全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

Efficient Identification Method of Interbeds Based on Neural Network Combined with Grey Relational Analysis
—Taking the Lower Sub-Member of the Sangonghe Formation in Moxizhuang Oilfield as an Example

DOI: 10.4236/gep.2025.132005, PP. 51-68

Keywords: Interlayer Recognition, Grey Relational Analysis, Fully Connected Neural Network, Second Member of Sangonghe Formation

Full-Text   Cite this paper   Add to My Lib

Abstract:

The storage layer within the Moxizhuang Oilfield in the Junggar Basin develops various types of interlayer barriers with significant differences in morphology and scale of development. In response to the issues of interlayer barriers affecting the formation of oil and gas reservoirs and controlling oil-water distribution, this study proposes precise classification and quantitative identification of interlayer barriers in the study area based on a fully connected neural network combined with grey relational analysis. Taking the second member of the Sangonghe Formation (J1S22) in the Moxizhuang Oilfield as an example, combined with previous research, this study statistically analyzes the lithology and logging response characteristics of three types of interlayer barriers in the study area. Based on differences in composition, lithology, and genesis, interlayer barrier types are classified. Sensitive logging data such as natural gamma, acoustic time difference, and resistivity are selected through crossover plots. Grey relational analysis is used to calculate comprehensive discrimination indicators for interlayer barriers. Combined with the fully connected neural network method, an interlayer barrier identification model is established, and model training is conducted to verify the accuracy of interlayer barrier identification. The results indicate that the interlayer barrier identification model based on a fully connected neural network can rapidly and accurately identify interlayer barriers and their types. Its application in the second member of the Sangonghe Formation in the Moxizhuang Oilfield in the Junggar Basin has proven that the identification results of this method for interlayer barriers have a conformity rate exceeding 90% with core data, demonstrating excellent performance in interlayer barrier identification and proving the effectiveness of the model for interlayer barrier identification and prediction in this area. The research conclusions can provide theoretical guidance and technical reference for the identification and evaluation of interlayer barriers in the second member of the Sangonghe Formation in the Moxizhuang Oilfield in the Junggar Basin.

