An Application of BP Neural Network Model to Predict the Moisture Content of Crude Oil

Ying Ming Zhou; Shu Wei Wang; Lin Lin

doi:10.4028/www.scientific.net/AMR.524-527.1327

Paper Titles

A New Model for Predicting Productivity and Application for Fractured Horizontal Wells
p.1310

A Novel Approach of Cuttings Transport with Bubbles in Horizontal Wells
p.1314

A Study of a New Stage Cementing Tool and its Field Application
p.1318

Air Foam Injection for EOR in Light Oil Reservoirs with High Heterogeneity
p.1322

An Application of BP Neural Network Model to Predict the Moisture Content of Crude Oil
p.1327

An Improved Artificial Neural Network for Recognition of Beam Pump Dynamometer Card
p.1331

Analysis of Acoustic Propagation Characteristic of Near-Bit Drill Tools
p.1335

Analysis of Interwell Communication by Rate Correlation Degree Method
p.1339

Analysis of Perforation Parameters under Fluid-Solid Coupling Theory
p.1344

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 524-527An Application of BP Neural Network Model to...

An Application of BP Neural Network Model to Predict the Moisture Content of Crude Oil

Abstract:

With the constant expansion of super heavy oil SAGD conversion development, the accurate testing of the crude oil in the high moisture content range is particularly important. In this paper, against the characteristics of Adopting SAGD technology exploiting heavy oil, BP neural network prediction model and calculation method has been adopted to predict the moisture content of crude oil. Through the study, the experimental data of the model were verified by the maximum prediction error is less than 3%, the accuracy of the forecast moisture content of crude oil to meet the site requirements. Through this study, the experimental data to the model was validated by the maximum prediction error is less than3%, the prediction accuracy of which to moisture content of crude oil is able to meet the requirements of the project site.

You might also be interested in these eBooks

Natural Resources and Sustainable Development II

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 524-527)

Pages:

1327-1330

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.524-527.1327

Citation:

Cite this paper

Online since:

May 2012

Authors:

Ying Ming Zhou, Shu Wei Wang, Lin Lin

Keywords:

BP Neural Network (BPNN), Model, Moisture Content of Crude Oil

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Goda H M，Maier H R，Behrenbruch P. SPE 93307，2005：312-314.

Google Scholar

[2] S.Dideron, A.Altentsetseg. Community land use planning in the Gobi Region, Mongolia: between centralised and market economy, Mongolian herders look for sustainable management systems [A]. Proceedings of the XXI International Grassland Congress and the VIII International Rangeland Congress (volumeⅡ) [C]. (2008)

Google Scholar

[3] NING Yang-cui,Zheng Xiao-xian, ZHAO Jing,JIANG Gui-juan The Key Laboratory for Silviculture and Conservation of Ministry of Education Beijing Forestry University Beijing, China. Forecasting the Natural Forest Stand Age Based on Artificial Neural Network Model [A]. 2010 International Conference on Computer and Communication Technologies in Agriculture Engineering（CCTAE 2010）（Volume 3）[C]. (2010)

DOI: 10.1109/cctae.2010.5544375

Google Scholar