A novel machine learning model for autonomous analysis and diagnosis of well integrity failures in artificial-lift production systems
Abstract view|0|times PDF download|0|times Supplements download|0|times
Abstract
The integrity failure in gas lift wells had been proven to be more severe than other artificial lift wells across the industry. Accurate risk assessment is an essential requirement for predicting well integrity failures. In this study, a machine learning model was established for automated and precise prediction of integrity failures in gas lift wells. The collected data contained 9,000 data arrays with 23 features. Data arrays were structured and fed into 11 different machine learning algorithms to build an automated systematic tool for calculating the imposed risk of any well. The study models included both single and ensemble supervised learning algorithms (e.g., random forest, support vector machine, decision tree, and scalable boosting techniques). Comparative analysis of the deployed models was performed to determine the best predictive model. Further, novel evaluation metrics for the confusion matrix of each model were introduced. The results showed that extreme gradient boosting and categorical boosting outperformed all the applied algorithms. They can predict well integrity failures with an accuracy of 100% using traditional or proposed metrics. Physical equations were also developed on the basis of feature importance extracted from the random forest algorithm. The developed model will help optimize company resources and dedicate personnel efforts to high-risk wells. As a result, progressive improvements in health, safety, and environment and business performance can be achieved.
Cited as: Salem, A. M., Yakoot, M. S., Mahmoud, O. A novel machine learning model for autonomous analysis and diagnosis of well integrity failures in artificial-lift production systems. Advances in Geo-Energy Research, 2022, 6(2): 123-142. https://doi.org/10.46690/ager.2022.02.05
Keywords
References
Abimbola, M., Khan, F., Khakzad, N. Risk-based safety analysis of well integrity operations. Safety Science, 2016, 84: 149-160.
Adeyinka, A., Tsakporhore, A., Arije, O., et al. Rethinking well integrity for sustainability: Adopting a risk-based approach. Paper SPE 203672 Presented at the SPE Nigeria Annual International Conference and Exhibition, Virtual, 11-13 August, 2020.
Anders, J. L., Rossberg, R. S., Dube, A. T., et al. Well integrity operations at Prudhoe Bay, Alaska. SPE Production & Operations, 2008, 23(2): 280-286.
AOGCC. Investigation of Explosion and Fire at Prudhoe Bay Well A-22 North Slope, Alaska. Alaska, USA, Alaska Oil & Gas Conservation Commission Staff Report, 2003.
Bates, R., Cosad, C., Fielder, L., et al. Taking the pulse of producing wells-ESP surveillance. Oilfield Review, 2004, 16(2): 16-25.
Bontempi, G. Statistical foundations of machine learning. Brussels, Universite Libre de Bruxelles, 2021.
Bravo, C., Rodriguez, J., Saputelli, L., et al. Applying analytics to production workflows: Transforming integrated operations into intelligent operations. Paper SPE 167823 Presented at the SPE Intelligent Energy Conference and Exhibition, Utrecht, Netherlands, 1-3 April, 2014a.
Bravo, C., Saputelli, L., Rivas, F., et al. State of the art of artificial intelligence and predictive analytics in the E&P industry: A technology survey. SPE Journal, 2014b, 19(4): 547-563.
Brechan, B., Dale, S. I., Sangesland, S. Well integrity risk assessment-software model for the future. Paper OTC 28481 Presented at the Offshore Technology Conference Asia, Kuala Lumpur, Malaysia, 20-23 March, 2018.
Brodie, A. Gas-lift valve design addresses long-term well integrity needs. Offshore, 2011, 71(2): 98-99.
Choubey, S., Karmakar, G. P. Artificial intelligence techniques and their application in oil and gas industry. Artificial Intelligence Review, 2021, 54(5): 3665-3683.
Cox, L. A. J. What’s wrong with risk matrices? Risk Analysis, 2008, 28(2): 497-512.
De Carvalho, A. C. P., Freitas, A. A. A tutorial on multilabel classification techniques, in Foundations of Computational Intelligence, edited by A. Abraham., A. E. Hassanien, and V. Snášel, Berlin Heidelberg, Germany, pp. 177-195, 2009.
Dethlefs, J., Chastain, B. Assessing well-integrity risk: A qualitative model. SPE Drilling & Completion, 2021, 27(2): 294-302.
Elgibaly, A. A., Ghareeb, M., Kamel, S., et al. Prediction of gas-lift performance using neural network analysis. AIMS Energy, 2021, 9(2): 355-378.
