文章摘要
基于BP神经网络的煤层气井产水量预测研究
Study on Water Production of Coalbed Methane Well by Using BP Neural Network
投稿时间:2018-03-05  修订日期:2018-03-05
DOI:
中文关键词: BP神经网络  MATLAB  煤层气井  产水量预测
英文关键词: BP Neural Network  MATLAB  Coalbed Methane Well  Water Production Forecast.
基金项目:国家自然科学基金项目(面上项目,重点项目,重大项目)
作者单位邮编
梅洋洋 河南理工大学资源与环境学院
河南理工大学资源与环境学院 
454003
王哲雷 河南理工大学资源与环境学院 454003
摘要点击次数: 985
全文下载次数: 0
中文摘要:
      在煤层气的生产开发过程中,由于产水量过大而导致降压解吸困难。因此,能够准确预测煤层气井产水量,对于煤层气井的生产开发具有十分重要的意义。本文基于时间序列预测思想,运用MATLAB软件,构建适合于煤层气井产水量预测的BP神经网络模型。在以沁水盆地南部柿庄TS-006井为预测实例的结果表明:BP神经网络模型能够较准确地预测出煤层气井未来7天的产水量,其平均绝对误差和平均相对误差分别为-0.08m3/d和-0.91%,从而可为煤层气井排采制度的调整提供科学依据。
英文摘要:
      During the development of coalbed methane, it is very difficult in depressurization and desorption of coal bed gas due to large amount of water production. Therefore, it is very important for the production and development of coalbed methane wells to predict the water production of coalbed methane wells accurately. This article is based on the idea of time series prediction, and using MATLAB software, finally the BP neural network model, which is suitable for the prediction of water production in coal bed gas wells, is constructed. The results of the prediction of the TS-006 well in Shizhuang, southern Qinshui Basin show that: this BP Neural Network model can accurately predict the water production of the coalbed methane wells in the next 7 days, the average error and relative error of water production forecast respectively -0.08m3/d和-0.91%,. Thus, it can provide a scientific basis for the adjustment of the drainage and production system of coal bed methane wells.
View Fulltext   查看/发表评论  下载PDF阅读器
关闭

手机扫一扫看 分享按钮