概率神经网络在丽水—椒江凹陷月桂峰组沉积微相识别中的应用
|
摘要
由于海上钻井取芯较少,所以东海陆架盆地丽水—椒江凹陷古新统月桂峰组地层沉积微相识别存在局限。运用概率神经网络对研究区进行沉积微相识别。首先,通过地震相-沉积相响应分析和测井曲线主成分分析,发现研究区地震相和沉积相之间存在耦合对应关系,因此选择地震相作为概率神经网络输入项中的范畴自变量参数,同时提取出能对沉积微相区分较好的自然伽马、自然电位、声波时差、密度测井、补偿中子、井径测井曲线值作为概率神经网络输入项的数值自变量;然后,选用2 199个学习样本对神经网络进行训练,经过65次试验,搜索出变量的最佳平滑因子,建立研究区20种沉积微相类型的判别模式;最后,利用建立的神经网络对研究区沉积微相进行识别。结果表明:跟岩芯分析的结果对比,运用概率神经网络识别的结果准确率达到90%以上,该方法应用于未取芯井区域沉积微相的识别具有可行性。
Sedimentary microfacies recognition of Yueguifeng Formation in Lishui-Jiaojiang sag of East China Sea Shelf Basin is circumscribed because of the shortage of offshore drilling well core.Probabilistic neural network(PNN)was used for sedimentary microfacies recognition of Yueguifeng Formation.Firstly,based on the response analysis of seismic facies-sedimentary facies and principal component analysis of logging curve,relationship between seismic facies and sedimentary facies was coupling and corresponding,so that seismic facies was selected as the category independent variable from the input item parameters of PNN,meanwhile,natural gamma,self potential,acoustic,density logging,compensated neutron and caliper logging curves,which were helpful to distinguish different sedimentary microfacies,were taken as the numerical independent variables from the input item parameters of PNN;secondly,2 199 learning samples were used to train PNN,the optimal smoothing factors of variables were searched after 65 tests,and the discrimination model for 20 kinds of sedimentary microfacies in study area was established;finally,the PNN established was used to identify sedimentary microfacies.The results show that compared with the result of well core analysis,the accuracy rate of sedimentary microfacies identified by PNN is more than 90% ,so that it is feasible to identify sedimentary microfacies from the non-cored area by PNN.
Sedimentary microfacies recognition of Yueguifeng Formation in Lishui-Jiaojiang sag of East China Sea Shelf Basin is circumscribed because of the shortage of offshore drilling well core.Probabilistic neural network(PNN)was used for sedimentary microfacies recognition of Yueguifeng Formation.Firstly,based on the response analysis of seismic facies-sedimentary facies and principal component analysis of logging curve,relationship between seismic facies and sedimentary facies was coupling and corresponding,so that seismic facies was selected as the category independent variable from the input item parameters of PNN,meanwhile,natural gamma,self potential,acoustic,density logging,compensated neutron and caliper logging curves,which were helpful to distinguish different sedimentary microfacies,were taken as the numerical independent variables from the input item parameters of PNN;secondly,2 199 learning samples were used to train PNN,the optimal smoothing factors of variables were searched after 65 tests,and the discrimination model for 20 kinds of sedimentary microfacies in study area was established;finally,the PNN established was used to identify sedimentary microfacies.The results show that compared with the result of well core analysis,the accuracy rate of sedimentary microfacies identified by PNN is more than 90% ,so that it is feasible to identify sedimentary microfacies from the non-cored area by PNN.
引文
[1]李双成,郑度.人工神经网络模型在地学研究中的应用进展[J].地球科学进展,2003,18(1):68-76.LI Shuang-cheng,ZHENG Du.Applications of Artificial Neural Networks to Geosciences:Review and Prospect[J].Advance in Earth Sciences,2003,18(1):68-76.
