Improving Two-Phase Flow Pattern Classification Accuracy in Horizontal Pipes Using Ensemble Techniques
DOI:
https://doi.org/10.2118/227650-MSKeywords:
fluid dynamics, artificial intelligence, reservoir surveillance, multiphase flow, production monitoring, flow pattern, machine learning, production control, production logging, accuracyAbstract
This study explored the application of ensemble machine-learning models to predict two-phase flow patterns in horizontal pipes. Ensemble techniques including boosting, bagging, and random forests (RF) were emplyed. A novel decision-tree classifier was developed by combining Random Trees (RT), J48, Reduced-Error Pruning Decision Trees (REPT), Logistic Model Trees (LMT), and Naive Bayes (NBT) algorithms, specifically designed to predict flow regimes. The ensemble models were built using approximately 2380 experimental data points. Feature selection involved the application of six optimization methods, with training and cross-validation used for optimal selection. Performance evaluation utilized metrics like classification accuracy, precision, recall, confusion matrix, a measure of predictive performance, F-Measure, and Precision-Recall Curve (PRC) area. The study's results indicate that boosting and RF classifiers demonstrate superior prediction accuracy compared to other ensemble algorithms. Particularly, the RF model exhibited exceptional performance across various evaluation metrics, emphasizing the efficacy of ensemble algorithms over single classifiers for tree-based models in predicting flow regimes with an impressive accuracy rate of 91%. The findings underscore the consistent outperformance of ensemble models, which integrate multiple classifiers, over individual classifiers regarding prediction accuracy. This underscores the benefits of leveraging diverse models to enhance accuracy and robustness in flow pattern classification. The analysis also highlights the significant influence of volumetric liquid velocity and gas velocity as key features in determining the models’ performance. This research presents a robust and refined ensemble approach, offering a cost-effective and highly accurate method for predicting two-phase flow regimes in horizontal conduits under various operating conditions.
References
Al-Dogail, A. S., & Gajbhiye, R. N. (2021). Effects of density, viscosity and surface tension on flow regimes and pressure drop of two-phase flow in horizontal pipes. Journal of Petroleum Science and Engineering, 205, Article 108719. https://doi.org/10.1016/j.petrol.2021.108719
Al-Dogail, A. S., Gajbhiye, R. N., Al-Naser, M. A., Aldoulah, A. A., Alshammari, H. Y., & Alnajim, A. A. (2023). Machine learning approach to predict pressure drop of multi-phase flow in horizontal pipe and influence of fluid properties. In SPE Gas & Oil Technology Showcase and Conference (p. D011S011R002). Society of Petroleum Engineers.
Alhashem, M. (2020). IPTC-20058-Abstract machine learning classification model for multiphase flow regimes in horizontal pipes. International Petroleum Technology Conference.
Al-Sharifi, H. A., Alkhudafi, A. M., Al-Gathe, A. A., Baarimah, S. O., Al-Ameri, W., & Alyazidi, A. T. (2024). Prediction of two-phase flow regimes in vertical pipes using tree-based ensemble models. In International Petroleum Technology Conference. https://doi.org/10.2523/iptc-24084-ms
Arteaga-Arteaga, H. B., Mora-Rubio, A., Florez, F., Murcia-Orjuela, N., Diaz-Ortega, C. E., Orozco-Arias, S., delaPava, M., Bravo-Ortíz, M. A., Robinson, M., Guillen-Rondon, P., & Tabares-Soto, R. (2021). Machine learning applications to predict two-phase flow patterns. PeerJ Computer Science, 7, Article e798. https://doi.org/10.7717/peerj-cs.798
Barjouei, H. S., Ghorbani, H., Mohamadian, N., Wood, D. A., Davoodi, S., Moghadasi, J., & Saberi, H. (2021). Prediction performance advantages of deep machine learning algorithms for two-phase flow rates through wellhead chokes. Journal of Petroleum Exploration and Production Technology, 11(3), 1233–1261. https://doi.org/10.1007/s13202-021-01087-4
Brownlee, J. (2021). A gentle introduction to ensemble learning algorithms. Machine Learning Mastery. https://machinelearningmastery.com
Cepeda-Vega, A., Amaya-Gómez, R., Asuaje, M., Torres, C., Valencia, C., & Ratkovich, N. (2022). Pipeline twophase flow pressure drop algorithm for multiple inclinations. Processes, 10(5), Article 1009. https://doi.org/10.3390/pr10051009
Demir, N. (2016). Ensemble methods: Elegant techniques to produce improved machine learning results. Towards Data Science. https://towardsdatascience.com
Gong, J., Kang, Q., Wu, H., Li, X., Shi, B., & Song, S. (2023). Application and prospects of multi-phase pipeline simulation technology in empowering the intelligent oil and gas fields. Journal of Pipeline Science and Engineering, 3(2), Article 100127. https://doi.org/10.1016/j.ipse.2023.100127
Hafsa, N., Rushd, S., & Yousuf, H. (2023). Comparative performance of machine-learning and deep-learning algorithms in predicting gas-liquid flow regimes. Processes, 11(1), Article 177. https://doi.org/10.3390/pr11010177
Huang, Z., Duo, Y., & Xu, H. (2024). Prediction of two-phase flow patterns based on machine learning. Nuclear Engineering and Design, 421, Article 113107. https://doi.org/10.1016/j.nucengdes.2024.113107
Ibrahim, S. S., Abdulkareem, L. A., & Mahmood, R. A. (2022). Mathematical model for predicting the development of two-phase flow in a horizontal pipe. Revista de Chimie, 73(2), 123–135. https://doi.org/10.37358/rev.chim.1949
Khan, U., Pao, W., Sallih, N., & Hassan, F. (2022). Identification of horizontal gas-liquid two-phase flow regime using deep learning. CFD Letters, 14(10), 68–78. https://doi.org/10.1007/s37934/cfdl.14.10.6878
Khan, U., Pao, W., & Sallih, N. (2023). Numerical gas-liquid two-phase flow regime identification in a horizontal pipe using dynamic pressure data. Applied Sciences, 13(2), Article 1225. https://doi.org/10.3390/app13021225
Lutins, E. (2017). Ensemble methods in machine learning: What are they and why use them. Towards Data Science. https://towardsdatascience.com
Manikonda, K., Islam, R., Obi, C., Hasan, A. R., Sleiti, A. K., Abdelrazeq, M. W., Hassan, I. G., & Rahman, M. A. (2022). Horizontal two-phase flow regime identification with machine learning classification models. In International Petroleum Technology Conference (p. D011S021R002). IPTC.
Mohammed, A., & Kora, R. (2023). A comprehensive review on ensemble deep learning: Opportunities and challenges. Journal of King Saud University - Computer and Information Sciences, 35(2), 757–774.
Ruiz-Díaz, C. M., Perilla-Plata, E. E., & González-Estrada, O. A. (2024). Two-phase flow pattern identification in vertical pipes using transformer neural networks. Inventions, 9(1), Article 15. https://doi.org/10.3390/inventions9010015
Soedarmo, A. A. (2023). A benchmark case of machine-learning, hybrid, and high-resolution physics-based models for gas-liquid stratified flow in pipes. In Offshore Technology Conference. OnePetro.
Wahid, M., Tafreshi, R., Khan, Z., & Retnanto, A. (2023). A hybrid model to predict the pressure gradient for the liquidliquid flow in both horizontal and inclined pipes for unknown flow patterns. Heliyon, 9(4), Article e15012. https://doi.org/10.1016/j.heliyon.2023.e15012
