Title :
The Effect Prediction of Profile Control Measures with the SVM
Author :
Yuan, Shi-Bao ; Wang, Li ; Jiang, Hai-Yan
Author_Institution :
Coll. of Marine Earth Sci., Ocean Univ. of China, Qingdao, China
Abstract :
Aiming at the drawbacks of numerical simulation in the effect prediction of profile control, and by using the support vector machine method, this paper studies and predicts the 32 wells samples of DONGXIN block, on which the profile control is carried out. And in a reasonable range, the sample´s density of some factors is locally refined and the critical value of the factor is discussed. It is indicated that the results predicted with SVM method match the actual data very well. Compared with the results of numerical simulation, the precision of SVM is higher than that of reservoir numerical simulation.
Keywords :
control engineering computing; oil technology; petroleum industry; production engineering computing; support vector machines; DONGXIN block; SVM; critical factor value; oil production; profile control measure; reservoir numerical simulation; support vector machine; Automation; Electronic mail; Geologic measurements; Kernel; Marine technology; Numerical simulation; Petroleum; Sea measurements; Statistical learning; Support vector machines; Support Vector Machine (SVM); effect prediction; profile control;
Conference_Titel :
Intelligent Computation Technology and Automation, 2009. ICICTA '09. Second International Conference on
Conference_Location :
Changsha, Hunan
Print_ISBN :
978-0-7695-3804-4
DOI :
10.1109/ICICTA.2009.228
