Machine learning accelerated discrete element modeling of granular flows

Lu, Liqiang; Gao, Xi; Dietiker, Jean-François; Shahnam, Mehrdad; Rogers, William A.

doi:10.1016/j.ces.2021.116832

Machine learning accelerated discrete element modeling of granular flows

Journal Article · Wed Jun 02 00:00:00 EDT 2021 · Chemical Engineering Science

DOI:https://doi.org/10.1016/j.ces.2021.116832· OSTI ID:1869680

Lu, Liqiang ^[1]; Gao, Xi ^[1]; Dietiker, Jean-François ^[1]; Shahnam, Mehrdad ^[2]; Rogers, William A. ^[2]

National Energy Technology Lab. (NETL), Morgantown, WV (United States); NETL Support Contractor, Morgantown, WV (United States)
National Energy Technology Lab. (NETL), Morgantown, WV (United States)

Granular flows are widely encountered in many industrial processes and natural phenomena. Discrete Element Modeling (DEM) is a useful tool for understanding and troubleshooting devices, which handle granular materials. However, its applicability is significantly limited by the huge computational cost associated with detecting and computing collisions. In this research, the computation speed of DEM was accelerated by orders of magnitude using a convolutional neural network to replace the direct calculation of particle-particle and particle-boundary collisions. The MFiX software was used to generate the training and testing dataset. Additionally, a GPU accelerated TensorFlow model was used to train the neural network and test the results. The model fluctuations caused by different training steps were reduced with a multi-scale loss function. The accuracy was improved with more frames within one training step. The modeling of a rotating drum and a hopper demonstrated the accuracy and efficiency of this machine learning accelerated DEM in the simulation of granular flows.

View Accepted Manuscript (DOE)

Research Organization:: National Energy Technology Laboratory (NETL), Pittsburgh, PA, Morgantown, WV, and Albany, OR (United States)

Sponsoring Organization:: USDOE Office of Fossil Energy (FE)

Grant/Contract Number:: 89243318CFE000003

OSTI ID:: 1869680

Journal Information:: Chemical Engineering Science, Journal Name: Chemical Engineering Science Journal Issue: None Vol. 245; ISSN 0009-2509

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (20)

