Application of BP neural network model in productivity prediction and evaluation of CBM wells fracturing

6th Annual International Conference on Material Science and Engineering

Hu, Gang^1 ; Zhao, Yunxiang^2 ; Wang, Liguo^1 ; Li, Teshe^1 ; Tang, Zhaoqing^1 ; Guo, Dali^2

Guizhou Unconventional Gas RandD Center, Guiyang

550081, China^1

School of Sciences, Southwest Petroleum University, Chengdu, Sichuan

610500, China^2

关键词: BP artificial neural network models;    BP neural network model;    Cbm productions;    Cbm wells;    Degree of correlations;    Evaluation accuracy;    Geological conditions;    Gray correlation analysis;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/397/1/012070/pdf
DOI  :  10.1088/1757-899X/397/1/012070

来源: IOP

【 摘 要 】

The geological conditions of coal-bed methane (CBM) are complex in China, so it is difficult to predict the production of CBM wells. Methodology of artificial intelligence was introduced in the mining of CBM. According to the characteristics of target block reservoir, the gray correlation analysis technology is used for analyzing the degree of correlation between each parameter and CBM production. And then the BP artificial neural network model is used in prediction and evaluation of CBM wells fracturing production. Application results show that the method improves the prediction and evaluation accuracy of CBM production.