波形分类中半自动确定分类数的方法

详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文

英文篇名：A new method for semi-automatic definition of cluster number in waveform classification 中文刊名：石油地球物理勘探 英文刊名：Oil Geophysical Prospecting 作者：熊伟 ; 万忠宏 ; 刘兰锋 ; 陈茂山 ; 张中平 英文作者：Xiong Wei1 ; Wan Zhong-hong1 ; Liu Lan-feng2 ; Chen Mao-shan1 and Zhang Zhong-ping1. 1. Geophysical Technology Research Centre ; BGP Inc. of CNPC ; Zhuozhou City ; Hebei province ; 072751 ; China2. Faculty of Natural Resources and Information Technology ; China University of Petroleum ; Beijing City ; 102249 ; China 中文关键词：自组织神经网络 ; 波形分类 ; 地震相 ; 分类数 英文关键词：self-organized neural network ; waveform classification ; seismic facies ; cluster number 出版日期：2010-04-15 机构：东方地球物理公司物探技术研究中心;中国石油大学(北京)资源与信息学院; 年：2010 期：02 出版单位：石油地球物理勘探

摘要

波形分类方法是现今比较成熟的地震相分析方法,此法已在岩性预测、砂体预测、裂缝性油气藏和隐蔽性油气藏预测中得到广泛的应用。然而,在以往实际应用中采用输入层为二维Kohonen网络进行地震相分类数的选择都是靠经验或试验方法确定的,增加了分类的不确定性和相应的工作量。本文提出了用改进的输出层为一维的自组织神经网络,半自动地估计地震相分类数。理论模型验证和实例应用表明,改进的Kohonen网络能很好地估计地震相分类数,从而实现快速准确地划分地震相。
The waveform classification is the mature method in seismic facies analysis, it has been widely used in lithology prediction, sandbody prediction, fracture reservoir prediction and subtle reservoir prediction. However in the past application of the method the selection of seismic facies cluster classification for 2d Kohonen network which was took as input layer was determined by experience and testing, as a result the uncertainty and work load for the classification were increased, then a improved Kohonen network was introduced in this paper to semi-automatically estimate seismic facies cluster number. The theoretical modeling and field data application show that the improved Kohonen network works very well for the estimation of seismic facies cluster number so that the fast classification of seismic facies was realized.

引文

[1]殷积峰等.波形分类技术在川东生物礁气藏预测中的应用.石油物探,2007,46(1):53~57
    [2]袁全社,乐友喜.用神经网络与构造属性进行交互地震相分析.石油地球物理勘探,2004,39(2):158~162
    [3]Paradigm地球物理公司.Strati magic2.0培训手册.2002
    [4]黄凤岗等.模式识别.黑龙江哈尔滨:哈尔滨工程大学出版社,1998
    [5]陈遵德.储层地震属性优化.北京:石油工业出版社,1997
    [6]罗立名,王允诚.自组织特征映射网络的改进及在储层预测中的应用.石油地球物理勘探,1997,32(2):237~245
    [7]Marclio Castro de Matos et al.Unsupervised seismic facies analysis using wavelet transformand self-organi-zing maps.Geophysics,2007,72(1):9~21
    [8]Santos MS.Caracteriza a~o de reservat幃rios via redes neurais:M.Sc.thesis.Bahia Federal University,1997