新疆石油地质

新疆石油地质 ›› 2005, Vol. 26 ›› Issue (5): 557-558.

• 油藏工程 • 上一篇    下一篇

基于人工神经网络的油气产量组合预测方法.

王磊1, 顾宏伟2, 姚恒申3   

  1. 1.西南石油学院研究生院,成都610500;
    2.中国石油 塔里木油田分公司 测井中心,新疆t 库尔勒841000;
    3.西南石油学院 计算机科学学院,成都610500
  • 收稿日期:2005-05-18 出版日期:2005-10-01 发布日期:2020-11-23
  • 作者简介:王磊(1981-),男,四川泸州人,在读硕上研究生,应用数学,(Tel)028-80961974(E-mail)f1ying9988@hotmail.com.
  • 基金资助:
    基金项日:油气藏地质及开发工程国家重点实验室(西南石油学院)“应用时间序列分析提高测井解释准确宰研究"(0121)资助

Artificial Neural Network-Based Combination Forecast Method for Oil-Gas Production

WANG Lei1, GU Hong-wei2, YAO Heng-shen3   

  1. 1. Posigraduate School, Southwest Petroleum Institute, Chengdu, Sichuan 610500, China;
    2. Well Log Center, Tarim Oilfeld Company, PetroChina, Korla, Xinjiang 841000, China;
    3. Computer Science Collge, Southwest Petroleum Institute, Chengdu, Sichuan 610500, China
  • Received:2005-05-18 Online:2005-10-01 Published:2020-11-23

PDF

203

摘要： 回顾了前人关于油气产量的预测方法,概述了传统组合预测方法的基本原理,在此基础上,对组合预测方法中基于最小二乘法的最优权重确定方法进行了改进,提出基于BP神经网络模型的最优权重确定方法,并将其应用于具体实例。结果表明,基于神经网络的组合预测模型能有效地提高油气产量预测精度,是比较优越的预测方法。

关键词: 产量, 预测, 精度, 神经网络, 模型

Abstract: The numerous existing methods for prediction of oil and gas production are reviewed, and the principle of conventional combination forecast method is explicated. The method for determining optimal weights in combination forecast based on least square method is improved. A novel method based on BP artifcial neural networks is proposed, which is also applied to the case study in this paper. The results show that this novel method or model a8 a preferential technique can be used to effectively improve the accuracy for prediction of oil-gas production.

Key words: production, prediction, accuracy, neural network, model

中图分类号: