APPLICATION OF EXTREME LEARNING MACHINE IN ANALYSIS OF CLAY MINERALS

BAI Ye; CAO Nai-wen; QIU Qing-liang

doi:10.13686/j.cnki.dzyzy.2021.04.014

2021 Vol. 30, No. 4

Article Contents

Article navigation > Geology and Resources > 2021 > 30(4): 505-511

Next Article Previous Article

BAI Ye, CAO Nai-wen, QIU Qing-liang. APPLICATION OF EXTREME LEARNING MACHINE IN ANALYSIS OF CLAY MINERALS[J]. Geology and Resources, 2021, 30(4): 505-511. doi: 10.13686/j.cnki.dzyzy.2021.04.014

Citation:

BAI Ye, CAO Nai-wen, QIU Qing-liang. APPLICATION OF EXTREME LEARNING MACHINE IN ANALYSIS OF CLAY MINERALS[J]. Geology and Resources, 2021, 30(4): 505-511. doi: 10.13686/j.cnki.dzyzy.2021.04.014

APPLICATION OF EXTREME LEARNING MACHINE IN ANALYSIS OF CLAY MINERALS

1.
Geophysical Prospecting and Surveying Team, Jilin Bureau of Coalfield Geology, Changchun 130031, China
2.
No. 203 Exploration Team, Jilin Bureau of Coalfield Geology, Siping 136000, Jilin Province, China
3.
No. 102 Exploration Team, Jilin Bureau of Coalfield Geology, Tonghua 135000, Jilin Province, China

Received Date: 08 June 2020

Revised Date: 24 July 2020

Publish Date: 25 August 2021

Abstract

Abstract

The study on low permeability reservoirs in the 8th member of Lower Shihezi Formation, Upper Paleozoic in northern Sulige of Ordos Basin show that diagenesis is one of the main factors controlling the distribution of gas reservoirs, while clay minerals affect the type and intensity of diagenesis and serve as an important indicator in the classification of diagenesis. This study attempts to use natural gamma-ray spectral logging combined with neural network (extreme learning machine, ELM) to accurately calculate the content of clay minerals in reservoir, providing support for automatic identification of diagenesis in the whole well. In the analysis of clay minerals, to avoid the influence of difference of rock skeleton and particle compositions on logging information, the neural network of clay mineral analysis is established respectively for lithic sandstone and lithic quartz sandstone in the study area to improve calculation accuracy. The neural network adopts the ELM with lower probability of trapping into low efficiency and local optimum to ensure the speed and stability of analysis result. On this basis, 15 X-ray diffraction analysis samples from the 8th member of Lower Shihezi Formation in northern Sulige area are used to compare the calculated results of differential and indifferential lithology, proving the effectiveness of the method.
- clay mineral /
- natural gamma-ray spectral logging /
- lithological analysis /
- extreme learning machine /
- Ordos Basin

FullText(HTML)

