DocumentCode :
2599146
Title :
Functional Network softsensor for formation porosity and water saturation in oil wells
Author :
Adeniran, Ahmed ; Elshafei, M. ; Hamada, Gharib
Author_Institution :
King Fahd Univ. of Pet. & Miner., Dhahran, Saudi Arabia
fYear :
2009
fDate :
5-7 May 2009
Firstpage :
1138
Lastpage :
1143
Abstract :
Formation porosity and water saturation play important role in evaluating potential oil reservoirs and for drafting development plans for new oil fields. This paper presents a novel method for estimating these two important parameters directly from conventional well measurements. The recently proposed Functional Networks technique is applied for rapid and accurate prediction of these parameters, using six and five basic well log measurements as data for estimating porosity and water saturation respectively. Functional network is a generalization of the conventional Feed Forward Neural Networks, which overcome many of the drawbacks of the conventional neural network techniques. The proposed functional network was trained using data gathered from two wells in the Middle East region. Results obtained from this case study using the proposed intelligent technique have shown to be fast and accurate.
Keywords :
feedforward neural nets; hydrocarbon reservoirs; oil technology; porosity; virtual instrumentation; well logging; Middle East region; feed forward neural networks; formation porosity estimation; functional network softsensor; intelligent technique; oil field drafting development; oil reservoirs; oil wells; water saturation; well log measurements; Feedforward neural networks; Hydrocarbon reservoirs; Instrumentation and measurement; Laboratories; Minerals; Neural networks; Neurons; Petroleum; Technical drawing; Water resources; component; functional networks; neural networks; porosity; water saturation; well log;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Instrumentation and Measurement Technology Conference, 2009. I2MTC '09. IEEE
Conference_Location :
Singapore
ISSN :
1091-5281
Print_ISBN :
978-1-4244-3352-0
Type :
conf
DOI :
10.1109/IMTC.2009.5168625
Filename :
5168625
Link To Document :
بازگشت