Multiscale CFD simulation of biomass fast pyrolysis with a machine learning derived intra-particle model and detailed pyrolysis kinetics

Liqiang Lu; M. Brennan Pecha; Gavin M. Wiggins; Yupeng Xu; Xi Gao; Bryan Hughes; Mehrdad Shahnam; William A. Rogers; Daniel Carpenter; James E. Parks

doi:10.1016/j.cej.2021.133853

Multiscale CFD simulation of biomass fast pyrolysis with a machine learning derived intra-particle model and detailed pyrolysis kinetics

Liqiang Lu, M. Brennan Pecha, Gavin M. Wiggins, Yupeng Xu, Xi Gao, Bryan Hughes, Mehrdad Shahnam, William A. Rogers, Daniel Carpenter, James E. Parks

Research output: Contribution to journal › Article › peer-review

37 Scopus citations

Abstract

Coupling particle and reactor scale models is as essential as reactor fluid dynamics and particle motion for accurate Computational Fluid Dynamic (CFD) simulations of biomass fast pyrolysis reactors due to intraparticle heat transfer and chemical reactions controlling conversion time and product distributions. Direct online coupling of a particle model with a reactor model is computationally expensive, while offline coupling is case-dependent. In this research, solutions from a series of particle pyrolysis simulations were regressed with Artificial Neural Network (ANN). This machine learning-derived model predicted the same temperature and conversion profiles compared with particle resolved simulation while the isothermal approach overpredicted the temperature by 130 K and underpredicted the conversion time by 30 s. The ANN model was then integrated into CFD simulations of fluidized bed biomass fast pyrolysis with varied feedstocks via coupling PyTorch and MFiX. The averaged error of simulation predicted bio-oil yields with four feedstocks is 6.4%. This multi-scale approach provides an efficient tool for the coupled particle and reactor scale simulations of biomass pyrolysis.

Original language	English
Article number	133853
Journal	Chemical Engineering Journal
Volume	431
DOIs	https://doi.org/10.1016/j.cej.2021.133853
State	Published - Mar 1 2022

Funding

This project was funded by the United States Department of Energy, National Energy Technology Laboratory, in part, through a site support contract. Neither the United States Government nor any agency thereof, nor any of their employees, nor the support contractor, nor any of their employees, makes any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States Government or any agency thereof. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof. This research was conducted as part of the Feedstock-Conversion Interface Consortium (FCIC) funded by the U.S. Department of Energy (DOE) Bioenergy Technologies Office (BETO). This work was also supported by the U.S. Department of Energy, Office of Energy Efficiency and Renewable Energy, Bioenergy Technology Office under Contract No. DE-AC36-08GO28308 with the Alliance for Sustainable Energy, LLC. The authors would like to thank Dr. Debiagi for helpful discussions on pyrolysis kinetics. Dr. Gao would like to acknowledge the partial support from the 2021 Guangdong Provincial Science and Technology Special Fund (“Grant Project + Task List”) Project ( 210729096900340 ). This work was authored in part by the National Renewable Energy Laboratory, operated by Alliance for Sustainable Energy, LLC, for the U.S. Department of Energy (DOE) under Contract No. DE-AC36-08GO28308. Funding provided by U.S. Department of Energy Office of Energy Efficiency and Renewable Energy Bioenergy Technologies Office. The views expressed in the article do not necessarily represent the views of the DOE or the U.S. Government. The U.S. Government retains and the publisher, by accepting the article for publication, acknowledges that the U.S. Government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this work, or allow others to do so, for U.S. Government purposes.

Funders	Funder number
Feedstock-Conversion Interface Consortium
Office of Energy Efficiency and Renewable Energy, Bioenergy Technology Office
U.S. Department of Energy	DE-AC36-08GO28308
National Renewable Energy Laboratory
Bioenergy Technologies Office
National Energy Technology Laboratory

Keywords

Biomass pyrolysis
Fluidized bed
Intra-particle model
Machine learning
Multiscale CFD
Pyrolysis kinetics

