DocumentCode :
2914353
Title :
Research on modeling method of water displacing oil physical simulation based on support vector machine
Author :
Gao, Meijuan ; Tian, Jingwen ; Zhou, Hao
Author_Institution :
Beijing Union Univ., Beijing
fYear :
2007
fDate :
18-20 Nov. 2007
Firstpage :
1128
Lastpage :
1133
Abstract :
An actual physical simulation model was constructed to simulate the course of water displacing oil Under certain physical property parameter conditions, we simulated the water injection well and the oil withdrawal well on the physical simulation model, and continuous measured online the oil and water content of different areas of physical simulation model in three-dimensional spaces using the 512 routes resistivity measuring circuit, then we can obtain large numbers of simulation samples. Considering the issues that the relationship between the remaining oil and every parameters of water displacing oil is complicated and nonlinear, the support vector machine (SVM) was used to establish the water displacing remaining oil model, in order to obtain the distributing situation of remaining oil in various complicated conditions. We proposed a self-adaptive parameter adjust iterative algorithm to confirm SVM parameters. The experimental results show that this method is feasible and effective.
Keywords :
digital simulation; iterative methods; oil technology; petroleum industry; solid modelling; support vector machines; oil industry; oil withdrawal well; self-adaptive parameter adjust iterative algorithm; support vector machine; three-dimensional space; water displacing oil physical simulation modeling; water injection well; Area measurement; Artificial neural networks; Circuit simulation; Hydrocarbon reservoirs; Intelligent systems; Petroleum; Production; Solid modeling; Support vector machines; Water resources;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Grey Systems and Intelligent Services, 2007. GSIS 2007. IEEE International Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4244-1294-5
Electronic_ISBN :
978-1-4244-1294-5
Type :
conf
DOI :
10.1109/GSIS.2007.4443448
Filename :
4443448
Link To Document :
بازگشت