摘要
油气层识别是测井解释的一项主要任务,现今采用基于统计学理论的常规识别方法本身存在不少缺点因而在应用中无法取得理想的效果。为此提出了一种基于粗集和神经网络的智能识别方法,先用粗集理论约简样本信息,然后采用带有非线性连接权的神经网络来识别油气层。通过塔里木油田实际油井的应用,结果表明这种识别方法的准确率远高于常规方法,且效果显著。
The oil & gas formation identification is an important task in logging interpretation.For there are some intrinsic shortcomings in present general identification methods based on statistics theory,it is hard to obtain an ideal effect in application.So a intelligence method based on rough set and neural network is presented to solve above problems,first,the rough set theory is applied in sample-information reduction,then the neural network with nonlinear connected weights is applied to identify oil & gas formation.Actual application example in Talimu oil-field shows the method is practicable,the identification accuracy is much better than that of general,and the interpretation effect is satisfactory.
出处
《计算机工程与应用》
CSCD
北大核心
2005年第5期190-192,共3页
Computer Engineering and Applications
基金
国家自然科学基金项目(编号:60173058)
中国石油天然气集团公司"九五"重点攻关项目(编号:2001-6-1)资助