[2]周金应,桂碧雯,李茂,等.基于岩控的人工神经网络在渗透率预测中的应用[J].石油学报,2010,31(6):985-988.ZHOU Jin-ying,GUI Bi-wen,LI Mao,et al.An Application of the Artificial Neural Net Dominated by Lithology to Permeability Prediction[J].Acta Petrolei Sinica,2010,31(6):985-988.
[3]李道伦,卢德唐,孔祥言,等.BP神经网络隐式法在测井数据处理中的应用[J].石油学报,2007,28(3):105-108.LI Dao-lun,LU De-tang,KONG Xiang-yan,et al.Processing of Well Log Data Based on Backpropagation Neural Network Implicit Approximation[J].Acta Petrolei Sinica,2007,28(3):105-108.
[4]潘文超.以广义回归神经网络预测共同基金报酬[J].长安大学学报:社会科学版,2007,9(4):55-58.PAN Wen-chao.Forecast for Mutual Fund Returns with General Regression Neural Network[J].Journal of Chang'an University:Social Science Edition,2007,9(4):55-58.
[5]胡世鹏,吴小林,马利敏,等.基于BP神经网络和遗传算法的天然气脱水装置能耗优化[J].天然气工业,2012,32(11):89-94.HU Shi-peng,WU Xiao-lin,MA Li-min,et al.BP-and GA-based Energy Consumption Optimization of Gas Dehydration Plants[J].Natural Gas Industry,2012,32(11):89-94.
[6]刘文超,卢祥国,刘进祥,等.一种基于BP神经网络的调驱增油预测方法[J].西安石油大学学报:自然科学版,2012,27(1):47-52.LIU Wen-chao,LU Xiang-guo,LIU Jin-xiang,et al.Prediction Method of Oil Increment of Profile-control and Flooding Measures Using BP Neural Network Based on Core Flooding Parameters[J].Journal of Xi'an Shiyou University:Natural Science Edition,2012,27(1):47-52.
[7]唐胜利,唐皓,郭辉.基于BP神经网络的空洞型采空区稳定性评价研究[J].西安科技大学学报,2012,32(2):234-238.TANG Sheng-li,TANG Hao,GUO Hui.Stability Evaluation of Empty Mine Goaf Based on BP Neural Network[J].Journal of Xi'an University of Science and Technology,2012,32(2):234-238.
[8]吴灿灿,李壮福.基于BP神经网络的测井相分析及沉积相识别[J].煤田地质与勘探,2012,40(1):68-71.WU Can-can,LI Zhuang-fu.Logging Facies Analysis and Sedimentary Facies Identification Based on BP Neural Network[J].Coal Geology and Exploration,2012,40(1):68-71.
[9]吴永良,田景春,朱迎堂.神经网络判识沉积微相的应用——以桩241块为例[J].地质找矿论丛,2009,24(4):317-321.WU Yong-liang,TIAN Jing-chun,ZHU Ying-tang.Application of the Neural Net-discrimated Micro-sedimentary Facies—A Case of Block Z241[J].Contributions to Geology and Mineral Resources Research,2009,24(4):317-321.
[10]郭曦榕,黄地龙.一种基于神经网络的沉积相识别方法[J].计算机应用与软件,2007,24(3):132-134.GUO Xi-rong,HUANG Di-long.A Kind of Sedimentary Facies Recognition Method Based on BP Neural Network[J].Computer Applications and Software,2007,24(3):132-134.
[11]许少华,陈可为,梁久祯,等.基于遗传-BP神经网络的沉积微相自动识别[J].大庆石油学院学报,2001,25(1):51-54.XU Shao-hua,CHEN Ke-wei,LIANG Jiu-zhen,et al.Automatic Sedimentary Facies Identification Method Based on Genetic-BP Neural Networks[J].Journal of Daqing Petroleum Institute,2001,25(1):51-54.
[12]秦亚玲,计平,郑宇霞,等.神经网络自动识别沉积微相在胡状集油田的应用[J].断块油气田,2001,8(1):10-12.QIN Ya-ling,JI Ping,ZHENG Yu-xia,et al.Nerve Network Automatically Identification of Sedimentary Microfacies in Huzhuangji Oilfield[J].Fault-block Oil and Gas Field,2001,8(1):10-12.
