[1]曹茂俊,崔欣锋.基于一维卷积神经网络的地层智能识别方法[J].计算机技术与发展,2023,33(09):133-140.[doi:10. 3969 / j. issn. 1673-629X. 2023. 09. 020]
 CAO Mao-jun,CUI Xin-feng.Intelligent Stratigraphic Recognition Method Based on 1DCNN[J].,2023,33(09):133-140.[doi:10. 3969 / j. issn. 1673-629X. 2023. 09. 020]
点击复制

基于一维卷积神经网络的地层智能识别方法()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
33
期数:
2023年09期
页码:
133-140
栏目:
人工智能
出版日期:
2023-09-10

文章信息/Info

Title:
Intelligent Stratigraphic Recognition Method Based on 1DCNN
文章编号:
1673-629X(2023)09-0133-08
作者:
曹茂俊崔欣锋
东北石油大学 计算机与信息技术学院,黑龙江 大庆 163318
Author(s):
CAO Mao-junCUI Xin-feng
School of Computer and Information Technology,Northeast Petroleum University,Daqing 163318,China
关键词:
地层识别一维卷积神经网络测井曲线深度学习特征工程
Keywords:
stratigraphic recognition1DCNNlogging curvesdeep learningfeature engineering
分类号:
TP181
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 09. 020
摘要:
地层识别是油气藏勘探的研究基础。 传统地层识别由地质学家根据自身掌握的知识和经验手工完成,这种地质学家主导的人工解释是主观的、耗时的,可能引入人为偏差。 深度学习在解决复杂非线性问题上具有优势,目前尚无有效解决地层识别的深度学习方法。 针对测井-地层识别,提出了基于特征工程和一维卷积神经网络的地层智
能识别方法。首先,利用 INPEFA 技术和中值滤波对原始曲线进行了多维重构,更好地提取了原始曲线的地层趋势及边缘特征,并对重构矩阵和原始曲线特征采用 K-means 聚类算法提取时空相关聚类特征;然后,以原始曲线特征、INPEFA 曲线、中值滤波特征和聚类特征作为输入,基于一维卷积神经网络得到当前深度地层预测类型。 与长短期记忆网络( LSTM) 和传统的机器学习方法对比发现,在地层的识别上,地层智能识别方法具有更优异的性能和鲁棒性。 该方法能有效识别地层,识别准确率达到 92. 82% ,且在识别地层的同时也完成了地层划分。
Abstract:
Stratigraphic recognition is the basis for the research of oil and gas reservoir exploration. Traditional stratigraphic identificationis done manually by geologists?
based on their own knowledge and experience,and this geologists-led manual interpretation is subjective,time - consuming,and can introduce artificial bias. Deep learning has advantages in solving complex nonlinear problems,and there iscurrently no effective deep learning method to solve formation recognition. For logging - stratigraphic recognition, a stratigraphic intelligent recognition method based on feature engineering and one-dimensional convolutional neural network is proposed. Firstly, the original curve is reconstructed by INPEFA and median filtering,the stratigraphic trend and edge features of the original curve are betterextracted,and the K-means clustering algorithm is used to extract the spatiotemporal correlation clustering features of the reconstructedmatrix and the original curve. Then,taking the original curve features,INPEFA curves,median filtering features and clustering features asinputs,the current deep stratigraphic prediction type is obtained based on the one-dimensional convolutional neural network. Comparedwith the long short - term memory network ( LSTM) and traditional machine learning methods, the formation intelligent recognitionmethod has better performance and robustness in the recognition of strata. The proposed method can effectively identify strata, therecognition accuracy reaches 92. 82% ,and the strata division is completed at the same time as identifying the strata.

相似文献/References:

[1]肖 红,张瑶瑶*,张福禄.改进的卷积神经网络及在地层识别中的应用[J].计算机技术与发展,2021,31(09):167.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 028]
 XIAO Hong,ZHANG Yao-yao*,ZHANG Fu-lu.Improved Convolution Neural Network and Its Application of Stratigraphic Identification[J].,2021,31(09):167.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 028]

更新日期/Last Update: 2023-09-10