Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Journal of Electrotechnology, Electrical Engineering and Management
  4. Vol 7, Issue 3, 2024

Hierarchical Multi-granularity Joint Learning for Well-Overflow Detection

Download as PDF

DOI: 10.23977/jeeem.2024.070301 | Downloads: 2 | Views: 43

Author(s)

Jianlong Wang 1, Zhiqiang Yu 1, Yunpeng Guo 2, Bing Deng 3, Yangyang Yang 2, Ming Zhao 2, Ziliang Cui 4, Ye Wang 4

Affiliation(s)

1 Bohai Drilling Engineering Technology Research Institute, CNPC, Tianjin, 300450, China
2 Bohai Drilling Engineering Company Limited, CNPC, Tianjin, 300450, China
3 Bohai NO.1 Drilling Engineering Company, CNPC, Tianjin, 300280, China
4 Chongqing University of Posts and Telecommunications, Chongqing, 400065, China

Corresponding Author

Jianlong Wang

ABSTRACT

Detecting well-overflow accurately is important in petroleum engineering, which helps reduce accident risks and ensure production safety. However, it still remains challenging due to limited datasets and varying well conditions. In this paper, we propose a hierarchical multi-granularity joint learning model for well-overflow detection. Specifically, we utilize different sampling frequencies to extract temporal and tabular features from each individual well. Then, a hierarchical multi-granularity feature fusion method is designed to merge the extracted features effectively, incorporating self-attention mechanisms for feature selection. Finally, ensemble learning is proposed to finalize the Detection of well-overflow. Extensive experiments demonstrate the effectiveness of our proposed model.

KEYWORDS

Well-overflow detection, Multi-granularity learning, Hierarchical representation

CITE THIS PAPER

Jianlong Wang, Zhiqiang Yu, Yunpeng Guo, Bing Deng, Yangyang Yang, Ming Zhao, Ziliang Cui, Ye Wang, Hierarchical Multi-granularity Joint Learning for Well-Overflow Detection. Journal of Electrotechnology, Electrical Engineering and Management (2024) Vol. 7: 1-10. DOI: http://dx.doi.org/10.23977/jeeem.2024.070301.

