一种新的砂泥岩孔隙度估计模型及其应用
|
摘要
针对不同岩性的储层孔隙类型不同,孔隙度结构也存在较大差异,导致支持向量回归机(SVR)在孔隙度预测中效果不理想这一问题,提出在孔隙度预测模型中考虑岩性信息的方法。该方法将样本岩性转化为一种与岩性变化相关性好的属性值,以此构造出一种新的预测模型。对于模型参数优选,提出使用网格粗选和智能精选相结合的方法,网格粗选确定最优解的近似范围,智能精选(遗传算法、粒子群算法)可以在局部区间搜索到最优解。利用优选出的参数建立预测模型,并将预测结果与实测资料进行对比。对比结果表明:加入岩性信息提高了模型的预测精度;在参数精选中,使用智能方法的预测精度高于常规网格搜索法。
In view of the problem that support vector regression( SVR) cannot provide better porosity prediction because different lithologic reservoirs have different pore types and different porosity structures,a new model for estimating porosity,taking lithology information into account,is proposed. In the model,the lithology information of the sample is converted to attribute values that are closely associated with the lithology information. A method that combines the grid search algorithm for rough screening and intelligent search algorithms( genetic algorithms and particle swarm optimization) for fine filtering was used to optimize the model parameters. The grid search algorithm for rough screening was used to determine the approximate scope of the optimal solution,and intelligent search algorithms for fine filtering were used to determine the optimal solution in a local region. The optimized parameters were used to establish the forecasting model. The predicted results were compared with the measured data. The results show that the prediction accuracy of the model is greatly improved when the lithology information is taken into account,and the prediction accuracy of the intelligent search algorithms for fine filtering is higher than that of traditional methods.
In view of the problem that support vector regression( SVR) cannot provide better porosity prediction because different lithologic reservoirs have different pore types and different porosity structures,a new model for estimating porosity,taking lithology information into account,is proposed. In the model,the lithology information of the sample is converted to attribute values that are closely associated with the lithology information. A method that combines the grid search algorithm for rough screening and intelligent search algorithms( genetic algorithms and particle swarm optimization) for fine filtering was used to optimize the model parameters. The grid search algorithm for rough screening was used to determine the approximate scope of the optimal solution,and intelligent search algorithms for fine filtering were used to determine the optimal solution in a local region. The optimized parameters were used to establish the forecasting model. The predicted results were compared with the measured data. The results show that the prediction accuracy of the model is greatly improved when the lithology information is taken into account,and the prediction accuracy of the intelligent search algorithms for fine filtering is higher than that of traditional methods.
引文
[1]陈欢庆,曹晨,梁淑贤,等.储层孔隙结构研究进展[J].天然气地球科学,2013,24(2):227-237.(CHEN Huanqing,CAO Chen,LIANG Shuxian,et al.Research advances on reservoir pores[J].Natural Gas Geoscience,2013,24(2):227-237.(in Chinese))
[2]黄思静,郎咸国,兰叶芳,等.储层孔隙度-渗透率关系曲线中的截止孔隙度与储层质量[J].成都理工大学学报:自然科学版,2011,38(6):593-602.(HUANG Sijing,LANG Xianguo,LAN Yefang,et al.Porosity cut off of porosity-permeability curve and the reservoir quality[J].Journal of Chengdu University of Technology:Science&Technology Edition,2011,38(6):593-602.(in Chinese))