Elmousalami, H. H., Elaskary, M. Drilling stuck pipe classification and mitigation in the Gulf of Suez oil fields using artificial intelligence. Journal of Petroleum Exploration and Production Technology, 2020, 10(5): 2055-2068.
Fernández, A., García, S., Galar, M., et al. Introduction to KDD and Data science, in Learning From Imbalanced Data Sets, edited by A. Fernández, S. García, M. Galar, et al., Springer, Berlin, pp. 1-16, 2018.
Gupta, S., Saputelli, L., Nikolaou, M. Applying big data analytics to detect, diagnose, and prevent impending failures in electric submersible pumps. Paper SPE 181510 Presented at the SPE Annual Technical Conference and Exhibition, Dubai, UAE, 26-28 September, 2016.
Hastie, T., Tibshirani, R., Friedman, J. Model assessment and selection, in The Elements of Statistical Learning: Data Mining, Inference, and Prediction, edited by T. Hastie, R. Tibshirani and J. Friedman, Springer, New York, pp. 219-259, 2017.
Holdaway, K. R. Fundamentals of soft computing, in Harness Oil and Gas Big Data with Analytics: Optimize Exploration and Production with Data-Driven Models, edited by K. R. Holdaway, Wiley and SAS Business Series, North Carolina, pp. 1-31, 2014.
Ismail, W. R., Trjangganung, K. Mature field gas lift optimisation: Challenges & strategies, case study of Dfield, Malaysia. Paper IPTC 17896 Presented at the International Petroleum Technology Conference, Kuala Lumpur, Malaysia, 10-12 December, 2014.
Kazak, A., Simono, K., Kulikov, V. Machine-learning-assisted segmentation of focused ion beam-scanning electron microscopy images with artifacts for improved void-space characterization of tight reservoir rocks. SPE Journal, 2021, 26(4): 1739-1758.
Khan, M. R., Tariq, Z., Abdulraheem, A. Application of artificial intelligence to estimate oil flow rate in gas-lift wells. Natural Resources Research, 2020, 29(1): 4017-4029.
Kiran, R., Teodoriu, C., Dadmohammadi, Y., et al. Identification and evaluation of well integrity and causes of failure of well integrity barriers (A review). Journal of Natural Gas Science and Engineering, 2017, 45: 511-526.
Li, B., Billiter, T. C., Tokar, T. Rescaling method for improved machine-learning decline curve analysis for unconventional reservoirs. SPE Journal, 2021, 26(4): 1759-1772.
Loizzo, M., Bois, A., Etcheverry, P., et al. An evidencebased approach to well-integrity risk management. SPE Economics & Management, 2015, 7(3): 100-111.
Mahdiani, M. R., Khamehchi, E., Hajirezaie, S., et al. Modeling viscosity of crude oil using k-nearest neighbor algorithm. Advances in Geo-Energy Research, 2020, 4(4): 435-447.
Miraglia, S. A data-driven probabilistic model for well integrity management: Case study and model calibration for the Danish sector of North Sea. Journal of Structural Integrity and Maintenance, 2020, 5(2): 142-153.
Mishra, S., Datta-Gupta, A. Applied Statistical Modeling and Data Analytics: A Practical Guide for the Petroleum Geosciences. Amsterdam, Netherlands, Elsevier, 2017.
Mohammed, R., Rawashdeh, J., Abdullah, M. Machine learning with oversampling and undersampling techniques: Overview study and experimental results. Paper ICICS Presented at the 11th International Conference on Information and Communication Systems, Irbid, Jordan, 7-9 April, 2020.
Olukoga, T. A., Feng, Y. Practical machine-learning applications in well-drilling operations. SPE Drilling & Completion, 2021, 36(4): 849-867.
Ragab, A. M. S., Yakoot, M. S., Mahmoud, O. Application of machine learning algorithms for managing well integrity in gas lift wells. Paper SPE 205736 Presented at the SPE/IATMI Asia Pacific Oil & Gas Conference and Exhibition, Virtual, 12-14 October, 2021.
Rahmanifard, H., Plaksina, T. Application of artificial intelligence techniques in the petroleum industry: A review. Artificial Intelligence Review, 2019, 52(4): 2295-2318.
Rahmawati, S. D., Chandra, S., Aziz, P. A., et al. Integrated application of flow pattern map for long-term gas lift optimization: A case study of Well T in Indonesia. Journal of Petroleum Exploration and Production Technology, 2020, 10(4): 1635-1641.