References

[1]  Bai, W., Cheng, S., Guo, X., Wang, Y., Guo, Q., & Tan, C. (2024). Oilfield Analogy and Productivity Prediction Based on Machine Learning: Field Cases in PL Oilfield, China. Petroleum Science, 21, 2554-2570.
https://doi.org/10.1016/j.petsci.2024.02.018
[2]  Bi, Y., Gao, S., & Zhu, Y. (2011). Hydrocarbon Accumulation Patterns of Moxizhuang Oilfield, the Junggar Basin. Oil & Gas Geology, 32, 318-326.
[3]  Chen, W., He, J., & Yang, B. (2011). Study on Logging Identification of Interbeds and Barriers in DH Oilfield. Computing Techniques for Geochemical and Calculation Techniques, 33, 202-205.
[4]  Chen, X., Xu, S., & Li, S. (2021). Identification of Interlayers in Braided River Reservoir Based on Support Vector Machine and Principal Component Analysis. Journal of China University of Petroleum (Edition of Natural Science), 45, 22-31.
[5]  Cheng, K. (2023). Characteristics and Genesis of Low Oil Saturation Reservoirs in the Moxizhuang Oilfield of the Junggar Basin. Xi’an Shiyou University.
[6]  Deng, X. (2016). Characteristics of Heterogeneous Interbeds in the J_1s_2 Reservoir of Block 1 in the Central Junggar Basin. Science Technology and Engineering, 16, 27-31.
[7]  Deng, Y., Guo, R., Tian, Z., Tan, W., Yi, Y., Xu, Z. et al. (2016). Geologic Features and Genesis of the Barriers and Intercalations in Carbonates: A Case Study of the Cretaceous Mishrif Formation, West Qurna Oil Field, Iraq. Petroleum Exploration and Development, 43, 136-144.
https://doi.org/10.1016/s1876-3804(16)30018-0
[8]  He, T., Zhou, N., & Wu, X. (2023). Prediction of Effective Sandstone Thickness in Reservoirs Based on Deep Fully Connected Neural Networks. Journal of Jilin University (Earth Science Edition), 53, 1262-1274.
[9]  Hochreiter, S., Younger, A. S., & Conwell, P. R. (2001). Learning to Learn Using Gradient Descent. In G. Dorffner, H. Bischof, & K. Hornik (Eds.), Lecture Notes in Computer Science (pp. 87-94). Springer.
https://doi.org/10.1007/3-540-44668-0_13
[10]  Huang, Y., Li, X., Liu, X., Zhai, Y., Fang, F., Guo, W. et al. (2023). Review of the Productivity Evaluation Methods for Shale Gas Wells. Journal of Petroleum Exploration and Production Technology, 14, 25-39.
https://doi.org/10.1007/s13202-023-01698-z
[11]  Jiang, P., Huang, J., Lei, X., Cheng, C., & Zhang, Y. (2014). Study on Interlayer Distribution of I Oil Group in Member 2 of Zhujiang Formation in a Oilfield. Journal of Southwest Petroleum University, 36, 19-26.
[12]  Jiao, S., Zhao, J., He, Y., Zhao, S., Wu, Z., Zeng, T. et al. (2023). Semi-Supervised Interlayer Intelligent Recognition Method. Earth Science Informatics, 16, 2187-2197.
https://doi.org/10.1007/s12145-023-01021-8
[13]  Jin, Y., Guo, K., Gao, X., & Li, Q. (2024). Tight Oil Well Productivity Prediction Model Based on Neural Network. Processes, 12, Article No. 2088.
https://doi.org/10.3390/pr12102088
[14]  Karande, A. M., & Kalbande, D. R. (2018). Weight Assignment Algorithms for Designing Fully Connected Neural Network. International Journal of Intelligent Systems and Applications, 10, 68-76.
https://doi.org/10.5815/ijisa.2018.06.08
[15]  Lee, P. T., Lin, C., & Shin, S. (2012). A Comparative Study on Financial Positions of Shipping Companies in Taiwan and Korea Using Entropy and Grey Relation Analysis. Expert Systems with Applications, 39, 5649-5657.
https://doi.org/10.1016/j.eswa.2011.11.052
[16]  LI, F.-F., Guo, R., & Liu, L.-F. (2020). Identification of Interlayer in Thick Carbonate Reservoir under the Control of Genesis. Science Technology and Engineering, 20, 3650-3657.
[17]  Meng, L. (2020). Lower Limits of Physical Properties of Sandstone Reservoirs in the Second Member of Sangonghe Formation in Moxizhuang Oilfield. Xinjiang Petroleum Geology, 40, 557-564.
[18]  Qu, Z., Luo, X., & Xie, R. (2009). Application of Wavelet Neural Network in the Study of Interlayer. Journal of Oil and Gas Technology, 31, 265-268.
[19]  Si, Y., Cai, M. J., & Zhang, J.L. (2023). Quantitative Identification Method of Reservoir Flow Barriers Based on Self-Organizing Neural Network and K-Nearest Neighbor Algorithm. Journal of China University of Petroleum (Edition of Natural Science), 47, 35-47.
[20]  Wang, Y., Lin, C., & Wen, C. (2006). Analysis of the Control Effect of Interlayers on Oil Reservoirs: A Case Study of the Sangonghe Formation in the Moxizhuang Area of Block 1 in the Central Junggar Basin. Petroleum Geology and Recovery Efficiency, 13, 17-20.
[21]  Xie, X., Deng, H., & Wang, J. (2004). Integration of Seismic Processing and Interpretation for Fine Reservoir Characterization: Taking Moxizhuang Area in Junggar Basin as an Example. Oil & Gas Geology, 25, 533-538.
[22]  Yang, F., Liao, M., & Wang, Q. (2014). The Use of Logging Data in Identifying the Interlayer in Tazhong Oilfield 4. Chinese Journal of Engineering Geophysics, 11, 487-492.
[23]  Yi, S., Wang, L., & Ni, J. E. (2021). Characteristics and Geological Significance of Mixed Reservoir Interbeds in the Asmari Formation of the M Oilfield in Iraq. Journal of Xi’an University of Science and Technology, 41, 1014-1024.
[24]  Yin, S., Wu, S., & Feng, W. (2013). Patterns of Inter-Layers in the Alluvial Fan Reservoirs: A Case Study on Triassic Lower Karamay Formation, Yizhong Area, Karamay Oilfield, NW China. Petroleum Exploration and Development, 40, 757-763.
[25]  Zhang, J., Liu, C., & Zhu, G. (2014). Characteristics and Genesis of Low-Permeability Reservoirs in the Moxizhuang Oilfield. Special Oil and Gas Reservoirs, 21, 58-61.
[26]  Zhong, Z., Ni, B., & Shi, Y. (2024). Response Analysis of Subway Stations and Optimization of Seismic Intensity Indices Based on Fully Connected Neural Networks. Chinese Journal of Geotechnical Engineering, 46, 567-577.
[27]  Zhou, X., Ding, W., & Chang, L. (2017). Three End-Member Diagram of Classification to Identify the Interlayers of Sandstone Reservoir in Littoral Facies: A Case from Carboniferous Donghe Sandstone in Hade Oil Field, Tarim Basin, NW China. Earth Science Frontiers, 24, 328-338.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133