[13]杨莉娜,杨斌,鲁洪江,等.五百梯气田长兴组储层裂缝发育程度的常规测井神经网络预测[J].中国石油勘探,2011,16(1):63-69.YANG Li-na,YANG Bin,LU Hong-jiang,et al.Prediction of Fracture Development in Changxing Formation Reservoir of Wubaiti Gas Field from Conventional Logging Data Using Neural Networks[J].China Petroleum Exploration,2011,16(1):63-69.
[14]庞国印,唐俊,王琪,等.利用概率神经网络预测成岩相[J].特种油气藏,2013,20(2):43-47.PANG Guo-yin,TANG Jun,WANG Qi,et al.Prediction of Diagenetic Facies with Probabilistic Neural Network[J].Special Oil and Gas Reservoirs,2013,20(2):43-47.
[15]黄正吉.中国近海优质烃源岩的发育特征及古生态标志[J].中国石油勘探,2012,17(5):10-16.HUANG Zheng-ji.Growth and Paleoecological Marker of High-grade Source Rocks in China Marginal Seas[J].China Petroleum Exploration,2012,17(5):10-16.
[16]张胜利,夏斌.丽水—椒江凹陷构造演化特征与油气聚集[J].天然气地球科学,2005,16(3):324-328.ZHANG Sheng-li,XIA Bin.Characters of Tectonic Evolution of the Lishui-Jiaojiang Sag and Oil Accumulation[J].Natural Gas Geoscience,2005,16(3):324-328.
[17]王毅,姜亮,杨伟利.丽水—椒江凹陷断裂构造运动学[J].地质科学,2000,35(4):441-448.WANG Yi,JIANG Liang,YANG Wei-li.Kinematical Analysis on Faults in the Lishui-Jiaojiang Sag[J].Scientia Geologica Sinica,2000,35(4):441-448.
[18]仝志刚,赵志刚,杨树春,等.低勘探程度盆地烃源岩热演化及排烃史研究——以东海椒江凹陷为例[J].石油实验地质,2012,34(3):319-324.TONG Zhi-gang,ZHAO Zhi-gang,YANG Shu-chun,et al.Research on Thermal Evolution and Hydrocarbon Expulsion History of Source Rocks in Low-exploration Basins—A Case Study on Jiaojiang Sag,East China Sea Basin[J].Petroleum Geology and Experiment,2012,34(3):319-324.
[19]纪友亮,李清山,王勇,等.高邮凹陷古近系戴南组扇三角洲沉积体系及其沉积相模式[J].地球科学与环境学报,2012,34(1):9-19.JI You-liang,LI Qing-shan,WANG Yong,et al.Fan Delta Sedimentary System and Facies Models of Dainan Formation of Paleogene in Gaoyou Sag[J].Journal of Earth Sciences and Environment,2012,34(1):9-19.
[20]张绍红.概率神经网络技术在非均质地层岩性反演中的应用[J].石油学报,2008,29(4):549-552.ZHANG Shao-hong.Application of Probabilistic Neural Network Technique to Lithology Inversion of Hetero-geneous Stratum[J].Acta Petrolei Sinica,2008,29(4):549-552.
[21]李曙光,徐天吉,唐建明,等.概率神经网络储层流体密度反演及应用[J].地质科技情报,2011,30(1):76-79.LI Shu-guang,XU Tian-ji,TANG Jian-ming,et al.Reservoir Fluid-density Inversion and Application Based on PNN[J].Geological Science and Technology,2011,30(1):76-79.
[22]肖波,韩学辉,周开金,等.测井曲线自动分层方法回顾与展望[J].地球物理学进展,2010,25(5):1802-1810.XIAO Bo,HAN Xue-hui,ZHOU Kai-jin,et al.A Review and Outlook of Automatic Zonation Methods of Well Log[J].Progress in Geophysics,2010,25(5):1802-1810.
