The application of movable water saturation from the calculation of neural network method

DOI

10.2991/eeeis-16.2017.115How to use a DOI?

Keywords

Movable water saturation; Nonlinear; neural network; Predict the characteristics of water production

Abstract

Movable water saturation can accurately evaluate the formation of gas and water layer. It is an important parameter to guide the development of tight gas reservoirs. Engineering often used single factor of porosity to estimate saturation of the movable water. And in the formation of strong heterogeneity conditions, precision linear regression method will be affected, BP neural network rule can be a good fit multivariate highly nonlinear problems. Combining multiple factors logs to establish BP neural network model to calculate the formation of the movable water saturation, and applied to other wells area to verify the distribution of gas and water layer. The results show: at formation heterogeneity strong case, BP neural network computing movable water saturation with sufficient accuracy, and can accurately predict the characteristics of water production in gas well.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Wei Xiong
AU  - Jia-Feng Wu
AU  - Shu-Sheng Gao
AU  - Li-You Ye
AU  - Fei-Fei Gou
PY  - 2016/12
DA  - 2016/12
TI  - The application of movable water saturation from the calculation of neural network method
BT  - Proceedings of the 2nd Annual International Conference on Electronics, Electrical Engineering and Information Science (EEEIS 2016)
PB  - Atlantis Press
SP  - 946
EP  - 957
SN  - 2352-5401
UR  - https://doi.org/10.2991/eeeis-16.2017.115
DO  - 10.2991/eeeis-16.2017.115
ID  - Xiong2016/12
ER  -