Lithology Recognition Method of Core Image Based on Deep Learning
DOI:
https://doi.org/10.26821/IJSHRE.9.7.2021.9710Keywords:
CNN, convolution neural network, core recognition, machine learningAbstract
Lithologic identification of strata is the basic object
of petroleum geology research, which can
accurately and directly reflect the distribution of
oil and gas reserves in the strata and point out the
direction for deep petroleum exploration and
development. But the early lithologic identification
is to use the method of artificial visual observation
and manual identification to study the core, which
can not guarantee the accuracy and speed of core
identification. Based on the achievements of
machine learning in the field of image processing
and analysis, this paper starts with machine
learning, and uses the advantages of machine
learning, which can automatically extract features
without the influence of external factors to extract
the features needed for rock debris recognition,
and constructs a three-layer convolution neural
network, Finally, a high-precision model for
classification and recognition of rock cuttings is
trained.
References
Yue Yongdong, Qu Hongjie, Tan Chunliang,
Zhu Qiang, Lin Guangli. Application of logging
lithology identification based on support vector
machine in loose sediment investigation [J].
Drilling engineering, 2021,48 (04): 29-36.
Samira Shayeganpour,Majid H.
Tangestani,Saeid Homayouni,Robert K. Vincent.
Evaluating pixel-based vs. object-based image
analysis approaches for lithological discrimination
using VNIR data of WorldView-3[J]. Frontiers of
Earth Science,2021.
Hu Po, Li Feng, Cheng Guangjin, Wang
Liang, Tong Shouqiang. Application of artificial
neural network lithology identification in
geological modeling [j]. Petrochemical application,
,39 (11): 94-96+104.
Wu Zhongyuan, Zhang Xin, Zhang Chunlei,
Wang Haiying. Lithologic identification method
based on LSTM recurrent neural network [J / OL].
Lithologic reservoir: 1-10 [2021-05-07]
http://kns.cnki.net/kcms/detail/62.1195.te.2020110
1333.007.html.
Zheng zunkai. Research on Debris Image
Recognition Based on deep learning model [D].
Changjiang University, 2019.
Zou Wenbo. Research status of artificial
intelligence and its application in logging field [J].
Logging technology, 2020,44 (04): 323-328.
Li Yan. Rock image recognition based on deep
learning [D]. Beijing Forestry University, 2020.
Gang Chen,Chen Gang,Chen Long,Li
Quanxin. Comparison and Application of Neural
Networks in LWD Lithology Identification[J]. IOP
Conference Series: Earth and Environmental
Science,2020,526(1).
Lin Xiangliang. Application of principal
component analysis and support vector machine in
Glutenite lithology identification [D]. Changjiang
University, 2020.
Gao Ting, Yang Yang, he Jiang. Application
of artificial intelligence in rock image [J]. China
Petroleum and chemical industry standards and
quality, 2020,40 (20): 98-100.