[23]BROWN L F,FISHER J W L.Seismic Stratigraphic Interpretation and Petroleum Exploration[M].Boulder:AAPG,1980.
[24]黄锋,李志荣,廖玲,等.利用地震资料进行沉积相分析[J].物探化探计算技术,2003,25(3):197-200.HUANG Feng,LI Zhi-rong,LIAO Ling,et al.Sedimentary Facies Analysis Using Seismic Data[J].Computing Techniques for Geophysical and Geochemical Exploration,2003,25(3):197-200.
[25]陈恭洋,陈玲,朱洁琼,等.地震属性分析在河流相储层预测中的应用[J].西南石油大学学报:自然科学版,2012,34(3):1-8.CHEN Gong-yang,CHEN Ling,ZHU Jie-qiong,et al.Application of Seismic Attributes Analysis Fluvial Reservoir to Prediction[J].Journal of Southwest Petroleum University:Science and Technology Edition,2012,34(3):1-8.
[26]唐为清,郭荣坤,王忠东,等.沉积微相测井资料神经网络判别方法研究[J].沉积学报,2001,19(4):581-585.TANG Wei-qing,GUO Rong-kun,WANG Zhongdong,et al.The Study on Method of Depositional Microfacies Discrimination with Well-logging Information[J].Acta Sedimentologica Sinica,2001,19(4):581-585.
[27]张福明,李洪奇,邵才瑞,等.应用神经网络模式识别技术进行测井沉积学研究[J].石油勘探与开发,2003,30(3):121-123.ZHANG Fu-ming,LI Hong-qi,SHAO Cai-rui,et al.Application of Artificial Neural Network Pattern Recognition Technology to the Study of Well-logging Sedimentology[J].Petroleum Exploration and Development,2003,30(3):121-123.
[2]周金应,桂碧雯,李茂,等.基于岩控的人工神经网络在渗透率预测中的应用[J].石油学报,2010,31(6):985-988.ZHOU Jin-ying,GUI Bi-wen,LI Mao,et al.An Application of the Artificial Neural Net Dominated by Lithology to Permeability Prediction[J].Acta Petrolei Sinica,2010,31(6):985-988.
[3]李道伦,卢德唐,孔祥言,等.BP神经网络隐式法在测井数据处理中的应用[J].石油学报,2007,28(3):105-108.LI Dao-lun,LU De-tang,KONG Xiang-yan,et al.Processing of Well Log Data Based on Backpropagation Neural Network Implicit Approximation[J].Acta Petrolei Sinica,2007,28(3):105-108.
[4]潘文超.以广义回归神经网络预测共同基金报酬[J].长安大学学报:社会科学版,2007,9(4):55-58.PAN Wen-chao.Forecast for Mutual Fund Returns with General Regression Neural Network[J].Journal of Chang'an University:Social Science Edition,2007,9(4):55-58.
[5]胡世鹏,吴小林,马利敏,等.基于BP神经网络和遗传算法的天然气脱水装置能耗优化[J].天然气工业,2012,32(11):89-94.HU Shi-peng,WU Xiao-lin,MA Li-min,et al.BP-and GA-based Energy Consumption Optimization of Gas Dehydration Plants[J].Natural Gas Industry,2012,32(11):89-94.
[6]刘文超,卢祥国,刘进祥,等.一种基于BP神经网络的调驱增油预测方法[J].西安石油大学学报:自然科学版,2012,27(1):47-52.LIU Wen-chao,LU Xiang-guo,LIU Jin-xiang,et al.Prediction Method of Oil Increment of Profile-control and Flooding Measures Using BP Neural Network Based on Core Flooding Parameters[J].Journal of Xi'an Shiyou University:Natural Science Edition,2012,27(1):47-52.
