[1]陈钢花,梁莎莎,王军,等.卷积神经网络在岩性识别中的应用[J].测井技术,2019,43(02):129-134.[doi:10.16489/j.issn.1004-1338.2019.02.004]
 CHEN Ganghua,LIANG Shasha,WANG Jun,et al.Application of Convolutional Neural Network in Lithology Identification[J].WELL LOGGING TECHNOLOGY,2019,43(02):129-134.[doi:10.16489/j.issn.1004-1338.2019.02.004]
点击复制

卷积神经网络在岩性识别中的应用()
分享到:

《测井技术》[ISSN:1004-1338/CN:61-1223/TE]

卷:
第43卷
期数:
2019年02期
页码:
129-134
栏目:
处理解释
出版日期:
2019-06-20

文章信息/Info

Title:
Application of Convolutional Neural Network in Lithology Identification
文章编号:
1004-1338(2019)02-0129-06
作者:
陈钢花1 梁莎莎1 王军2 隋淑玲2
(1.中国石油大学(华东)地球科学与技术学院, 山东 青岛 266580; 2.中国石油化工股份有限公司胜利油田分公司勘探开发研究院, 山东 东营 257000)
Author(s):
CHEN Ganghua1 LIANG Shasha1 WANG Jun2 SUI Shuling2
(1. School of Geosciences, China University of Petroleum, Qingdao, Shandong 266580, China; 2. Research Institute of Exploration and Development, Shengli Oilfield Company, SINOPEC, Dongying, Shandong 257000, China)
关键词:
测井解释 深度学习 卷积神经网络 岩性识别
Keywords:
logg interpretation deep learning convolutional neural network lithology identification
分类号:
P631.84
DOI:
10.16489/j.issn.1004-1338.2019.02.004
文献标志码:
A
摘要:
深度学习是人工智能中的一个重要部分,卷积神经网络作为深度学习一个分支,用多层非线性计算单元可以表达高度非线性和高变度函数。提出将卷积神经网络应用于判别储层岩性的方法,构建了一个双层的卷积神经网络模型,样本回判准确率为99%。通过把卷积神经网络方法与岩石物理相方法和支持向量机方法进行对比,分析卷积神经网络方法准确率高、速度快,岩性预测具有实时性。由此证明卷积神经网络在储层岩性识别中的适用性,且准确率较高。
Abstract:
Deep learning is an important part of artificial intelligence. As a branch of deep learning, convolutional neural networks can express highly nonlinear and highly variable functions with multi-layer nonlinear computing units. A method of using convolution neural network to discriminate reservoir lithology is proposed, and a two-layer convolution neural network model is established in this paper. The accuracy of sample retroaction is 99%. Compared with petrophysical facies and support vector machine, the convolution neural network method predicts reservoir lithology accurately, fast and real-time. It has been proved applicable for reservoir lithology identification.

参考文献/References:

[1] RUMELHART D E. Paralled distributed processing, 1&2 [M]. MIT Press: Cambridge, MA, 1986. [2] 刘争平, 何永富. 人工神经网络在测井解释中的应用 [J]. 地球物理学报, 1995(增刊1): 323-330. [3] 杨辉, 黄健全, 胡雪涛, 等. BP神经网络在致密砂岩气藏岩性识别中的应用 [J]. 油气地球物理, 2013, 11(1): 39-42. [4] HUBEL D, WIESEL T. Receptive fields, binocular interaction, and function architecture in the cat's visal cortex [J]. Journal of Physiology, 1962, 160: 106-154. [5] LECUN Y, BOSER B. Back propagation applied to handwritten zip code recognition [J]. Neural Computation, 1989, 1(4): 541-551. [6] LECUN Y, BOTTOU L, et al. Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324. [7] HITON G E, SALAKHUTDIOV R R. Reducing the dimensionality of data with neural networks [J]. Science, 2006, 313(5786): 504-507. [8] 段友祥, 李根田, 孙歧峰. 卷积神经网络在储层预测中的应用研究 [J]. 通信学报, 2016, 37(增刊1): 1-9. [9] HITON G E, OSINDERO S, THE Y W. A fast learning algorithm for deep belief nets [J]. Neural Computation, 2006, 18(7): 1527-1554. [10] 董宁芳. 浅析沾化凹陷构造演化对沙四段成藏的控制作用 [J]. 中国新技术新产品, 2013(7): 135-136.

