计算物理 ›› 1998, Vol. 15 ›› Issue (6): 761-768.

• 论文 • 上一篇    下一篇

CUSI网络与遗传算法结合计算油气储层物性参数

陈遵德1, 蒋先艺2, 王建华3   

  1. 1. 江汉石油学院物探系, 湖北 434102;
    2. 石油物探局二处, 河南 475002;
    3. 大港油田研究院, 天津 300280
  • 收稿日期:1997-04-16 修回日期:1998-06-12 出版日期:1998-11-25 发布日期:1998-11-25
  • 作者简介:陈遵德,男,42,副教授,硕士
  • 基金资助:
    国家自然科学基金及湖北省自然科学基金资助

CALCULATING PHYSICAL PROPERTY PARAMETERS OF OIL GAS RESERVOIR BY COMBINING CUSI NETWORK WITH GENETIC ALGORITHM

Chen Zunde1, Jiang Xianyi2, Wang Jianhua3   

  1. Geophysical Dept., Jianghan Petroleum University, Jingzhou, Hubei 434102
  • Received:1997-04-16 Revised:1998-06-12 Online:1998-11-25 Published:1998-11-25

摘要: 油气储层物性参数(简称储层参数)是储层描述的重要参数。考虑到地震数据求取储层参数的复杂性与BP网络非线性映射需要利用全体样本信息且学习效率低等不足,提出采用完全利用样本信息(CUSI)的网络与遗传算法结合计算储层参数的方法。

关键词: 函数逼近, 神经网络, 遗传算法, 储层物性, 特征优化

Abstract: Physical property parameters of oil gas reservoir(i.e.reservoir parameters) are important in reservoir description. Considering both the complexity of finding reservoir parameters by seismic data and the shortages of the nonlinear mapping of BP network which needs complete sample information and is the low effciency of learning.This paper presents a method combining Complete Utilization of Sample Information (CUSI) with genetic algorithm(GA) to calculate these parameters.

Key words: function approximation, aitificial neural network, genetic algorithm, reservoir physical properties, feature optimization

中图分类号: