Deep learning interfacial momentum closures in coarse-mesh CFD two-phase flow simulation using validation data. (February 2021)

• Record Type: Journal Article
• Authors: Bao, Han; Feng, Jinyong; Dinh, Nam; Zhang, Hongbin
• Is Part Of: International journal of multiphase flow. Volume 135(2021)
• Publication Date: 2021-02
• Subjects: Machine learning -- CFD -- Two-phase flow -- Interfacial forces -- Coarse mesh; BAMF Bubbly and moderate void fraction -- CFD computational fluid dynamics -- DFNN Deep feedforward neural network -- DNB Departure from nucleate boiling -- DNS Direct numerical simulation -- FSM Feature similarity measurement -- GELI Global extrapolation through local interpolation -- HF High-fidelity -- IC/BC Initial condition/boundary condition -- IT Interface tracking -- KDE Kernel density estimation -- LF Low-fidelity -- Ml machine learning -- NPP Nuclear power plant -- NRMSE Normalized root mean squared error -- PWR Pressurized water reactor -- QOI Quantity of interest -- RANS Reynolds-averaged navier-stokes; Multiphase flow -- Periodicals; Écoulement polyphasique -- Périodiques; Multiphase flow; Periodicals; 620.1064
• DOI: 10.1016/j.ijmultiphaseflow.2020.103489
• Languages: English
• ISSNs: 0301-9322

Abstract

Highlights: Interfacial momentum exchange is recovered using deep learning and validation data. A data-driven approach is developed to correct coarse-mesh CFD results. Local physical features are identified to represent underlying local patterns. High similarity leads to better predictive performance of deep learning model. Abstract: Multiphase flow phenomena have been widely observed in the industrial applications, yet it remains a challenging unsolved problem. Three-dimensional computational fluid dynamics (CFD) approaches resolve of the flow fields on finer spatial and temporal scales, which can complement dedicated experimental study. However, closures must be introduced to reflect the underlying physics in multiphase flow. Among them, the interfacial forces, including drag, lift, turbulent-dispersion and wall-lubrication forces, play an important role in bubble distribution and migration in liquid-vapor two-phase flows. Development of those closures traditionally rely on the experimental data and analytical derivation with simplified assumptions that usually cannot deliver a universal solution across a wide range of flow conditions. In this paper, a data-driven approach, named as feature-similarity measurement (FSM), is developed and applied to improve the simulation capability of two-phase flow with coarse-mesh CFD approach. Interfacial momentum transfer in adiabatic bubbly flow serves as the focus of the present study. Both a mature and a simplified set of interfacial closures are taken as the low-fidelity data. Validation data (including relevant experimental data and validated fine-mesh CFD simulations results) are adopted as high-fidelity data. Qualitative and quantitative analysis are performed in this paper. These reveal that FSM can substantially improve the prediction of the coarse-mesh CFD model, regardless of the choice of interfacial closures. It demonstrates that data-driven methods can aid the multiphase flow modeling by exploring the connections between local physical features and simulation errors.