鄂尔多斯盆地铜川地区油页岩含油率测井评价方法研究
|
摘要
油页岩属于非常规能源,储量非常丰富,是重要的替代能源.含油率是油页岩储层评价中最重要的一个参数.油页岩储层在测井曲线上具有典型"三高一低"特征,即高电阻率、高声波时差、高自然伽马、低密度.综合利用油页岩典型测井响应特征预测油页岩含油率,成为快速准确评价油页岩资源的有效途径.由于油页岩储层具有较强的非均质性,储层含油率受多种地质因素的影响,且储层含油率与常规测井响应存在着复杂关系,传统方法难以表征它们之间的内在关系.本次研究对鄂尔多斯盆地铜川地区三叠系长7段265块油页岩含油率及常规测井响应进行分析,建立支持向量机神经网络预测模型,对实际资料进行处理,并进行误差分析对比.结果表明:支持向量机神经网络预测含油率可有效的弥补实验室测定含油率的不足,且能够成为快速准确评价鄂尔多斯盆地东南部三叠系油页岩资源的有效方法.
Oil shale is an unconventional energy source. It has abundant reserves and is an important alternative energy source. Oil content is one of the most important parameters in oil shale reservoir evaluation. The oil shale reservoir has a typical"three high and one low"characteristics in the logging curve,and the comprehensive utilization of logging data to predict the oil content becomes an effective way to quickly and accurately evaluate oil shale resources.Due to shale reservoir with strong heterogeneity,reservoir oil content is influenced by many geological factors, oil content and conventional log response and reservoir there exists a complex relationship. The traditional method is difficult to characterize the internal relationship between them. In this study,We analyzed 265 oil content and conventional logging response for chang 7 layer of Tong chuan area,and established support vector machine neural network prediction model; The results show that the support vector machine neural network to predict oil content can effectively compensate the shortage of oil shale yield in the laboratory,and can be an effective method to evaluate oil shale resources of the Triassic oil shale in the southeastern part of Ordos basin.
Oil shale is an unconventional energy source. It has abundant reserves and is an important alternative energy source. Oil content is one of the most important parameters in oil shale reservoir evaluation. The oil shale reservoir has a typical"three high and one low"characteristics in the logging curve,and the comprehensive utilization of logging data to predict the oil content becomes an effective way to quickly and accurately evaluate oil shale resources.Due to shale reservoir with strong heterogeneity,reservoir oil content is influenced by many geological factors, oil content and conventional log response and reservoir there exists a complex relationship. The traditional method is difficult to characterize the internal relationship between them. In this study,We analyzed 265 oil content and conventional logging response for chang 7 layer of Tong chuan area,and established support vector machine neural network prediction model; The results show that the support vector machine neural network to predict oil content can effectively compensate the shortage of oil shale yield in the laboratory,and can be an effective method to evaluate oil shale resources of the Triassic oil shale in the southeastern part of Ordos basin.
引文
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 Q H,Fan J J,Zhang X.2014.Application of BP neural network in oil content prediction[J].Journal of Computer Applications(in Chinese),34(S2):186-189.
Li Y H,Jiang T,Wu F L,et al.2014.Evaluation methods and results of oil shale resources in south-eastern Ordos Basin[J].Geological Bulletin of China(in Chinese),33(9):1417-1424.
Li Y H,Yao Z G,Zhang H Y,et al.2012.Logging evaluation method for oil-bearing rate of oil shale in Tongchuan area of Shaanxi[J].Journal of Xi’an University of Science and Technology(in Chinese),32(5):591-597.
Lu J C,Li Y H,Wei X Y,et al.2006.Research on the depositional environment and resources potential of the oil shale in the Chang 7member,Triassic Yanchang formation in the Ordos Basin[J].Journal of Jilin University(Earth Science Edition)(in Chinese),36(6):928-932.
Meng Z P,Guo Y S,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.
Vapnik V N.1995.The Nature of Statistical Learning Theory[M].New York:Springer.
Wu J X,Liu Z D,Xu D F.2013.Predicting oil content of oil shale in Chang 7 formation of Ordos Basin[J].Journal of Yanan University(Natural Science Edition)(in Chinese),32(3):88-91.
Zhang L P,Bian R X,Yang S Y,et al.2001.Identifying hydrocarbon source rock with log data[J].Well Logging Technology(in Chinese),25(2):146-152.
