Article

Study on High-Performance Prediction of Wellbore Multiphase Flow Pressure Drop Distribution Based on Artificial Neural Networks

Xi Ouyang^1,2, Xiang Rao^1,2,3*

¹School of Petroleum Engineering, Yangtze University, Wuhan 430100, China.
²State Key Laboratory of Low Carbon Catalysis and Carbon Dioxide Utilization (Yangtze University), Wuhan 430100, China.
³Western Research Institute, Yangtze University, Karamay 834000, China.

^*Correspondence: Xiang Rao, E-mail: raoxiang0103@163.com

Received: 2026-02-02Accepted: 2026-02-07Published: 2026-02-28

AESIG 2026, 2(1), 91-104; https://doi.org/10.58244/aesig.263567

Funding

This research was no funding provided.

Abstract

This paper constructs a proxy model to predict the pressure drop distribution in wellbore multiphase flow based on artificial neural networks (ANNs). 10,000 sets of high-quality samples involving 15 parameters involving wellbore multiphase flow and covering diverse working conditions were generated based on the Beggs-Brill algorithm, which ensures the physical consistency of data and the comprehensiveness of working conditions; two ANN models were constructed to realize the bidirectional nonlinear mapping from wellhead parameters to bottom-hole pressure and from bottom-hole parameters to wellhead pressure, respectively. Case verification results show that the mean relative error of the forward ANN model is only 0.10%, that of the reverse ANN model is 0.15%, and the prediction time for a single sample is less than 0.002 seconds for both models. The research results provide an efficient and reliable technical tool for the dynamic production regulation of oil and gas fields and the rapid evaluation of multi-well development schemes, helping to improve the recovery efficiency and economic benefits of oil and gas exploitation.

Keywords: Deep Learning; Wellbore multiphase flow; Pressure drop prediction; Neural network; Beggs-Brill algorithm; Coupled simulation; Machine learning

Full Text

Download the full text PDF for viewing and using it according to the license of this paper.

Funding

The General Program of the National Natural Science Foundation of China (Grant No. 52574028)
The Youth Science Fund Program (Category A) of the National Natural Science Foundation of China (Grant No. 52525403)
The “Science and Technology Innovation Team” Program of the Xinjiang Uygur Autonomous Region (Grant No. 2024TSYCTD0018).

References

Beggs, D. H., & Brill, J. P. (1973). A study of two-phase flow in inclined pipes. Journal of Petroleum technology, 25(05), 607-617.
Bello, O., & Asafa, T. (2014, April). A functional networks softsensor for flowing bottomhole pressures and temperatures in multiphase flow production wells. In SPE Intelligent Energy International Conference and Exhibition (pp. SPE-167881). SPE.
Cioncolini, A., & Thome, J. R. (2017). Pressure drop prediction in annular two-phase flow in macroscale tubes and channels. International Journal of Multiphase Flow, 89, 321-330.
Ling, C., & Hibiki, T. (2025). Advances in machine learning for data-driven classification of gas–liquid flow regimes. International Communications in Heat and Mass Transfer, 169, 109582.
Liu, Y., Rao, X., He, X., Fu, Q., & Hoteit, H. (2025, September). Boundary-Integral Type Neural Network (BINN) for Flow Problems in Homogeneous Reservoirs. In SPE Middle East Oil and Gas Show and Conference (p. D011S024R002). SPE.
Mahmoud, A. A., Elkatatny, S., & Al-AbdulJabbar, A. (2021). Application of machine learning models for real-time prediction of the formation lithology and tops from the drilling parameters. Journal of Petroleum Science and Engineering, 203, 108574.
Osgouei, R. E., Ozbayoglu, A. M., Ozbayoglu, E. M., Yuksel, E., & Eresen, A. (2015). Pressure drop estimation in horizontal annuli for liquid–gas 2 phase flow:
Orkiszewski, J. (1967). Predicting two-phase pressure drops in vertical pipe. Journal of Petroleum technology, 19(06), 829-838.
Petalas, N., & Aziz, K. (2000). A mechanistic model for multiphase flow in pipes. Journal of Canadian petroleum technology, 39(06).
Rao, X., Liu, Y., & Shen, Y. (2025). Quantum-Classical Physics-Informed Neural Networks for Solving Reservoir Seepage Equations. arXiv preprint arXiv:2512.03923.
Rao, X., Liu, Y., He, X., & Hoteit, H. (2025). Physics-informed Kolmogorov–Arnold networks to model flow in heterogeneous porous media with a mixed pressure-velocity formulation. Physics of Fluids, 37(7).
Rao, X., Liu, Y., Fu, Q., He, X., Kwak, H., Zhao, H., & Hoteit, H. (2025, September). Boundary-Integral Type Neural Network (BINN) for Flow Problems in Anisotropic Reservoirs. In SPE Middle East Oil and Gas Show and Conference (p. D021S048R001). SPE.
Rao, X. (2024). Performance study of variational quantum linear solver with an improved ansatz for reservoir flow equations. Physics of Fluids, 36(4).
Rao, X., Luo, C., He, X., & Hyung, K. (2024, November). An Efficient Quantum Neural Network Model for Prediction of Carbon Dioxide CO2 Sequestration in Saline Aquifers. In Abu Dhabi International Petroleum Exhibition and Conference (p. D021S061R005). SPE.
Rao, X. (2024, November). The first application of quantum computing algorithm in streamline-based simulation of water-flooding reservoirs. In Abu Dhabi International Petroleum Exhibition and Conference (p. D011S003R006). SPE.
Rao, X., He, X., Du, K., Kwak, H., Yousef, A., & Hoteit, H. (2024). A novel projection-based embedded discrete fracture model (pEDFM) for anisotropic two-phase flow simulation using hybrid of two-point flux approximation and mimetic finite difference (TPFA-MFD) methods. Journal of Computational Physics, 499, 112736.
Rao, X., Zhao, H., & Liu, Y. (2022). A meshless numerical modeling method for fractured reservoirs based on extended finite volume method. SPE Journal, 27(6), 3525–3564.
Santoso, A., Goto, D., Takehira, T., Aslam, A., Kawahara, A., & Sadatomi, M. (2016). Non-Newtonian Two-Phase Flow Characteristics across Sudden Expansion in Horizontal Rectangular Minichannel. World Journal of Mechanics, 6(8), 257-272.
Shijo, J. S., & Behera, N. (2023). Pressure drop prediction in fluidized dense phase pneumatic conveying using machine learning algorithms. Journal of Applied Fluid Mechanics, 16(10), 1951-1961.
Zheng, H., Lin, B., Jiang, J., Jin, Y., & Peng, L. (2024, February). Knowledge-Guided Machine Learning Method for Downhole Gauge Record Prediction in Deep Water Gas Field. In Offshore Technology Conference Asia (p. D031S020R004). OTC.