基于Boosting-PLS回归的页岩总含气量预测方法  

Method to Predict Total Gas Content in Shale Reservoir Combing Boosting-PLS Algorithm and Conventional Logging Data

作　　者：冯明刚[1] 严伟[1] 朱林奇 葛新民[4] 刘帅[1] FENG Ming-gang;YAN Wei;ZHU Lin-qi;GE Xin-min;LIU Shuai(Explorationand and Research Institute of Sinopec Exploration Company,C hengdu 610041,China;Key Laboratory of Exploration Technologies for Oil and Gas Resources,Ministry of Education,Yangtze University,Wuhan 430100,China;Hubei Cooperative Innovation Center of Unconventional Oil and Gas,Yangtze University,Wuhan 430100,China;College of Earth Science and Technology,China University of Petroleum,Qingdao 266580,China)

机构地区：[1]中国石化勘探分公司勘探研究院,成都610041 [2]长江大学油气资源与勘探技术教育部重点实验室,武汉430100 [3]长江大学非常规油气湖北省协同创新中心,武汉430100 [4]中国石油大学(华东)地球科学与技术学院,山东青岛266580

出　　处：《煤炭技术》2018年第10期23-25,共3页Coal Technology

基　　金：国家科技重大专项(2017ZX05036005)

摘　　要：提出Boosting-PLS回归算法进行页岩总含气量的预测。提取最能反映含气性的密度、中子、铀、钍等测井信息,通过模型自动学习训练样本中输出曲线响应值与总含气量的响应关系,利用所得响应关系建立总含气量预测模型。Presents a method to predict the total gas content of shale reservoir by combining BoostingPLS algorithm with conventional logging data.The method is optimized by using the density curve,the uranium content curve,the thorium content curve,and the natural gamma log curve response value as input,the total gas content of reservoir obtained from core experiment as output,it studies automatically the relationship between the response value of the output curve and the total gas content through the model,by which it predicts the total gas content of the verified well.

关 键 词：页岩 总含量 偏最小二乘 Boosting-PLS 

分 类 号：P631[天文地球—地质矿产勘探] TD84[天文地球—地质学]