Raschka, S. Building good training sets-data preprocessing, in Python Machine Learning: Unlock Deeper Insights into Machine Learning with This Vital Guide to Cutting-Edge Predictive Analytics, edited by S. Raschka, Safari Books Online, Packt Publishing, Birmingham, United Kingdom, pp. 99-127, 2015.
Salem, A. M., Yakoot, M. S., Mahmoud, O. Addressing diverse petroleum industry problems using machine learning techniques: Literary methodology-spotlight on predicting well integrity failures. ACS Omega, 2022, 7: 2504-2519.
Saputelli, L. Technology focus: Petroleum data analytics. Journal of Petroleum Technology, 2016, 68(10): 66-66.
Shalaby, M. R., Malik, O. A., Lai, D., et al. Thermal maturity and TOC prediction using machine learning techniques: Case study from the Cretaceous-Paleocene source rock, Taranaki Basin, New Zealand. Journal of Petroleum Exploration and Production Technology, 2020, 10(6): 2175-2193.
Silla, C. N., Freitas, A. A. A survey of hierarchical classification across different application domains. Data Mining and Knowledge Discovery, 2011, 22(1): 31-72.
Sokolova, M., Lapalme, G. A systematic analysis of performance measures for classification tasks. Information Processing & Management, 2009, 45(4): 427-437.
Tang, J., Fan, B., Xiao, L., et al. A new ensemble machinelearning framework for searching sweet spots in shale reservoirs. SPE Journal, 2021, 26(1): 482-497.
Vidiyala, R. How to select the right machine learning algorithm. Towards Data Science, 2020.
Wood, D. A. A transparent Open-Box learning network provides insight to complex systems and a performance benchmark for more-opaque machine learning algorithms. Advances in Geo-Energy Research, 2018, 2(2): 148-162.
Wood, D. A. Gamma-ray log derivative and volatility attributes assist facies characterization in clastic sedimentary sequences for formulaic and machine learning analysis. Advances in Geo-Energy Research, 2022, 6(1): 69-85.
Yakoot, M. S., Elgibaly, A. A., Ragab, A. M. S., et al. A comprehensive review and analysis of maturity model for well integrity in brownfield. Paper Presented at the IADC Drilling Middle East Conference & Exhibition, Virtual, 14-15 December, 2020.
Yakoot, M. S., Elgibaly, A. A., Ragab, A. M. S., et al. Well integrity management in mature fields: A state-of-theart review on the system structure and maturity. Journal of Petroleum Exploration and Production Technology, 2021a, 11(4): 1833-1853.
Yakoot, M. S., Ragab, A. M. S., Mahmoud, O. Machine learning application for gas lift performance and well integrity. Paper SPE 205134 Presented at the SPE Europec Featured at 82nd EAGE Conference and Exhibition, Amsterdam, The Netherlands, 18-21 October, 2021b.
Yakoot, M. S., Ragab, A. M. S., Mahmoud, O. Multi-class taxonomy of well integrity anomalies applying inductive learning algorithms: Analytical approach for artificiallift wells. Paper SPE 206129 Presented at the SPE Annual Technical Conference and Exhibition, Dubai, United Arab Emirates, 21-23 September, 2021c.
Yakoot, M. S., Ragab, A. M. S., Mahmoud, O. Developing analytical model for calculating the wellbore-integrity comprehensive risk in artificial-lift system. Paper OMAE 2022-80222 to be Presented at the ASME 41st International Conference on Ocean, Offshore and Arctic Engineering, Hamburg, Germany, 6-9 June, 2022.
Yavari, H., Khosravanian, R., Wood, D. A., et al. Application of mathematical and machine learning models to predict differential pressure of autonomous downhole inflow control devices. Advances in Geo-Energy Research, 2021, 5(4): 386-406.
Yin, Q., Yang, J., Tyagi, M., et al. Machine learning for deepwater drilling: Gas-kick-alarm Classification using pilot-scale rig data with combined surface-riser-downhole monitoring. SPE Journal, 2021, 26(4): 1773-1799.
Zhao, L., Yan, Y., Wang, P., et al. A risk analysis model for underground gas storage well integrity failure. Journal of Loss Prevention in the Process Industries, 2019, 62: 103951.
DOI: https://doi.org/10.46690/ager.2022.02.05
Refbacks
- There are currently no refbacks.
Copyright (c) 2022 The Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.