• 责任者：Pang Heqing (College of Energy Resources ; Chengdu University of Technology ; Chengdu 610059 ; China) ; Kuang Jianchao
• 刊名：Geophysical and Geochemical Exploration
• 出版年：2012
• 卷期：36(6)
• 关键词：储层预测 ; reservoir prediction ; 支持向量机 ; support vector machine ; 主成分分析 ; principal components analysis
• 页码：p.1001-1005,1013
• 图表：2 illus., 3 tables, 16 refs.
• 分类号：1003
• issnNo：ISSN1000-8918
• isbnNo：CN 11-1906/P

Through the polynomial kernel function of the KPCA,the model can obtain the nonlinear feature extraction.Then the Gaussian kernel function in the SVM is chosen to perform optimization again.Finally,reservoir identification is implemented in the SVM.As the model incorporates the advantages of kernel function,principal component analysis and support vector classification,it can better solve the problem of nonlinear small sample,eliminate the noise of the data and reduce the dimension without missing valid information.The model was employed to predict the reservoir in x856 well block,which belongs to Xu2 member gas reservoir of the Xinchang gas field.The results show the superiority of this model.