REFERENCES

[1] J. Speers, G. Gehrig, Delta flow: An accurate, reliable system for detecting kicks and loss of circulation during drilling, SPE Drilling Engineering 2 (04) (1987) 359–363.
[2] W. Liu, J. Fu, Y. Liang, M. Cao, X. Han, A well-overflow prediction algorithm based on semi-supervised learning, Energies 15 (12) (2022) 4324.
[3] W. Yi, W. Liu, J. Fu, L. He, X. Han, An improved transformer framework for well-overflow early detection via self-supervised learning, Energies 15 (23) (2022) 8799.
[4] H. Liang, H. Han, P. Ni, Y. Jiang, Overflow warning and remote monitoring technology based on improved random forest, Neural Computing and Applications 33 (2021) 4027–4040.
[5] J. Mckay, C. Simmons, T. Hogg, G. Starling, M. Doty, A. Pere, Blowout preventer (bop) health monitoring, in: SPE/IADC Drilling Conference and Exhibition, SPE, 2012, pp. SPE–151182.
[6] J. Orban, K. Zanker, Accurate flow-out measurements for kick detection, actual response to controlled gas influxes, in: SPE/IADC Drilling Conference and Exhibition, SPE, 1988, pp. SPE–17229.
[7] J. Brakel, B. Tarr, W. Cox, F. Jørgensen, H. V. Straume, Smart kick detection: First step on the well-control automation journey, SPE Drilling & Completion 30 (03) (2015) 233–242.
[8] I. Mills, D. Reitsma, J. Hardt, Z. Tarique, Simulator and the first field test results of an automated early kick detection system that uses standpipe pressure and annular discharge pressure, in: SPE/IADC Managed Pressure Drilling and Underbalanced Operations Conference and Exhibition?, SPE, 2012, pp. SPE–156902.
[9] A. A. Nayeem, R. Venkatesan, F. Khan, Monitoring of down-hole parameters for early kick detection, Journal of Loss Prevention in the Process Industries 40 (2016) 43–54.
[10] R. Islam, F. Khan, R. Venkatesan, Real time risk analysis of kick detection: testing and validation, Reliability Engineering & System Safety 161 (2017) 25–37.
[11] I. O. Sule, F. Khan, S. Butt, Experimental investigation of gas kick effects on dynamic drilling parameters, Journal of Petroleum Exploration and Production Technology 9 (2019) 605–616.
[12] X. Song, S. Duan, Z. Pei, Z. Zhu, Research on kick detection model based on machine learning, in: International Con- ference on Offshore Mechanics and Arctic Engineering, Vol. 85208, American Society of Mechanical Engineers, 2021, p. V010T11A005.
[13] X. L. Wang, X. Y. Lian, L. Yao, Fault diagnosis of drilling process based on rough set and support vector machine, Advanced materials research 709 (2013) 266–272.
[14] R. Alouhali, M. Aljubran, S. Gharbi, A. Al-yami, Drilling through data: automated kick detection using data mining, in: SPE International Heavy Oil Conference and Exhibition, SPE, 2018, p. D012S018R001.
[15] X. Shi, Y. Zhou, Q. Zhao, H. Jiang, L. Zhao, Y. Liu, G. Yang, A new method to detect influx and loss during drilling based on machine learning, in: International Petroleum Technology Conference, IPTC, 2019, p. D021S018R003.
[16] Q. Yin, J. Yang, M. Tyagi, X. Zhou, X. Hou, B. Cao, Field data analysis and risk assessment of gas kick during industrial deepwater drilling process based on supervised learning algorithm, Process Safety and Environmental Protection 146 (2021) 312–328.
[17] Z. Cai, S. Lei, X. Lu, Deep learning based granularity detection network for mine dump materials, Minerals 12 (4) (2022) 424.
[18] T. Guo, F. Luo, Y. Duan, X. Huang, G. Shi, Rethinking representation learning-based hyperspectral target detection: A hierarchical representation residual feature-based method, Remote Sensing 15 (14) (2023) 3608.
[19] H. Liang, H. Han, P. Ni, Y. Jiang, Overflow warning and remote monitoring technology based on improved random forest, Neural Computing and Applications 33 (2021) 4027–4040.
[20] Y.-H. Chang, C.-W. Tseng, H.-C. Hsu, Predicting the overflowing of urban personholes based on machine learning techniques, Water 15 (23) (2023) 4100.
[21] C.-C. Chia, Z. Syed, Scalable noise mining in long-term electrocardiographic time-series to predict death following heart attacks, in: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, 2014, pp. 125–134.
[22] S. Yan, B. Tang, J. Luo, X. Fu, X. Zhang, Unsupervised anomaly detection with variational auto-encoder and local outliers factor for kpis, in: 2021 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Comput- ing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom), IEEE, 2021, pp. 476–483.
[23] J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 7132–7141.
[24] J. Cervantes, F. Garcia-Lamont, L. Rodr´ıguez-Mazahua, A. Lopez, A comprehensive survey on support vector machine classification: Applications, challenges and trends, Neurocomputing 408 (2020) 189–215.
[25] H. Xie, A. K. Shanmugam, R. R. Issa, Big data analysis for monitoring of kick formation in complex underwater drilling projects, Journal of Computing in Civil Engineering 32 (5) (2018) 04018030.
[26] Z. Wang, G. Chen, R. Zhang, W. Zhou, Y. Hu, X. Zhao, P. Wang, Early monitoring of gas kick in deepwater drilling based on ensemble learning method: A case study at south china sea, Process Safety and Environmental Protection 169 (2023) 504–514.
[27] A. Youssef, M. Abdelrazek, C. Karmakar, Use of ensemble learning to detect buffer overflow exploitation, IEEE Access.
[28] W. Yi, W. Liu, J. Fu, L. He, X. Han, An improved transformer framework for well-overflow early detection via self-supervised learning, Energies 15 (23) (2022) 8799.
[29] Q. Yin, J. Yang, M. Tyagi, X. Zhou, N. Wang, G. Tong, R. Xie, H. Liu, B. Cao, Downhole quantitative evaluation of gas kick during deepwater drilling with deep learning using pilot-scale rig data, Journal of Petroleum Science and Engineering 208 (2022) 109136.
[30] A. K. Fjetland, J. Zhou, D. Abeyrathna, J. E. Gravdal, Kick detection and influx size estimation during offshore drilling operations using deep learning, in: 2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA), IEEE, 2019, pp. 2321–2326.
[31] M. Fraccaro, S. K. Sønderby, U. Paquet, O. Winther, Sequential neural models with stochastic layers, Advances in neural information processing systems 29.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 2901
Visits: 123842

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.