[3]范铭涛,沈全意,吴辉,等.复杂岩性裂缝-孔隙型储层孔隙度计算方法研究[J].天然气工业,2005,25(5):29-30.(FAN Mingtao,SHEN Quanyi,WU Hui,et al.Porosity calculation method of complex lithological fractured-porous reservoir[J].Natural Gas Industry,2005,25(5):29-30.(in Chinese))
[4]方中于,万欢,李勇.W地区储层孔隙度地震预测技术及应用研究[J].矿物岩石,2012,32(3):110-115.(FANG Zhongyu,WAN Huan,LI Yong.Research on the application of reservoir porosity prediction method in w district[J].Journal of Mineralogy and Petrology,2012,32(3):110-115.(in Chinese))
[5]朱永才,薛坤林.基于支持向量机的储层参数反演[J].茂名学院学报,2012,22(1):44-46.(ZHU Yongcai,XUE Kunlin.Inversion of reservoir parameters based on the support vector machine[J].Journal of Guangdong University of Petrochemical Technology,2012,22(1):44-46.(in Chinese))
[6]张彦周,王春香.支持向量机的测井数据预测储层渗透率方法[J].应用科学,2009,6(5):83-85.(ZHANG Yanzhou,WANG Chunxiang.SVM logging data to predict reservoir permeability method[J].Applied Science,2009,6(5):83-85.(in Chinese))
[7]陈华,邓少贵,范宜仁.基于LS-SVM的测井物性参数的预测方法[J].计算机工程与应用,2007,43(23):208-210.(CHEN Hua,DENG Shaogui,FAN Yiren.Forecast method of logging physical property parameters based on LS-SVM[J].Computer Engineering and Applications,2007,43(23):208-210.(in Chinese))
[8]史基安,王琪.影响碎屑岩天然气储层物性的主要控制因素[J].沉积学报,1995,13(2):128-139.(SHI Ji’an,WANG Qi.A discussion on main controlling factors on the properties of clastic gas reservoirs[J].Acta Sedimentologica Sinica,1995,13(2):128-139.(in Chinese))
[9]赖锦,王贵文,王书南,等.碎屑岩储层成岩相研究现状及进展[J].地球科学进展,2013,28(1):39-50.(LAI Jin,WANG Guiwen,Wang Shunan,et al.Research status and advances in the diagenetic facies of clastic reservoirs[J].Advances in Earth Science,2013,28(1):39-50.(in Chinese))
[10]廖士中,丁立中,贾磊.支持向量回归多参数的同时调节[J].南京大学学报:自然科学版,2009,45(5):585-592.(LIAO Shizhong,DING Lizhong,JIA Lei.Simultaneous tuning of multiple parameters for support vector regression[J].Journal of Nanjing University:Natural Sciences,2009,45(5):585-592.(in Chinese))
[11]李新虎.基于不同测井曲线参数集的支持向量机岩性识别对比[J].煤田地质与勘探,2007,35(3):72-76,80.(LI Xinhu.Lithology identification methods contrast based on support vector machines at different well logging parameter[J].Coal Geology&Exploration,2007,35(3):72-76,80.(in Chinese))
[12]王健峰,张磊,陈国兴,等.基于改进的网格搜索法的SVM参数优化[J].应用科技,2012,39(3):28-31.(WANG Jianfeng,ZHANG Lei,CHEN Guoxing,et al.A parameter optimization method for an svm based on improved grid search algorithm[J].Applied Science and Technology,2012,39(3):28-31.(in Chinese))
[13]熊伟丽,徐保国.基于PSO的SVR参数优化选择方法研究[J].系统仿真学报,2006,18(9):2442-2445.(XIONG Weili,XU Baoguo.Study on optimization of SVR Parameters selection based on PSO[J].Journal of System Simulation,2006,18(9):2442-2445.(in Chinese))
[14]杨俊燕,张优云,朱永生.ε不敏感损失函数支持向量机分类性能研究[J].西安交通大学学报,2007,41(11):1315-1320.(YANG Junyan,ZHANG Youyun,ZHU Yongsheng.Classification performance of support vector machine withε-insensitive loss function[J].Journal of xi’an Jiaotong University,2007,41(11):1315-1320.(in Chinese))
[15]赵晓明,罗明高.储层岩性不同油藏孔隙度下限确定方法研究[J].大庆石油地质与开发,2008,27(1):90-92,96.(ZHAO Xiaoming,LUO Minggao.Study on low limitation determination method for various reservoir porosity with various lithology[J].Petroleum Geology&Oilfield Development in Daqing,2008,27(1):90-92,96.(in Chinese))
