西南石油大学学报(自然科学版) ›› 2006, Vol. 28 ›› Issue (1): 5-8.DOI: 10.3863/j.issn.1000-2634.2006.01.002

• 地质勘探 • 上一篇    下一篇

基于神经网络的多属性火成岩岩性反演技术

冉启全 周雪峰 胡永乐
  

  1. (中国石油勘探开发研究院,北京,100083)
  • 收稿日期:2005-03-17 修回日期:1900-01-01 出版日期:2006-02-20 发布日期:2006-02-20
  • 通讯作者: 冉启全

MULTIATTRIBUTES LITHOLOGICAL INVERSION OF IGNEOUS ROCKS BASED ON NEURAL NETWORK

RAN Qi-quan ZHOU Xue-feng HU Yong-le.
  

  1. ( Research Institute of Petroleum Exploration and Development of Petrochina, Beijing 100083,China)
  • Received:2005-03-17 Revised:1900-01-01 Online:2006-02-20 Published:2006-02-20
  • Contact: RAN Qi-quan

摘要: 在岩心分析的基础上应用地质测井地震等多学科资料对枣园火成岩的岩性电性波阻杭特征进行了研究并对岩性、电性与波阻杭、地震属性间的相关性进行了系统分析。在此基础上,针对常规波阻杭反演方法的不足,形成了一套基于神经网络的多属性岩性反演技术,采用该技术对枣园火成岩不同岩性进行了反演,给出了火成岩厚度及孔隙度分布。

关键词: 火成岩, 岩性, 电性, 地震属性, 神经网络, 岩性反演

Abstract: Based on core analysis, the lithalogies, electrology charac-ters, and wave impedance characteristics of Igneous Rocks have been analyzed with geological, logging, seismic and many other information. The carrelativity between the lithologies, electrology characters and wave impedance, seismic attribute has been systematically investigated. To overcome the shortage of conven-tional wave impedance inversion, a set of multi一attributes 1i-thological inversion of Igneous Rocks based on neural network has been established. The lithologies of Igneous Rock in Zaoyuan oilfield have been predicted with the inversion method ,and the distribution of thickness and porosity were given.

Key words: Igneous Rock, lithalogies, electrology characters, seismic attribute, neural network, lithological inversion

中图分类号: