差.因此在测井资料完善的情况下,本文建议使用BP神经网络评价复杂岩性的致密层有机质.
This paper points out the ΔLogR technology has a couple of limitations for organic evaluation in the complex lithology tight stratum through systematic analysis. On the choice of parameter,selection of well logging parameters is too single to weaken effectively the influence of complex lithology and porosity,and other factors to the calculation of organic content in tight layer; on the construction of the model,eliminating artificially abnormal points brings random errors to affect the accuracy of the model. Aimed at these problems,the BP neural network model was established to calculate vertical continuous organic carbon content in tight stratum of the Xiahuapidianzi Formation in Liuchan-1 well,Liuhe basin.Without eliminating artificially abnormal points, the correlation between the TOC values calculated by BP neural network model and the 116 sets of measured TOC values reaches to 0. 886,which shows the modeling effect of BP neural network is good. Then the BP neural network model and the ΔLogR model were respectively applied to work out the vertical continuous TOC curve of the tight layer. The TOC curve calculated form the BP neural network model agrees well with the measured TOC values,while the latter does not. Therefore,in the case of complete logging data,this article recommends building the BP neural network model for evaluating organic matter in complex lithology tight stratum.
This paper points out the ΔLogR technology has a couple of limitations for organic evaluation in the complex lithology tight stratum through systematic analysis. On the choice of parameter,selection of well logging parameters is too single to weaken effectively the influence of complex lithology and porosity,and other factors to the calculation of organic content in tight layer; on the construction of the model,eliminating artificially abnormal points brings random errors to affect the accuracy of the model. Aimed at these problems,the BP neural network model was established to calculate vertical continuous organic carbon content in tight stratum of the Xiahuapidianzi Formation in Liuchan-1 well,Liuhe basin.Without eliminating artificially abnormal points, the correlation between the TOC values calculated by BP neural network model and the 116 sets of measured TOC values reaches to 0. 886,which shows the modeling effect of BP neural network is good. Then the BP neural network model and the ΔLogR model were respectively applied to work out the vertical continuous TOC curve of the tight layer. The TOC curve calculated form the BP neural network model agrees well with the measured TOC values,while the latter does not. Therefore,in the case of complete logging data,this article recommends building the BP neural network model for evaluating organic matter in complex lithology tight stratum.
引文
Chen G W,Lu S F,Tian S S,et al.2014.Application of RBF neura network to logging evaluation of clay shale organic heterogeneity[J].Journal of Gansu Sciences(in Chinese),26(1):104-108.
Chen T P,Chen H.1993.Approximation capability to functions of several variables,nonlinear functionals and operators by radial basis function neural networks[C].//Proceedings of 1993 International Joint Conference on Neural Networks.Nagoya,Japan:IEEE:1439-1442.
Cheng S Y.2006.Regional tectonic characters and meso-cenozoic basin evolution in northeastern China(in Chinese)[Ph.D.thesis].Beijing:China University of Petroleum(Beijing).
Cheng X J.1995.The Principle and Application of Neural Network(in Chinese)[M].Beijing:National Defence Industry Press.
Fertl W H,Chilingar G V.1988.Total organic carbon content determined from well logs[J].SPE Formation Evaluation,3(2):407-419.
Guo L,Chen J F,Miao Z Y.2009.Study and application of a new overlay method of the TOC content[J].Natural Gas Geoscience(in Chinese),20(6):951-956.
Guo Z Q,Sun P,Liu W H.2012.The carbon calculation byΔlogRtechnology in Sanhu area of Qaidam basin[J].Progress in Geophysics(in Chinese),27(2):626-633,doi:10.6038/j.issn.1004-2903.2012.02.027.
Hu H T,Lu S F,Liu C,et al.2011.Models for calculating organic carbon content from logging information:Comparison and analysis[J].Acta Sedimentologica Sinica(in Chinese),29(6):1199-1205.
Hu H T,Su R,Liu C,et al.2016.The method and application of using generalized-ΔLgR technology to predict the organic carbon content of continental deep source rocks[J].Natural Gas Geoscience(in Chinese),27(1):149-155.
Huang W B,Deng S W,Lu S F,et al.2014.Shale organic heterogeneity evaluation method and its application to shale oil resource evaluation-a case study from Qingshankou Formation,southern Songliao Basin[J].Oil&Gas Geology(in Chinese),35(5):704-711.
Jiang W W,Tu G H,Zhu D Y,et al.2006.Characters of geophysical fields and floor of Daqing outer basins[J].Progress in Geophysics(in Chinese),21(4):1064-1079,doi:10.3969/j.issn.1004-2903.2006.04.004.
