西南石油大学学报(自然科学版)

• 地质勘探 • 上一篇    下一篇

新场气田须二气藏单井气水层识别模型研究

庞河清1,匡建超2,3,蔡左花4,廖开贵4,王众2,3   

  1. 1. 中国石化西南油气分公司博士后科研工作站,四川成都610041;2. 成都理工大学能源学院,四川成都610059;
    3. 成都理工大学管理科学学院,四川成都610059;4. 中国石化西南油气分公司勘探开发研究院,四川成都6100411.
  • 出版日期:2014-04-01 发布日期:2014-04-01
  • 基金资助:

    教育部规划基金项目(11YJAZH043);四川石油天然气研究中心项目(川油气科SKA09–01)。

Study on Gas-water Layer Identification Model in the Single Well
of Xu 2 Gas Reservoir of Xinchang Gas Field

Pang Heqing1, Kuang Jianchao2,3, Cai Zuohua4, Liao Kaigui4, Wang Zhong2,3   

  1. 1. Post-doctoral Research Station,SWPB,SINOPEC,Chengdu,Sichuan 610041,China
    2. College of Energy Resources,Chengdu University of Technology,Chengdu,Sichuan 610059,China
    3. College of Management Science,Chengdu University of Technology,Chengdu,Sichuan 610059,China
    4. Exploration and Development Institute,SWPB,SINOPEC,Chengdu,Sichuan 610041,China
  • Online:2014-04-01 Published:2014-04-01

摘要:

川西新场气田须二气藏为典型的低渗致密碎屑岩气藏,由于地质条件复杂,储层非均质性严重,气水分布十分复
杂,束缚水含量较高,气层、气水同层电阻率界限模糊不清,测井解释往往造成很大误判。针对这一难点,应用基于粒子群
算法(PSO)的核主成分分析与支持向量机(KPCA–SVM)模型进行气水层识别。模型先通过核主成分分析(KPCA)进行
非线性属性变量提取,再将提取的属性变量作为支持向量机(SVM)的输入变量,在识别过程中利用粒子群算法(PSO)寻
优,最终实现气水层识别。将模型应用于新场气田须二气藏气水层识别,识别结果符合研究区的实际情况。

关键词: 粒子群算法, 核主成分分析, 支持向量机, 气水层识别, 新场须二气藏

Abstract:

Xu 2 Gas Reservoir,which is in Xinchang Gas Field in western Sichuan Basin,is a typical low-permeability and tight
clastic gas reservoir. Due to the complicated geological conditions and serious heterogeneity in this area,the gas-water layer
distribution is very complicated,and the bound water’s content is high. The boundaries of resistivity between gas reservoir and
gas-water layer are blurred,so that some mistakes arise in log interpretation. We use kernel principal component analysis and
support vector machine,also known as KPCA–SVM model,which is based on particle swarm optimization(PSO),to solve
the problem. Firstly,the model extracts non-linear properties of variables by kernel principal component analysis(KPCA),
and then inputs the properties of a variable into the support vector machine(SVM). And in the identification process,we
use the particle swarm optimization(PSO)to seek the optimization algorithm. Finally,the gas-water layer identification is
implemented in the SVM. We applied this model to gas & water layer prediction of Xu 2 Member gas reservoir of Xinchang
Gas Field,and the recognition result is in line with the actual situation of the study area.

Key words: particle swarm optimization, kernel principal component analysis, support vector machine, gas-water layer identification,
Xu 2 Member gas reservoir of Xinchang Gas Field