石油与天然气地质 ›› 2004, Vol. 25 ›› Issue (3): 338-343.doi: 10.11743/ogg20040320

• 技术方法 • 上一篇    下一篇

神经网络在低渗透油田试井解释中的应用

王安辉1,3, 宇淑颖2, 张英魁3, 王龙源4苗德顺4, 盛国军5, 刘家君3, 王琳芳3   

  1. 1. 中国地质大学,北京 100083;
    2. 吉林松原市宁江区第一中学,吉林松原 138003;
    3. 吉林油田分公司勘探开发研究院,吉林松原 138003;
    4. 吉林石油集团有限责任公司运输公司,吉林松原 138003;
    5. 吉林石油集团有限责任公司热电厂,吉林松原 138003;
    6. 华北油田分公司第五采油厂,河北任丘 062500
  • 收稿日期:2004-03-15 出版日期:2004-06-25 发布日期:2012-01-16

Application of neural network in well test analysis in low permeability oilfield

Wang Anhui1,3, Yu Shuying2, Zhang Yingkui3, Wang Longyuan4, Miao Deshun5, Sheng Guojun3, Liu Jiajun3   

  1. 1. China University of Geosciences, Beijing;
    2. No.1 Middle School of Ningjiang District, Songyuan, Jilin;
    3. Exploration and Development Research Institute of Jilin Oilfield Company, Songyuan, Jilin;
    4. Transportation Company of Jilin Petroleum Group;
    5. Heat and Power Plant of Jilin Petroleum Group;
    6. No.5 Oil Production Plant of Huabei Oifield Company, Renqiu, Hebei
  • Received:2004-03-15 Online:2004-06-25 Published:2012-01-16

PDF (PC)

674

被引次数

29

摘要：

A油田是吉林油区开发较好的典型低渗透砂岩油藏,其试井解释比较复杂,压力恢复曲线出现径向流的井次仅占总井次的20%～30%。图形识别+神经网络BP算法+试井解释软件三位一体的联合技术能使未出现径向流的大部分井的压力恢复资料得到很好应用。该技术具体步骤为:(1)分析解释有径向流的井的双对数图和半对数图,找出续流段的伪斜率(m1)、拐点处的伪斜率(m2)、过渡段的伪斜率(m3)和径向流直线段斜率(m);(2)利用神经网络BP算法,构建m1,m2,m3与m之间的数学关系;(3)将未出现径向流的井的基础测试资料录入到试井解释软件中,求出m1,m2,和m3,利用BP算法求出m;(4)把以上参数代入进行拟合,直到双对数图、半对数图和历史拟合图三条曲线完全拟合为止。

关键词: 低渗透油田, 试井解释, 图形识别, 神经网络, BP算法

Abstract:

"A" oilfield is a typical low permeability sandstone oil reservoir that has relatively successfully been developed in Jilin oilfield area.The well test interpretation is relatively complicated.The times of radial flow occurring on wells'pressure build-up curves account for only 20%～30% of the total times occurring in all tested wells.This paper introduces an integrated interpretation technology by integrating pattern recognition,neural network BP algorithm and well test interpretation software.It can specifically divided into the following steps:(1)analyze and interprete the bilogarithmic and semilogarithmic diagrams of wells with radial flows,and find out the pseudoslopes(m1,m2,m3 and m)in the continuous flow section,at the flex point,in the transitional section and on the straight line section of radial flow;(2)applying the neural network BP algorithm to construct the mathematical relation among m1,m2,m3 and m;(3)input the basic testing data of the wells without radial flow into the well test interpretation software,derive the m1,m2 and m3,and then derive m with BP algorithm;(4)substitute the parameters mentioned above and fitting them through to the three curves in the bilogarithmic and semilogarithmic diagrams,and in historic fitting diagram to be fitting to one another.

Key words: low permeability oilfield, well test interpretation, pattern recognition, neural network, BP algorithm

中图分类号: