A hybrid simulation method integrating CFD and deep learning for gas–liquid bubbly flow

被引：0

作者：

Wen, Kaijie ^{[1
,2
]}

Guo, Li ^{[1
,2
]}

Xia, Zhaojie ^{[1
,2
]}

Cheng, Sibo ^{[3
,4
]}

Chen, Jianhua ^{[1
]}

机构：

[1] State Key Laboratory of Mesoscience and Engineering, Institute of Process Engineering, Chinese Academy of Sciences, Beijing,100190, China

[2] School of Chemical Engineering, University of Chinese Academy of Sciences, Beijing,100049, China

[3] CEREA, École des Ponts Paristech and EDF R&D, Île-de-France, France

[4] Data Science Institute, Department of Computing, Imperial College London, London,SW7 2AZ, United Kingdom

来源：

Chemical Engineering Journal | 2024年 / 495卷

关键词：

This paper develops a hybrid framework that integrates deep learning and CFD simulation for physical field prediction of bubbly flow. The framework utilizes PyTorch for constructing the deep learning model; and OpenFOAM for conducting the CFD simulations. In recursive predictions; i.e. predicting the flow field by the deep learning model successively; the prediction error increases. In contrast; the hybrid simulation mitigates error accumulation and can run for long flow time (T = 300 s) without divergence. Besides; the hybrid simulation effectively predicts the variation in bubble quantity within the calculation domain. The velocity fluctuation at the measurement point can be qualitatively captured; with reasonable fluctuation amplitude close to the prediction of Euler-Lagrange solver DPMFoam. However; there is still some error in the fluctuation period; which may be further reduced by improving the deep learning model or shortening its prediction time span. In the studied case; the hybrid simulation saves a total of 40% of the computation time compared with OpenFOAM simulation. This work provides a feasible way to combine deep learning and CFD for studies of the gas–liquid bubbly flow and more related multiphase flows; and makes contribution to the long-term accelerated simulation. © 2024 Elsevier B.V;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

Journal article (JA)

引用

共 50 条

[1] A hybrid simulation method integrating CFD and deep learning for gas-liquid bubbly flow
Wen, Kaijie
Guo, Li
Xia, Zhaojie
Cheng, Sibo
Chen, Jianhua
CHEMICAL ENGINEERING JOURNAL, 2024, 495
[2] Simulation of a reacting gas-liquid bubbly flow with CFD and PBM: Validation with experiments
Buffo, A.
Vanni, M.
Marchisio, D. L.
APPLIED MATHEMATICAL MODELLING, 2017, 44 : 43 - 60
[3] A rapid simulation method of gas-solid flow by coupling CFD and deep learning
Wen K.
Guo L.
Xia Z.
Chen J.
Huagong Xuebao/CIESC Journal, 2023, 74 (09): : 3775 - 3785
[4] A deep learning-based segmentation method for multi-scale and overlapped bubbles in gas-liquid bubbly flow
Yang, Zhilong
Tian, Wenbin
Deng, Xiaoliang
He, Xiashu
Wang, Zhiying
Wang, Jingzhu
Wang, Yiwei
PHYSICS OF FLUIDS, 2025, 37 (03)
[5] CFD simulation of bubbly turbulent Tayor–Couette flow
Xi Gao
Bo Kong
R.Dennis Vigil
ChineseJournalofChemicalEngineering, 2016, 24 (06) : 719 - 727
[6] Computationally efficient CFD prediction of bubbly flow using physics-guided deep learning
Bao, Han
Feng, Jinyong
Nam Dinh
Zhang, Hongbin
INTERNATIONAL JOURNAL OF MULTIPHASE FLOW, 2020, 131
[7] CFD Simulation of the Gas-Liquid Flow on the Ripple Tray
Jiang, Bin
Li, Zhongtao
Zhang, Luhong
ADVANCED MANUFACTURING TECHNOLOGY, PTS 1-4, 2012, 472-475 : 1605 - 1609
[8] CFD simulation of bubbly flow in a long coaxial heat exchanger
Akhmadullin, Ildar
Kartushinsky, Alexander
THERMAL SCIENCE AND ENGINEERING PROGRESS, 2021, 25
[9] CFD simulation of bubbly turbulent Tayor-Couette flow
Gao, Xi
Kong, Bo
Vigil, R. Dennis
CHINESE JOURNAL OF CHEMICAL ENGINEERING, 2016, 24 (06) : 719 - 727
[10] Assessment of a hybrid CFD model for simulation of complex vertical upward gas-liquid churn flow
Parsi, Mazdak
Agrawal, Madhusuden
Srinivasan, Vedanth
Vieira, Ronald E.
Torres, Carlos F.
McLaury, Brenton S.
Shirazi, Siamack A.
Schleicher, Eckhard
Hampel, Uwe
CHEMICAL ENGINEERING RESEARCH & DESIGN, 2016, 105 : 71 - 84

← 1 2 3 4 5 →