| 卷积神经网络在岩性识别中的应用 |
| |
| 引用本文： | 陈钢花,梁莎莎,王军,隋淑玲.卷积神经网络在岩性识别中的应用[J].测井技术,2019,43(2):129-134. |
| |
| 作者姓名： | 陈钢花 梁莎莎 王军 隋淑玲 |
| |
| 作者单位： | 中国石油大学(华东)地球科学与技术学院,山东 青岛,266580;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 |
| |
| 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。
|
| 关 键 词： | 测井解释 深度学习 卷积神经网络 岩性识别 |
Application of Convolutional Neural Network in Lithology Identification |
| |
| CHEN Ganghua,LIANG Shasha,WANG Jun,SUI Shuling.Application of Convolutional Neural Network in Lithology Identification[J].Well Logging Technology,2019,43(2):129-134. |
| |
| Authors: | CHEN Ganghua LIANG Shasha WANG Jun SUI Shuling |
| |
| Affiliation: | (School of Geosciences, China University of Petroleum, Qingdao, Shandong 266580, China;Research Institute of Exploration and Development, Shengli Oilfield Company, SINOPEC, Dongying, Shandong 257000, China) |
| |
| 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. |
| |
| Keywords: | logg interpretation deep learning convolutional neural network lithology identification |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