[2]黄思静,郎咸国,兰叶芳,等.储层孔隙度-渗透率关系曲线中的截止孔隙度与储层质量[J].成都理工大学学报:自然科学版,2011,38(6):593-602.(HUANG Sijing,LANG Xianguo,LAN Yefang,et al.Porosity cut off of porosity-permeability curve and the reservoir quality[J].Journal of Chengdu University of Technology:Science&Technology Edition,2011,38(6):593-602.(in Chinese))
[3]范铭涛,沈全意,吴辉,等.复杂岩性裂缝-孔隙型储层孔隙度计算方法研究[J].天然气工业,2005,25(5):29-30.(FAN Mingtao,SHEN Quanyi,WU Hui,et al.Porosity calculation method of complex lithological fractured-porous reservoir[J].Natural Gas Industry,2005,25(5):29-30.(in Chinese))
[4]方中于,万欢,李勇.W地区储层孔隙度地震预测技术及应用研究[J].矿物岩石,2012,32(3):110-115.(FANG Zhongyu,WAN Huan,LI Yong.Research on the application of reservoir porosity prediction method in w district[J].Journal of Mineralogy and Petrology,2012,32(3):110-115.(in Chinese))
[5]朱永才,薛坤林.基于支持向量机的储层参数反演[J].茂名学院学报,2012,22(1):44-46.(ZHU Yongcai,XUE Kunlin.Inversion of reservoir parameters based on the support vector machine[J].Journal of Guangdong University of Petrochemical Technology,2012,22(1):44-46.(in Chinese))
[6]张彦周,王春香.支持向量机的测井数据预测储层渗透率方法[J].应用科学,2009,6(5):83-85.(ZHANG Yanzhou,WANG Chunxiang.SVM logging data to predict reservoir permeability method[J].Applied Science,2009,6(5):83-85.(in Chinese))
[7]陈华,邓少贵,范宜仁.基于LS-SVM的测井物性参数的预测方法[J].计算机工程与应用,2007,43(23):208-210.(CHEN Hua,DENG Shaogui,FAN Yiren.Forecast method of logging physical property parameters based on LS-SVM[J].Computer Engineering and Applications,2007,43(23):208-210.(in Chinese))
[8]史基安,王琪.影响碎屑岩天然气储层物性的主要控制因素[J].沉积学报,1995,13(2):128-139.(SHI Ji’an,WANG Qi.A discussion on main controlling factors on the properties of clastic gas reservoirs[J].Acta Sedimentologica Sinica,1995,13(2):128-139.(in Chinese))
[9]赖锦,王贵文,王书南,等.碎屑岩储层成岩相研究现状及进展[J].地球科学进展,2013,28(1):39-50.(LAI Jin,WANG Guiwen,Wang Shunan,et al.Research status and advances in the diagenetic facies of clastic reservoirs[J].Advances in Earth Science,2013,28(1):39-50.(in Chinese))
[10]廖士中,丁立中,贾磊.支持向量回归多参数的同时调节[J].南京大学学报:自然科学版,2009,45(5):585-592.(LIAO Shizhong,DING Lizhong,JIA Lei.Simultaneous tuning of multiple parameters for support vector regression[J].Journal of Nanjing University:Natural Sciences,2009,45(5):585-592.(in Chinese))
[11]李新虎.基于不同测井曲线参数集的支持向量机岩性识别对比[J].煤田地质与勘探,2007,35(3):72-76,80.(LI Xinhu.Lithology identification methods contrast based on support vector machines at different well logging parameter[J].Coal Geology&Exploration,2007,35(3):72-76,80.(in Chinese))
[12]王健峰,张磊,陈国兴,等.基于改进的网格搜索法的SVM参数优化[J].应用科技,2012,39(3):28-31.(WANG Jianfeng,ZHANG Lei,CHEN Guoxing,et al.A parameter optimization method for an svm based on improved grid search algorithm[J].Applied Science and Technology,2012,39(3):28-31.(in Chinese))
[13]熊伟丽,徐保国.基于PSO的SVR参数优化选择方法研究[J].系统仿真学报,2006,18(9):2442-2445.(XIONG Weili,XU Baoguo.Study on optimization of SVR Parameters selection based on PSO[J].Journal of System Simulation,2006,18(9):2442-2445.(in Chinese))
[14]杨俊燕,张优云,朱永生.ε不敏感损失函数支持向量机分类性能研究[J].西安交通大学学报,2007,41(11):1315-1320.(YANG Junyan,ZHANG Youyun,ZHU Yongsheng.Classification performance of support vector machine withε-insensitive loss function[J].Journal of xi’an Jiaotong University,2007,41(11):1315-1320.(in Chinese))
[15]赵晓明,罗明高.储层岩性不同油藏孔隙度下限确定方法研究[J].大庆石油地质与开发,2008,27(1):90-92,96.(ZHAO Xiaoming,LUO Minggao.Study on low limitation determination method for various reservoir porosity with various lithology[J].Petroleum Geology&Oilfield Development in Daqing,2008,27(1):90-92,96.(in Chinese))