自组织特征映射神经网络在测井岩性识别中的应用  

The application of self-organizing feature map neural network to logging lithological identification

作　　者：张治国[1] 杨毅恒[1] 夏立显[1] 

机构地区：[1]吉林大学综合信息矿产预测研究所,长春130026

出　　处：《地球物理学进展》2005年第2期332-336,共5页Progress in Geophysics

基　　金：国家"863"计划项目(2001AA1351202)资助.

摘　　要：为了解决测井岩性识别问题,引入具有较强的聚类和容错能力的自组织特征映射(SOFM)神经网络.在说明SOFM网络的模型和算法的基础上,结合某地的实际测井资料,建立SOFM网络岩性识别模型,进行岩性识别的应用研究.结果表明,识别的准确率较高,证明SOFM网络可以用于解决测井岩性识别问题,具有很好的应用前景.Based on the self-organizing feature map(SOFM) neural network this paper introduces a logging lithological identification technology. First, it describes the model and algorithm of the SOFM network. Then an example is used to show how to build up an SOFM network model for logging lithological identification and its application to logging lithological identification. The results indicate that the accuracy of identification is high and the SOFM network can be used in lithological identification of logging data, which has good prospects.

关 键 词：自组织特征映射 人工神经网络 测井资料 岩性识别 

分 类 号：P631[天文地球—地质矿产勘探] P628[天文地球—地质学]