Li Y J,Zhang L H,Feng Y Y,et al.2013.Logging evaluation method and its application for measuring the total organic carbon content in shale gas[J].Natural Gas Geoscience(in Chinese),24(1):169-175.
Lin C C,Hao G L,Chen G B,et al.2013.Petroleum geology and exploration orientation in faulted basins along the Duahua-Mishan fault in Jilin Province[J].Global Geology(in Chinese),32(2):317-324.
Liu C.2011.Evaluating source rock using logging data-improvement and application(in Chinese)[Master thesis].Daqing:Northeast Petroleum University.
Liu C,Yin C H,Lu S F.2015.Predicting key parameters for VariablecoefficientΔLgR logging technique and its application in source rocks evaluation[J].Natural Gas Geoscience(in Chinese),26(10):1925-1931.
Meng Z P,Guo Y X,Liu W.2015.Relationship between organic carbon content of shale gas reservoir and logging parameters and its prediction model[J].Journal of China Coal Society(in Chinese),40(2):247-253.
Passey Q R,Creaney S,Kulla J B,et al.1990.A practical model for organic richness from porosity and resistivity logs[J].AAPGBulletin,74(12):1777-1794.
Schmoker J W.1981.Determination of organic-matter content of Appalachian Devonian shales from gamma-ray logs[J].AAPGBulletin,65(7):1285-1298.
Shan X L,Xie X T,Ren Y,et al.2013.Meso-Cenozoic unconventional hydrocarbon resources in eastern Jilin and prospect of development[J].Global Geology(in Chinese),32(1):77-83.
Wang W F,Lu S K,Jin Q.1999.Geodynamics of sedimentary basins in eastern China[J].Journal of the University of Petroleum,China(in Chinese),23(4):1-5.
Wang Z L,Li J,Luo Q,et al.2012.Fine evaluation of source rock with logging data in Langgu Sag of Jizhong depression[J].Natural Gas Geoscience(in Chinese),23(3):430-437.
Xu H L,Fan C Y,Gao X.2013.Early Cretaceous prototype restoration of the basin group in eastern Jilin[J].Global Geology(in Chinese),32(2):263-272.
Yang S C,Wang N,Li M R,et al.2013.The logging evaluation of source rocks of triassic Yanchang Formation in Chongxin Area,Ordos Basin[J].Natural Gas Geoscience(in Chinese),24(3):470-476.
Zhu G Y,Jin Q.2002.Study on source rock heterogeneity-a case of Niu-38 well in Dongying depression[J].Acta Petrolei Sinica(in Chinese),23(5):34-39.
陈国辉,卢双舫,田善思等.2014.+BF神经网络法在泥页岩有机非均质性测井评价中的应用[J].甘肃科学学报,26(1):104-108.
程三友.2006.中国东北地区区域构造特征与中、新生代盆地演化[博士论文].北京:中国地质大学(北京).
程相君.1995.神经网络原理及其应用[M].北京:国防工业出版社.
郭龙,陈践发,苗忠英.2009.一种新的TOC含量拟合方法研究与应用[J].天然气地球科学,20(6):951-956.
郭泽清,孙平,刘卫红.2012.利用ΔlogR技术计算柴达木盆地三湖地区第四系有机碳[J].地球物理学进展,27(2):626-633,doi:10.6038/j.issn.1004-2903.2012.02.027.
胡慧婷,卢双舫,刘超等.2011.测井资料计算源岩有机碳含量模型对比及分析[J].沉积学报,29(6):1199-1205.
胡慧婷,苏瑞,刘超等.2016.广义ΔLgR技术预测陆相深层烃源岩有机碳含量方法及其应用[J].天然气地球科学,27(1):149-155.
黄文彪,邓守伟,卢双舫等.2014.泥页岩有机非均质性评价及其在页岩油资源评价中的应用---以松辽盆地南部青山口组为例[J].石油与天然气地质,35(5):704-711.
江为为,涂广红,朱东英等.2006.大庆外围盆地地球物理场与盆地基底特征[J].地球物理学进展,21(4):1064-1079,doi:10.3969/j.issn.1004-2903.2006.04.004.
李延钧,张烈辉,冯媛媛等.2013.页岩有机碳含量测井评价方法及其应用[J].天然气地球科学,24(1):169-175.
林长城,郝国丽,陈贵标等.2013.敦-密断裂带吉林段断陷盆地石油地质条件及勘探方向[J].世界地质,32(2):317-324.
刘超.2011.测井资料评价烃源岩方法改进及作用[硕士论文].大庆:东北石油大学.