[7]唐胜利,唐皓,郭辉.基于BP神经网络的空洞型采空区稳定性评价研究[J].西安科技大学学报,2012,32(2):234-238.TANG Sheng-li,TANG Hao,GUO Hui.Stability Evaluation of Empty Mine Goaf Based on BP Neural Network[J].Journal of Xi'an University of Science and Technology,2012,32(2):234-238.
[8]吴灿灿,李壮福.基于BP神经网络的测井相分析及沉积相识别[J].煤田地质与勘探,2012,40(1):68-71.WU Can-can,LI Zhuang-fu.Logging Facies Analysis and Sedimentary Facies Identification Based on BP Neural Network[J].Coal Geology and Exploration,2012,40(1):68-71.
[9]吴永良,田景春,朱迎堂.神经网络判识沉积微相的应用——以桩241块为例[J].地质找矿论丛,2009,24(4):317-321.WU Yong-liang,TIAN Jing-chun,ZHU Ying-tang.Application of the Neural Net-discrimated Micro-sedimentary Facies—A Case of Block Z241[J].Contributions to Geology and Mineral Resources Research,2009,24(4):317-321.
[10]郭曦榕,黄地龙.一种基于神经网络的沉积相识别方法[J].计算机应用与软件,2007,24(3):132-134.GUO Xi-rong,HUANG Di-long.A Kind of Sedimentary Facies Recognition Method Based on BP Neural Network[J].Computer Applications and Software,2007,24(3):132-134.
[11]许少华,陈可为,梁久祯,等.基于遗传-BP神经网络的沉积微相自动识别[J].大庆石油学院学报,2001,25(1):51-54.XU Shao-hua,CHEN Ke-wei,LIANG Jiu-zhen,et al.Automatic Sedimentary Facies Identification Method Based on Genetic-BP Neural Networks[J].Journal of Daqing Petroleum Institute,2001,25(1):51-54.
[12]秦亚玲,计平,郑宇霞,等.神经网络自动识别沉积微相在胡状集油田的应用[J].断块油气田,2001,8(1):10-12.QIN Ya-ling,JI Ping,ZHENG Yu-xia,et al.Nerve Network Automatically Identification of Sedimentary Microfacies in Huzhuangji Oilfield[J].Fault-block Oil and Gas Field,2001,8(1):10-12.
[13]杨莉娜,杨斌,鲁洪江,等.五百梯气田长兴组储层裂缝发育程度的常规测井神经网络预测[J].中国石油勘探,2011,16(1):63-69.YANG Li-na,YANG Bin,LU Hong-jiang,et al.Prediction of Fracture Development in Changxing Formation Reservoir of Wubaiti Gas Field from Conventional Logging Data Using Neural Networks[J].China Petroleum Exploration,2011,16(1):63-69.
[14]庞国印,唐俊,王琪,等.利用概率神经网络预测成岩相[J].特种油气藏,2013,20(2):43-47.PANG Guo-yin,TANG Jun,WANG Qi,et al.Prediction of Diagenetic Facies with Probabilistic Neural Network[J].Special Oil and Gas Reservoirs,2013,20(2):43-47.
[15]黄正吉.中国近海优质烃源岩的发育特征及古生态标志[J].中国石油勘探,2012,17(5):10-16.HUANG Zheng-ji.Growth and Paleoecological Marker of High-grade Source Rocks in China Marginal Seas[J].China Petroleum Exploration,2012,17(5):10-16.
[16]张胜利,夏斌.丽水—椒江凹陷构造演化特征与油气聚集[J].天然气地球科学,2005,16(3):324-328.ZHANG Sheng-li,XIA Bin.Characters of Tectonic Evolution of the Lishui-Jiaojiang Sag and Oil Accumulation[J].Natural Gas Geoscience,2005,16(3):324-328.
[17]王毅,姜亮,杨伟利.丽水—椒江凹陷断裂构造运动学[J].地质科学,2000,35(4):441-448.WANG Yi,JIANG Liang,YANG Wei-li.Kinematical Analysis on Faults in the Lishui-Jiaojiang Sag[J].Scientia Geologica Sinica,2000,35(4):441-448.