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.cej.2021.133853

Cite this

@article{1396da34da8f4f0ab5564b18b92291d9,

title = "Multiscale CFD simulation of biomass fast pyrolysis with a machine learning derived intra-particle model and detailed pyrolysis kinetics",

abstract = "Coupling particle and reactor scale models is as essential as reactor fluid dynamics and particle motion for accurate Computational Fluid Dynamic (CFD) simulations of biomass fast pyrolysis reactors due to intraparticle heat transfer and chemical reactions controlling conversion time and product distributions. Direct online coupling of a particle model with a reactor model is computationally expensive, while offline coupling is case-dependent. In this research, solutions from a series of particle pyrolysis simulations were regressed with Artificial Neural Network (ANN). This machine learning-derived model predicted the same temperature and conversion profiles compared with particle resolved simulation while the isothermal approach overpredicted the temperature by 130 K and underpredicted the conversion time by 30 s. The ANN model was then integrated into CFD simulations of fluidized bed biomass fast pyrolysis with varied feedstocks via coupling PyTorch and MFiX. The averaged error of simulation predicted bio-oil yields with four feedstocks is 6.4%. This multi-scale approach provides an efficient tool for the coupled particle and reactor scale simulations of biomass pyrolysis.",

keywords = "Biomass pyrolysis, Fluidized bed, Intra-particle model, Machine learning, Multiscale CFD, Pyrolysis kinetics",

author = "Liqiang Lu and {Brennan Pecha}, M. and Wiggins, {Gavin M.} and Yupeng Xu and Xi Gao and Bryan Hughes and Mehrdad Shahnam and Rogers, {William A.} and Daniel Carpenter and Parks, {James E.}",

note = "Publisher Copyright: {\textcopyright} 2021 Elsevier B.V.",

year = "2022",

month = mar,

day = "1",

doi = "10.1016/j.cej.2021.133853",

language = "English",

volume = "431",

journal = "Chemical Engineering Journal",

issn = "1385-8947",

publisher = "Elsevier",

}

TY - JOUR

T1 - Multiscale CFD simulation of biomass fast pyrolysis with a machine learning derived intra-particle model and detailed pyrolysis kinetics

AU - Lu, Liqiang

AU - Brennan Pecha, M.

AU - Wiggins, Gavin M.

AU - Xu, Yupeng

AU - Gao, Xi

AU - Hughes, Bryan

AU - Shahnam, Mehrdad

AU - Rogers, William A.

AU - Carpenter, Daniel

AU - Parks, James E.

PY - 2022/3/1

Y1 - 2022/3/1

N2 - Coupling particle and reactor scale models is as essential as reactor fluid dynamics and particle motion for accurate Computational Fluid Dynamic (CFD) simulations of biomass fast pyrolysis reactors due to intraparticle heat transfer and chemical reactions controlling conversion time and product distributions. Direct online coupling of a particle model with a reactor model is computationally expensive, while offline coupling is case-dependent. In this research, solutions from a series of particle pyrolysis simulations were regressed with Artificial Neural Network (ANN). This machine learning-derived model predicted the same temperature and conversion profiles compared with particle resolved simulation while the isothermal approach overpredicted the temperature by 130 K and underpredicted the conversion time by 30 s. The ANN model was then integrated into CFD simulations of fluidized bed biomass fast pyrolysis with varied feedstocks via coupling PyTorch and MFiX. The averaged error of simulation predicted bio-oil yields with four feedstocks is 6.4%. This multi-scale approach provides an efficient tool for the coupled particle and reactor scale simulations of biomass pyrolysis.

AB - Coupling particle and reactor scale models is as essential as reactor fluid dynamics and particle motion for accurate Computational Fluid Dynamic (CFD) simulations of biomass fast pyrolysis reactors due to intraparticle heat transfer and chemical reactions controlling conversion time and product distributions. Direct online coupling of a particle model with a reactor model is computationally expensive, while offline coupling is case-dependent. In this research, solutions from a series of particle pyrolysis simulations were regressed with Artificial Neural Network (ANN). This machine learning-derived model predicted the same temperature and conversion profiles compared with particle resolved simulation while the isothermal approach overpredicted the temperature by 130 K and underpredicted the conversion time by 30 s. The ANN model was then integrated into CFD simulations of fluidized bed biomass fast pyrolysis with varied feedstocks via coupling PyTorch and MFiX. The averaged error of simulation predicted bio-oil yields with four feedstocks is 6.4%. This multi-scale approach provides an efficient tool for the coupled particle and reactor scale simulations of biomass pyrolysis.

KW - Biomass pyrolysis

KW - Fluidized bed

KW - Intra-particle model

KW - Machine learning

KW - Multiscale CFD

KW - Pyrolysis kinetics

UR - http://www.scopus.com/inward/record.url?scp=85120913796&partnerID=8YFLogxK

U2 - 10.1016/j.cej.2021.133853

DO - 10.1016/j.cej.2021.133853

M3 - Article

AN - SCOPUS:85120913796

SN - 1385-8947

VL - 431

JO - Chemical Engineering Journal

JF - Chemical Engineering Journal

M1 - 133853

ER -

Multiscale CFD simulation of biomass fast pyrolysis with a machine learning derived intra-particle model and detailed pyrolysis kinetics

Abstract

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this