Zhu J W,Zhao G,Liu B,et al.2012.Identification technology and it's
application of well-logging about oil shale[J].Journal of Jilin
University(Earth Science Edition)(in Chinese),42(2):289-295.
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.
胡启华,范晶晶,张新.2014.应用BP神经网络预测油页岩含油率[J].计算机应用,34(S2):186-189.
李玉宏,姜亭,武富礼,等.2014.鄂尔多斯盆地东南部油页岩资源评价[J].地质通报,2014,33(9):1417-1424.
李玉宏,姚志刚,张慧元,等.2012.陕西铜川地区油页岩含油率测井评价方法[J].西安科技大学学报,2012,32(5):591-597.
卢进才,李玉宏,魏仙样,等.2006.鄂尔多斯盆地三叠系延长组长7油层组油页岩沉积环境与资源潜力研究[J].吉林大学学报(地球科学版),36(6):928-932.
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.
吴建兴,刘之的,徐德峰.2013.鄂尔多斯盆地长7地层油页岩含油率预测[J].延安大学学报(自然科学版),32(3):88-91.
张立鹏,边瑞雪,杨双彦,等.2001.用测井资料识别烃源岩[J].测井技术,25(2):146-152.
朱建伟,赵刚,刘博,等.2012.油页岩测井识别技术及应用[J].吉林大学学报(地球科学版),42(2):289-295.
Hu Q H,Fan J J,Zhang X.2014.Application of BP neural network in oil content prediction[J].Journal of Computer Applications(in Chinese),34(S2):186-189.
Li Y H,Jiang T,Wu F L,et al.2014.Evaluation methods and results of oil shale resources in south-eastern Ordos Basin[J].Geological Bulletin of China(in Chinese),33(9):1417-1424.
Li Y H,Yao Z G,Zhang H Y,et al.2012.Logging evaluation method for oil-bearing rate of oil shale in Tongchuan area of Shaanxi[J].Journal of Xi’an University of Science and Technology(in Chinese),32(5):591-597.
Lu J C,Li Y H,Wei X Y,et al.2006.Research on the depositional environment and resources potential of the oil shale in the Chang 7member,Triassic Yanchang formation in the Ordos Basin[J].Journal of Jilin University(Earth Science Edition)(in Chinese),36(6):928-932.
Meng Z P,Guo Y S,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.
Vapnik V N.1995.The Nature of Statistical Learning Theory[M].New York:Springer.
Wu J X,Liu Z D,Xu D F.2013.Predicting oil content of oil shale in Chang 7 formation of Ordos Basin[J].Journal of Yanan University(Natural Science Edition)(in Chinese),32(3):88-91.
Zhang L P,Bian R X,Yang S Y,et al.2001.Identifying hydrocarbon source rock with log data[J].Well Logging Technology(in Chinese),25(2):146-152.
Zhu J W,Zhao G,Liu B,et al.2012.Identification technology and it's
application of well-logging about oil shale[J].Journal of Jilin
University(Earth Science Edition)(in Chinese),42(2):289-295.
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.
胡启华,范晶晶,张新.2014.应用BP神经网络预测油页岩含油率[J].计算机应用,34(S2):186-189.
李玉宏,姜亭,武富礼,等.2014.鄂尔多斯盆地东南部油页岩资源评价[J].地质通报,2014,33(9):1417-1424.
李玉宏,姚志刚,张慧元,等.2012.陕西铜川地区油页岩含油率测井评价方法[J].西安科技大学学报,2012,32(5):591-597.
卢进才,李玉宏,魏仙样,等.2006.鄂尔多斯盆地三叠系延长组长7油层组油页岩沉积环境与资源潜力研究[J].吉林大学学报(地球科学版),36(6):928-932.
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.
吴建兴,刘之的,徐德峰.2013.鄂尔多斯盆地长7地层油页岩含油率预测[J].延安大学学报(自然科学版),32(3):88-91.
张立鹏,边瑞雪,杨双彦,等.2001.用测井资料识别烃源岩[J].测井技术,25(2):146-152.
朱建伟,赵刚,刘博,等.2012.油页岩测井识别技术及应用[J].吉林大学学报(地球科学版),42(2):289-295.