期刊文献+

松辽盆地中央坳陷区储层岩性智能识别方法 被引量:2

Intelligent Identification Method of Reservoir Lithology in Central Depression of Songliao Basin
下载PDF
导出
摘要 岩性信息的识别分类对油气储层分类以及储层岩石可压性评价具有重要意义。本文根据对深度学习网络U-Net进行改进,结合松辽盆地中央坳陷区实验数据进行对比和验证,提出了一种更适合测井数据的特征注意力融合网络(feature attention fusion Unet,FAF-Unet)。测井数据主要通过敏感性分析的方式选择特征参数(自然电位,声波时差,光电吸收截面指数,井径,密度,自然伽马以及深、浅侧向电阻率等),分析储层岩石岩性。FAF-Unet是一种融合残差块和通道注意力机制的网络,残差块可以更好地保留深度方向低级特征的数据,而通道注意力机制可以弥补竖向卷积时忽略横向通道之间联系的问题。分别对比了支持向量机、决策树、U-Net、添加有效通道注意力(efficient channel attention,ECA)机制的U-Net(ECA-Unet)、添加残差块的U-Net(Res-Unet)以及同时添加ECA和残差块的FAF-Unet 6种识别方法的准确率和召回率,结果表明,FAF-Unet的准确率与召回率均达到89.00%以上,在6种识别方法中识别效果最佳,且准确率与召回率的波动范围更小。 The recognition and classification of lithological information hold significant importance for categorizing oil and gas reservoirs and evaluating the compressibility of reservoir rocks.This study presents enhancements to the deep learning network U-Net and conducts a comparative validation using experimental data from central depression of Songliao Basin.We propose a more suitable feature attention fusion Unet(FAF-Unet)designed for well logging data.The selection of logging data primarily involves sensitivity analysis to identify characteristic parameters,including natural potential,acoustic time difference,photoelectric absorption cross-section index,wellbore diameter,density,natural gamma,and deep and shallow lateral resistivity.These parameters are analyzed to understand reservoir rock lithology.FAF-Unet is a network that amalgamates residual blocks and channel attention mechanisms.Residual blocks can better retain the data with lower-level features of the depth direction,and channel attention mechanisms can make up for the problem of ignoring the connection between horizontal channels during vertical convolution.Comparing the accuracy and recall of six recognition methods,including support vector machine,decision tree,U-Net,U-Net with effective channel attention(ECA)mechanism,U-Net with residual block(Res-Unet),and FAF-Unet with both ECA and residual block,experimental results demonstrate that FAF-Unet achieves an accuracy and recall rate exceeding 89.00%.FAF-Unet outperforms the other five methods in terms of recognition performance and exhibits a narrower fluctuation range between accuracy and recall.
作者 王婷婷 孙振轩 戴金龙 姜基露 赵万春 Wang Tingting;Sun Zhenxuan;Dai Jinlong;Jiang Jilu;Zhao Wanchun(School of Electrical Engineering&Information,Northeast Petroleum University,Daqing 163318,Heilongjiang,China;Institute of Unconventional Oil&Gas,Northeast Petroleum University,Daqing 163318,Heilongjiang,China)
出处 《吉林大学学报(地球科学版)》 CAS CSCD 北大核心 2023年第5期1611-1622,共12页 Journal of Jilin University:Earth Science Edition
基金 国家自然科学基金项目(52074088,52174022,51574088,51404073) 东北石油大学黑龙江省杰出青年后备人才项目(SJQHB201802,SJQH202002) 东北石油大学西部油田开拓专项项目(XBYTKT202001) 黑龙江省博士后科研启动项目(LBH-Q20074,LBH-Q21086)。
关键词 岩性识别 深度学习 残差块 通道注意力机制 U-Net lithology lecognition deep learning residual blocks channel attention mechanism U-Net
  • 相关文献

参考文献8

二级参考文献73

共引文献61

同被引文献41

引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部