论文详情

基于BP神经网络的油田生产动态分析方法

断块油气田

2013年 20卷第02期

阅读：108

查看详情

Title

Analysis method of oilfield production performance based on BP neural network

作者

樊灵赵孟孟殷川朋兴亚

单位

中国石油大学（华东）石油工程学院，山东东营 257061 中海石油（中国）有限公司天津分公司，天津 300452

Organization

College of Petroleum Engineering, China University of Petroleum, Dongying 257061, China Tianjin Branch of CNOOC Ltd., Tianjin 300452, China

摘要

为克服目前生产动态分析方法所需数据量大、费工费时和应用局限性大等缺点，文中提出了一种基于BP神经网络的油田生产动态分析新方法。该方法使用一些广泛易得的数据（如测井数据、生产历史数据）建立数据集，然后利用神经网络建模技术建立全油藏范围的基于数据驱动的预测模型，进行预测分析。实际油藏应用结果表明，产油速度的最大预测误差低于7%，产水速度的预测误差低于5%。预测效果较好，具有一定的应用和研究价值。

Abstract

Aiming at the situation that many techniques of production performance analysis require lots of data and are expensive considering the computational and human resources, and their applications are limited, this paper puts forward a new method based on BP neural network. It builds a dataset with some available measured data such as well logs and production history, then, builds a field-wide production model by neural network technique. The model will be used to predict. The technique is verified, which shows that the predicted results are consistent with the maximum error of oil production rate of lower than 7% and the !maximum error of water production rate of lower than 5%, having certain application and research value.

关键词：

神经网络; 生产动态; 数据集; 网格划分;

Keywords:

neural network; production performance; dataset; mesh delineation

;

基金项目

DOI

10.6056/dkyqt201302017