Machine learning to assist filtered two‐fluid model development for dense gas–particle flows Zhu, Li‐Tao; Tang, Jia‐Xun; Luo, Zheng‐Hong AIChE Journal, Vol. 66, Issue 6 https://doi.org/10.1002/aic.16973	journal	March 2020
The multiphase particle-in-cell (MP-PIC) method for dense particulate flows Andrews, M. J.; O'Rourke, P. J. International Journal of Multiphase Flow, Vol. 22, Issue 2 https://doi.org/10.1016/0301-9322(95)00072-0	journal	April 1996
Verification and validation of a coarse grain model of the DEM in a bubbling fluidized bed Sakai, Mikio; Abe, Minami; Shigeto, Yusuke Chemical Engineering Journal, Vol. 244 https://doi.org/10.1016/j.cej.2014.01.029	journal	May 2014
Computer virtual experiment on fluidized beds using a coarse-grained discrete particle method—EMMS-DPM Lu, Liqiang; Xu, Ji; Ge, Wei Chemical Engineering Science, Vol. 155 https://doi.org/10.1016/j.ces.2016.08.013	journal	November 2016
Influences of operating parameters on the fluidized bed coal gasification process: A coarse-grained CFD-DEM study Hu, Chenshu; Luo, Kun; Wang, Shuai Chemical Engineering Science, Vol. 195 https://doi.org/10.1016/j.ces.2018.10.015	journal	February 2019
Modeling of the filtered drag force in gas–solid flows via a deep learning approach Zhang, Yu; Jiang, Ming; Chen, Xiao Chemical Engineering Science, Vol. 225 https://doi.org/10.1016/j.ces.2020.115835	journal	November 2020
Parallel-vector algorithms for particle simulations on shared-memory multiprocessors Nishiura, Daisuke; Sakaguchi, Hide Journal of Computational Physics, Vol. 230, Issue 5 https://doi.org/10.1016/j.jcp.2010.11.040	journal	March 2011
Quasi-real-time simulation of rotating drum using discrete element method with parallel GPU computing Xu, Ji; Qi, Huabiao; Fang, Xiaojian Particuology, Vol. 9, Issue 4 https://doi.org/10.1016/j.partic.2011.01.003	journal	August 2011
Open-source MFIX-DEM software for gas–solids flows: Part I—Verification studies Garg, Rahul; Galvin, Janine; Li, Tingwen Powder Technology, Vol. 220 https://doi.org/10.1016/j.powtec.2011.09.019	journal	April 2012
Open-source MFIX-DEM software for gas-solids flows: Part II — Validation studies Li, Tingwen; Garg, Rahul; Galvin, Janine Powder Technology, Vol. 220 https://doi.org/10.1016/j.powtec.2011.09.020	journal	April 2012
A GPU-based DEM approach for modelling of particulate systems Gan, J. Q.; Zhou, Z. Y.; Yu, A. B. Powder Technology, Vol. 301 https://doi.org/10.1016/j.powtec.2016.07.072	journal	November 2016
Neural-network-based filtered drag model for gas-particle flows Jiang, Yundi; Kolehmainen, Jari; Gu, Yile Powder Technology, Vol. 346 https://doi.org/10.1016/j.powtec.2018.11.092	journal	March 2019
A supervised machine learning approach for predicting variable drag forces on spherical particles in suspension He, Long; Tafti, Danesh K. Powder Technology, Vol. 345 https://doi.org/10.1016/j.powtec.2019.01.013	journal	March 2019
Reynolds averaged turbulence modelling using deep neural networks with embedded invariance Ling, Julia; Kurzawski, Andrew; Templeton, Jeremy Journal of Fluid Mechanics, Vol. 807 https://doi.org/10.1017/jfm.2016.615	journal	October 2016
Assessment of Different Discrete Particle Methods Ability To Predict Gas-Particle Flow in a Small-Scale Fluidized Bed Lu, Liqiang; Gopalan, Balaji; Benyahia, Sofiane Industrial & Engineering Chemistry Research, Vol. 56, Issue 27 https://doi.org/10.1021/acs.iecr.7b01862	journal	June 2017
Deep learning LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey Nature, Vol. 521, Issue 7553 https://doi.org/10.1038/nature14539	journal	May 2015
Machine learning–accelerated computational fluid dynamics Kochkov, Dmitrii; Smith, Jamie A.; Alieva, Ayya Proceedings of the National Academy of Sciences, Vol. 118, Issue 21 https://doi.org/10.1073/pnas.2101784118	journal	May 2021
Latent Space Physics: Towards Learning the Temporal Evolution of Fluid Flow Wiewel, S.; Becher, M.; Thuerey, N. Computer Graphics Forum, Vol. 38, Issue 2 https://doi.org/10.1111/cgf.13620	journal	May 2019
Data-driven fluid simulations using regression forests Ladický, L'ubor; Jeong, SoHyeon; Solenthaler, Barbara ACM Transactions on Graphics, Vol. 34, Issue 6 https://doi.org/10.1145/2816795.2818129	journal	November 2015
Coarse-Grain DEM Modelling in Fluidized Bed Simulation: A Review Di Renzo, Alberto; Napolitano, Erasmo; Di Maio, Francesco Processes, Vol. 9, Issue 2 https://doi.org/10.3390/pr9020279	journal	February 2021

Similar Records

Developing Drag Models for Non-Spherical Particles through Machine Learning

Technical Report · Sun Jan 19 23:00:00 EST 2025 · OSTI ID:2503555

Classification of particle height in a hopper bin from limited discharge data using convolutional neural network models

Journal Article · Thu Aug 23 00:00:00 EDT 2018 · Powder Technology · OSTI ID:1543588

Dense granular flows with MFIX-Exa

Technical Report · Tue Mar 04 23:00:00 EST 2025 · OSTI ID:2530749

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
TensorFlow
convolutional neural network
discrete element modeling
granular flow
machine learning

Machine learning accelerated discrete element modeling of granular flows

Citation Formats

References (20)

Similar Records

Related Subjects