References

[1]	白烨, 薛林福, 石玉江, 等. 测井成岩相自动识别及其在鄂尔多斯盆地苏里格地区的应用[J]. 中国石油大学学报(自然科学版), 2013, 37(1): 35-41. doi: 10.3969/j.issn.1673-5005.2013.01.006 CrossRef Google Scholar Bai Y, Xue L F, Shi Y J, et al. An automatic identification method of log diagenetic facies and its application in Sulige area, Ordos Basin[J]. Journal of China University of Petroleum (Edition of Natural Science), 2013, 37(1): 35-41. doi: 10.3969/j.issn.1673-5005.2013.01.006 CrossRef Google Scholar
[2]	张海涛, 时卓, 石玉江, 等. 低渗透致密砂岩储层成岩相类型及测井识别方法——以鄂尔多斯盆地苏里格气田下石盒子组₈段为例[J]. 石油与天然气地质, 2012, 33(2): 256-264. Google Scholar Zhang H T, Shi Z, Shi Y J, et al. Diagenetic facies types and logging identification methods for low-permeability tight sandstone reservoirs: A case study on the 8th member of Xiashihezi Formation in Sulige Gasfield, Ordos Basin[J]. Oil & Gas Geology, 2012, 33(2): 256-264. Google Scholar
[3]	牟传龙, 王秀平, 王启宇, 等. 关于苏里格气田东二区盒₈段储层成岩相的再认识[J]. 沉积学报, 2016, 34(2): 346-355. Google Scholar Mou C L, Wang X P, Wang Q Y, et al. The recognition of diagenetic facies on the case from the reservoir in He8 section of Shihezi Formation, East Ⅱ part of Sulige gas field, Qrdos Basin[J]. Acta Sedimentologica Sinica, 2016, 34(2): 346-355. Google Scholar
[4]	王秀平, 牟传龙, 贡云云, 等. 苏里格气田Z30区块下石盒子组8段储层成岩演化与成岩相[J]. 石油学报, 2013, 34(5): 883-895. Google Scholar Wang X P, Mu C L, Gong Y Y, et al. Diagenetic evolution and facies of reservoirs in Member 8 of Permian Xiashihezi Formation in the Z30 block of Sulige gasfield[J]. Acta Petrolei Sinica, 2013, 34(5): 883-895. Google Scholar
[5]	徐同台, 王行信, 张有瑜, 等. 中国含油气盆地粘土矿物[M]. 北京: 石油工业出版社, 2003: 20-53. Google Scholar Xu T T, Wang X X, Zhang Y Y, et al. Clay minerals of petroliferous basins in China[M]. Beijing: Petroleum Industry Press, 2003: 20-53. (in Chinese) Google Scholar
[6]	刘菁华, 王祝文, 易清平. 利用自然γ能谱测井资料确定粘土矿物的含量及其应用[J]. 吉林大学学报(地球科学版), 2010, 40(1): 215-221. Google Scholar Liu J H, Wang Z W, Yi Q P. Determinating clay mineral content by natural gamma-ray spectral logging data[J]. Journal of Jilin University (Earth Science Edition), 2010, 40(1): 215-221. Google Scholar
[7]	石强. 利用自然伽马能谱测井定量计算粘土矿物成分方法初探[J]. 测井技术, 1998, 22(5): 349-352. Google Scholar Shi Q. Preliminary investigation on quantitative analysis of the composition of clay minerals using NGS log[J]. Well Logging Technology, 1998, 22(5): 349-352. Google Scholar
[8]	郭影文. 自然伽马能谱测井在粘土矿物含量分析中的应用[J]. 石油天然气学报(江汉石油学院学报), 2008, 30(6): 268-270. Google Scholar Guo Y W. Application of natural gamma ray spectroscopy log for analysis of clay mineral content[J]. Journal of Oil and Gas Technology (Journal of Jianghan Petroleum Institute), 2008, 30(6): 268-270. Google Scholar
[9]	谭廷栋. 测井解释粘土矿物[J]. 石油钻采工艺, 1987, 4(6): 25-32. Google Scholar Tan T D. Log interpretation of clay minerals[J]. Oil Drilling & Production Technology, 1987, 4(6): 25-32. (in Chinese) Google Scholar
[10]	孙建孟, 李召成. 应用自然伽马能谱测井确定粘土矿物类型和含量[J]. 石油大学学报(自然科学版), 1999, 23(4): 29-32. doi: 10.3321/j.issn:1000-5870.1999.04.008 CrossRef Google Scholar Sun J M, Li Z C. Determination of clay types and contents by natural gamma-ray spectrum logging[J]. Journal of the University of Petroleum, China, 1999, 23(4): 29-32. doi: 10.3321/j.issn:1000-5870.1999.04.008 CrossRef Google Scholar
[11]	Schlumberger Wireline & Testing. Schlumberger log interpretation charts[M]. Houston: Schlumberger, 1997: 4-30. Google Scholar
[12]	张立明. 人工神经网络的模型及其应用[M]. 上海: 复旦大学出版社, 1993: 32-47. Google Scholar Zhang L M. Models and applications of artificial neural networks[M]. Shanghai: Fudan University Press, 1993: 32-47. Google Scholar
[13]	桂现才. BP神经网络在MATLAB上的实现与应用[J]. 湛江师范学院学报, 2004, 25(3): 79-83. doi: 10.3969/j.issn.1006-4702.2004.03.021 CrossRef Google Scholar Gui X C. Realization of BP networks and their applications on MATLAB[J]. Journal of Zhanjiang Normal College, 2004, 25(3): 79-83. doi: 10.3969/j.issn.1006-4702.2004.03.021 CrossRef Google Scholar
[14]	苏高利, 邓芳萍. 论基于MATLAB语言的BP神经网络的改进算法[J]. 科技通报, 2003, 19(2): 130-135. doi: 10.3969/j.issn.1001-7119.2003.02.012 CrossRef Google Scholar Su G L, Deng F P. On the improving backpropagation algorithms of the neural networks based on MATLAB language: A review[J]. Bulletin of Science and Technology, 2003, 19(2): 130-135. doi: 10.3969/j.issn.1001-7119.2003.02.012 CrossRef Google Scholar
[15]	黄丽. BP神经网络算法改进及应用研究[D]. 重庆: 重庆师范大学, 2008. Google Scholar Huang L. BP neural network algorithm improvement and application research[D]. Chongqing: Chongqing Normal University, 2008. Google Scholar
[16]	王娜娜. 神经网络在测井岩性识别中的应用[D]. 北京: 北京化工大学, 2009. Google Scholar Wang N N. The application of neural network in logging lithology identification[D]. Beijing: Beijing University of Chemical Technology, 2009. Google Scholar
[17]	蔡磊, 程国建, 潘华贤. 极限学习机在岩性识别中的应用[J]. 计算机工程与设计, 2010, 31(9): 2010-2012. Google Scholar Cai L, Cheng J G, Pan H X. Lithologic identification based on ELM[J]. Computer Engineering and Design, 2010, 31(9): 2010-2012. Google Scholar
[18]	Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: A new learning scheme of feedforward neural networks[C]//Proceedings of 2004 IEEE International Joint Conference on Neural Networks. Budapest, Hungary: IEEE, 2004. Google Scholar
[19]	白烨, 薛林福, 潘保芝, 等. 多方法融合判别复杂砂砾岩岩性[J]. 吉林大学学报(地球科学版), 2012, 42(S2): 442-451. Google Scholar Bai Y, Xue L F, Pan B Z, et al. Multi-methods combined identify lithology of glutenite[J]. Journal of Jilin University (Earth Science Edition), 2012, 42(S2): 442-451. Google Scholar
[20]	黄隆基. 放射性测井原理[M]. 北京: 石油工业出版社, 1985: 66-79. Google Scholar Huang L J. Principle of radioactive logging[M]. Beijing: Petroleum Industry Press, 1985: 66-79. (in Chinese) Google Scholar