相似文献/References:

[1]赵军龙,李甘,李传浩,等.鄂尔多斯盆地Z区长81储层流体快速识别技术研究[J].测井技术,2012,36(05):485.
 ZHAO Junlong,LI Gan,LI Chuanhao,et al.Research on the Fast Identification Technique about Fluid Property of Chang 81 Reservoirs at Z Block in Ordos Basin[J].WELL LOGGING TECHNOLOGY,2012,36(02):485.
[2]关丽.偶极子声波测井在罗家地区沙三段泥页岩储层评价中的应用[J].测井技术,2012,36(05):495.
 GUAN Li.Application of Dipole Acoustic Logging to Shale Reservoir Evaluation of Luojia Area[J].WELL LOGGING TECHNOLOGY,2012,36(02):495.
[3]赵永刚,冉利民,吴非.螺纹井眼测井曲线频域滤波校正[J].测井技术,2012,36(05):499.
 ZHAO Yonggang,RAN Limin,WU Fei.Frequency Domain Filtering Correction of Log Data from a Corkscrew Borehole[J].WELL LOGGING TECHNOLOGY,2012,36(02):499.
[4]李山生,黄质昌,杜蕊,等.WaxmanSmits模型中参数B和QV计算方法研究[J].测井技术,2012,36(03):244.
 LI Shansheng,HUANG Zhichang,DU Rui,et al.Study on Computational Methods of Parameter B and QV in WaxmanSmits Model[J].WELL LOGGING TECHNOLOGY,2012,36(02):244.
[5]陈明江,任兴国.含沥青储层的测井识别及评价[J].测井技术,2012,36(03):272.
 CHEN Mingjiang,REN Xingguo.Log Identification and Evaluation for Bitumenbearing Reservoir[J].WELL LOGGING TECHNOLOGY,2012,36(02):272.
[6]程玉梅,张小刚,魏国.介电扫描测井技术在长庆油田的应用[J].测井技术,2012,36(03):277.
 CHENG Yumei,ZHANG Xiaogang,WEI Guo.Application of Dielectric Scanner Logging in Changqing Oilfield[J].WELL LOGGING TECHNOLOGY,2012,36(02):277.
[7]孙建孟,闫国亮.渗透率模型研究进展[J].测井技术,2012,36(04):329.
 SUN Jianmeng,YAN Guoliang.Review on Absolute Permeability Model[J].WELL LOGGING TECHNOLOGY,2012,36(02):329.
[8]宋延杰,么丽娜,徐广田,等.长垣地区低孔隙度低渗透率砂岩储层中连通导电模型的应用[J].测井技术,2012,36(04):345.
 SONG Yanjie,YAO Lina,XU Guangtian,et al.Study on Connectivity Model for Low Porosity and Permeability Sand Reservoirs in Daqing Placanticline[J].WELL LOGGING TECHNOLOGY,2012,36(02):345.
[9]张丽华,潘保芝,刘思慧,等.梨树断陷东南斜坡带砂砾岩岩性识别方法研究[J].测井技术,2012,36(04):370.
 ZHANG Lihua,PAN Baozhi,LIU Sihui,et al.On Lithology Identification Methods of Glutinite in Southeast Ramp Region of Lishu Fault Depression[J].WELL LOGGING TECHNOLOGY,2012,36(02):370.
[10]张盼,冯吉坤,李雪磊,等.火山岩中CO2储层的自动识别[J].测井技术,2012,36(04):373.
 ZHANG Pan,FENG Jikun,LI Xuelei,et al.Automatic Identification of CO2Bearing Beds in the Volcanic Reservoir[J].WELL LOGGING TECHNOLOGY,2012,36(02):373.

备注/Memo

备注/Memo:
(修改回稿日期: 2018-09-17 本文编辑 余迎)基金项目: 国家科技重大专项“渤海湾盆地济阳坳陷致密油开发示范工程”(2017ZX05072002) 第一作者: 陈钢花,女,教授,从事测井资料数字处理与综合解释、测井资料在地质、油藏及钻井工程中的应用、非均质油气藏测井评价等教学科研工作。E-mail:cgh_63@sina.com
更新日期/Last Update: 2019-06-20