神经网络方法识别测井曲线形态  

LOGGING CURVE SHAPE IDENTIFICATION USING SELF-ORGANIZATION NEURAL NETWORK

作　　者：张冰[1] 潘保芝[1] 王英伟[1] 张平[2] 

机构地区：[1]吉林大学地球探测科学与技术学院,吉林长春130026 [2]中国石油勘探开发研究院西北分院,甘肃兰州730020

出　　处：《物探化探计算技术》2009年第6期611-616,共6页Computing Techniques For Geophysical and Geochemical Exploration

摘　　要：随着油田勘探开发程度的不断提高,要找到有利的油气聚集带以及在开发阶段提高油田采收率,都必须进行储层沉积相分析。这里介绍一种利用自组织神经网络识别曲线形态的方法。采用将测井曲线网格化,再利用自组织神经网络识别曲线形态,进而去判别沉积相。此方法可以对测井曲线形态进行识别,且消除了测井曲线中的不确定因素,运用该方法对实际测井曲线形态的识别基本正确。With the deep exploration and development of oilfield,sedimentary facies analysis is needed in order to find more favorable hydrocarbon accumulation zone,or to increase productivity.The paper introduces a method to identify the log curve shape using self-organization neural network.In this method,the curve is firstly gridded,then the curve shape is identified using the self-organization neural network,and the sedimentary facies could be identified finally.This method can be used to identify the log curve shape and remove some uncertain factors from log data.In this paper,the identification of the actual curve is basically accurate by using the method.

关 键 词：自组织神经网络 曲线形态 模式识别 沉积相 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]