[18]仝志刚,赵志刚,杨树春,等.低勘探程度盆地烃源岩热演化及排烃史研究——以东海椒江凹陷为例[J].石油实验地质,2012,34(3):319-324.TONG Zhi-gang,ZHAO Zhi-gang,YANG Shu-chun,et al.Research on Thermal Evolution and Hydrocarbon Expulsion History of Source Rocks in Low-exploration Basins—A Case Study on Jiaojiang Sag,East China Sea Basin[J].Petroleum Geology and Experiment,2012,34(3):319-324.
[19]纪友亮,李清山,王勇,等.高邮凹陷古近系戴南组扇三角洲沉积体系及其沉积相模式[J].地球科学与环境学报,2012,34(1):9-19.JI You-liang,LI Qing-shan,WANG Yong,et al.Fan Delta Sedimentary System and Facies Models of Dainan Formation of Paleogene in Gaoyou Sag[J].Journal of Earth Sciences and Environment,2012,34(1):9-19.
[20]张绍红.概率神经网络技术在非均质地层岩性反演中的应用[J].石油学报,2008,29(4):549-552.ZHANG Shao-hong.Application of Probabilistic Neural Network Technique to Lithology Inversion of Hetero-geneous Stratum[J].Acta Petrolei Sinica,2008,29(4):549-552.
[21]李曙光,徐天吉,唐建明,等.概率神经网络储层流体密度反演及应用[J].地质科技情报,2011,30(1):76-79.LI Shu-guang,XU Tian-ji,TANG Jian-ming,et al.Reservoir Fluid-density Inversion and Application Based on PNN[J].Geological Science and Technology,2011,30(1):76-79.
[22]肖波,韩学辉,周开金,等.测井曲线自动分层方法回顾与展望[J].地球物理学进展,2010,25(5):1802-1810.XIAO Bo,HAN Xue-hui,ZHOU Kai-jin,et al.A Review and Outlook of Automatic Zonation Methods of Well Log[J].Progress in Geophysics,2010,25(5):1802-1810.
[23]BROWN L F,FISHER J W L.Seismic Stratigraphic Interpretation and Petroleum Exploration[M].Boulder:AAPG,1980.
[24]黄锋,李志荣,廖玲,等.利用地震资料进行沉积相分析[J].物探化探计算技术,2003,25(3):197-200.HUANG Feng,LI Zhi-rong,LIAO Ling,et al.Sedimentary Facies Analysis Using Seismic Data[J].Computing Techniques for Geophysical and Geochemical Exploration,2003,25(3):197-200.
[25]陈恭洋,陈玲,朱洁琼,等.地震属性分析在河流相储层预测中的应用[J].西南石油大学学报:自然科学版,2012,34(3):1-8.CHEN Gong-yang,CHEN Ling,ZHU Jie-qiong,et al.Application of Seismic Attributes Analysis Fluvial Reservoir to Prediction[J].Journal of Southwest Petroleum University:Science and Technology Edition,2012,34(3):1-8.
[26]唐为清,郭荣坤,王忠东,等.沉积微相测井资料神经网络判别方法研究[J].沉积学报,2001,19(4):581-585.TANG Wei-qing,GUO Rong-kun,WANG Zhongdong,et al.The Study on Method of Depositional Microfacies Discrimination with Well-logging Information[J].Acta Sedimentologica Sinica,2001,19(4):581-585.
[27]张福明,李洪奇,邵才瑞,等.应用神经网络模式识别技术进行测井沉积学研究[J].石油勘探与开发,2003,30(3):121-123.ZHANG Fu-ming,LI Hong-qi,SHAO Cai-rui,et al.Application of Artificial Neural Network Pattern Recognition Technology to the Study of Well-logging Sedimentology[J].Petroleum Exploration and Development,2003,30(3):121-123.
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