刘超,印长海,卢双舫.2015.变系数ΔLgR烃源岩测井评价技术关键参数厘定方法及应用[J].天然气地球科学,26(10):1925-1931.
孟召平,郭彦省,刘尉.2015.页岩气储层有机碳含量与测井参数的关系及预测模型[J].煤炭学报,40(2):247-253.
单玄龙,解晓婷,任宇等.2013.吉林东部中、新生代盆地非常规油气资源及潜力分析[J].世界地质,32(1):77-83.
王伟锋,陆诗阔,金强.1999.中国大陆东部盆地构造动力学分析[J].石油大学学报(自然科学版),23(4):1-5.
王宗礼,李君,罗强等.2012.利用测井资料精细评价冀中坳陷廊固凹陷烃源岩[J].天然气地球科学,23(3):430-437.
徐汉梁,范超颖,高璇.2013.吉林东部盆地群早白垩世原型盆地恢复[J].世界地质,32(2):263-272.
杨少春,王娜,李明瑞等.2013.鄂尔多斯盆地崇信地区三叠系延长组烃源岩测井评价[J].天然气地球科学,24(3):470-476.
朱光有,金强.2002.烃源岩的非均质性研究---以东营凹陷牛38井为例[J].石油学报,23(5):34-39.
Chen T P,Chen H.1993.Approximation capability to functions of several variables,nonlinear functionals and operators by radial basis function neural networks[C].//Proceedings of 1993 International Joint Conference on Neural Networks.Nagoya,Japan:IEEE:1439-1442.
Cheng S Y.2006.Regional tectonic characters and meso-cenozoic basin evolution in northeastern China(in Chinese)[Ph.D.thesis].Beijing:China University of Petroleum(Beijing).
Cheng X J.1995.The Principle and Application of Neural Network(in Chinese)[M].Beijing:National Defence Industry Press.
Fertl W H,Chilingar G V.1988.Total organic carbon content determined from well logs[J].SPE Formation Evaluation,3(2):407-419.
Guo L,Chen J F,Miao Z Y.2009.Study and application of a new overlay method of the TOC content[J].Natural Gas Geoscience(in Chinese),20(6):951-956.
Guo Z Q,Sun P,Liu W H.2012.The carbon calculation byΔlogRtechnology in Sanhu area of Qaidam basin[J].Progress in Geophysics(in Chinese),27(2):626-633,doi:10.6038/j.issn.1004-2903.2012.02.027.
Hu H T,Lu S F,Liu C,et al.2011.Models for calculating organic carbon content from logging information:Comparison and analysis[J].Acta Sedimentologica Sinica(in Chinese),29(6):1199-1205.
Hu H T,Su R,Liu C,et al.2016.The method and application of using generalized-ΔLgR technology to predict the organic carbon content of continental deep source rocks[J].Natural Gas Geoscience(in Chinese),27(1):149-155.
Huang W B,Deng S W,Lu S F,et al.2014.Shale organic heterogeneity evaluation method and its application to shale oil resource evaluation-a case study from Qingshankou Formation,southern Songliao Basin[J].Oil&Gas Geology(in Chinese),35(5):704-711.
Jiang W W,Tu G H,Zhu D Y,et al.2006.Characters of geophysical fields and floor of Daqing outer basins[J].Progress in Geophysics(in Chinese),21(4):1064-1079,doi:10.3969/j.issn.1004-2903.2006.04.004.
Li Y J,Zhang L H,Feng Y Y,et al.2013.Logging evaluation method and its application for measuring the total organic carbon content in shale gas[J].Natural Gas Geoscience(in Chinese),24(1):169-175.
Lin C C,Hao G L,Chen G B,et al.2013.Petroleum geology and exploration orientation in faulted basins along the Duahua-Mishan fault in Jilin Province[J].Global Geology(in Chinese),32(2):317-324.
Liu C.2011.Evaluating source rock using logging data-improvement and application(in Chinese)[Master thesis].Daqing:Northeast Petroleum University.
Liu C,Yin C H,Lu S F.2015.Predicting key parameters for VariablecoefficientΔLgR logging technique and its application in source rocks evaluation[J].Natural Gas Geoscience(in Chinese),26(10):1925-1931.
Meng Z P,Guo Y X,Liu W.2015.Relationship between organic carbon content of shale gas reservoir and logging parameters and its prediction model[J].Journal of China Coal Society(in Chinese),40(2):247-253.
Passey Q R,Creaney S,Kulla J B,et al.1990.A practical model for organic richness from porosity and resistivity logs[J].AAPGBulletin,74(12):1777-1794.
Schmoker J W.1981.Determination of organic-matter content of Appalachian Devonian shales from gamma-ray logs[J].AAPGBulletin,65(7):1285-1298.
Shan X L,Xie X T,Ren Y,et al.2013.Meso-Cenozoic unconventional hydrocarbon resources in eastern Jilin and prospect of development[J].Global Geology(in Chinese),32(1):77-83.
Wang W F,Lu S K,Jin Q.1999.Geodynamics of sedimentary basins in eastern China[J].Journal of the University of Petroleum,China(in Chinese),23(4):1-5.
Wang Z L,Li J,Luo Q,et al.2012.Fine evaluation of source rock with logging data in Langgu Sag of Jizhong depression[J].Natural Gas Geoscience(in Chinese),23(3):430-437.
Xu H L,Fan C Y,Gao X.2013.Early Cretaceous prototype restoration of the basin group in eastern Jilin[J].Global Geology(in Chinese),32(2):263-272.
Yang S C,Wang N,Li M R,et al.2013.The logging evaluation of source rocks of triassic Yanchang Formation in Chongxin Area,Ordos Basin[J].Natural Gas Geoscience(in Chinese),24(3):470-476.
Zhu G Y,Jin Q.2002.Study on source rock heterogeneity-a case of Niu-38 well in Dongying depression[J].Acta Petrolei Sinica(in Chinese),23(5):34-39.
陈国辉,卢双舫,田善思等.2014.+BF神经网络法在泥页岩有机非均质性测井评价中的应用[J].甘肃科学学报,26(1):104-108.
程三友.2006.中国东北地区区域构造特征与中、新生代盆地演化[博士论文].北京:中国地质大学(北京).
程相君.1995.神经网络原理及其应用[M].北京:国防工业出版社.
郭龙,陈践发,苗忠英.2009.一种新的TOC含量拟合方法研究与应用[J].天然气地球科学,20(6):951-956.
郭泽清,孙平,刘卫红.2012.利用ΔlogR技术计算柴达木盆地三湖地区第四系有机碳[J].地球物理学进展,27(2):626-633,doi:10.6038/j.issn.1004-2903.2012.02.027.
胡慧婷,卢双舫,刘超等.2011.测井资料计算源岩有机碳含量模型对比及分析[J].沉积学报,29(6):1199-1205.
胡慧婷,苏瑞,刘超等.2016.广义ΔLgR技术预测陆相深层烃源岩有机碳含量方法及其应用[J].天然气地球科学,27(1):149-155.
黄文彪,邓守伟,卢双舫等.2014.泥页岩有机非均质性评价及其在页岩油资源评价中的应用---以松辽盆地南部青山口组为例[J].石油与天然气地质,35(5):704-711.
江为为,涂广红,朱东英等.2006.大庆外围盆地地球物理场与盆地基底特征[J].地球物理学进展,21(4):1064-1079,doi:10.3969/j.issn.1004-2903.2006.04.004.
李延钧,张烈辉,冯媛媛等.2013.页岩有机碳含量测井评价方法及其应用[J].天然气地球科学,24(1):169-175.
林长城,郝国丽,陈贵标等.2013.敦-密断裂带吉林段断陷盆地石油地质条件及勘探方向[J].世界地质,32(2):317-324.
刘超.2011.测井资料评价烃源岩方法改进及作用[硕士论文].大庆:东北石油大学.
刘超,印长海,卢双舫.2015.变系数ΔLgR烃源岩测井评价技术关键参数厘定方法及应用[J].天然气地球科学,26(10):1925-1931.
孟召平,郭彦省,刘尉.2015.页岩气储层有机碳含量与测井参数的关系及预测模型[J].煤炭学报,40(2):247-253.
单玄龙,解晓婷,任宇等.2013.吉林东部中、新生代盆地非常规油气资源及潜力分析[J].世界地质,32(1):77-83.
王伟锋,陆诗阔,金强.1999.中国大陆东部盆地构造动力学分析[J].石油大学学报(自然科学版),23(4):1-5.
王宗礼,李君,罗强等.2012.利用测井资料精细评价冀中坳陷廊固凹陷烃源岩[J].天然气地球科学,23(3):430-437.
徐汉梁,范超颖,高璇.2013.吉林东部盆地群早白垩世原型盆地恢复[J].世界地质,32(2):263-272.
杨少春,王娜,李明瑞等.2013.鄂尔多斯盆地崇信地区三叠系延长组烃源岩测井评价[J].天然气地球科学,24(3):470-476.
朱光有,金强.2002.烃源岩的非均质性研究---以东营凹陷牛38井为例[J].石油学报,23(5):34-39.