Sparse scattered high performance computing data driven artificial neural networks for multi-dimensional optimization of buoyancy driven heat and mass transfer in porous structures

UM > Faculty of Science and Technology > DEPARTMENT OF ELECTROMECHANICAL ENGINEERING

Status	已發表Published
	Sparse scattered high performance computing data driven artificial neural networks for multi-dimensional optimization of buoyancy driven heat and mass transfer in porous structures
	Su, Y.; Ng, T.I.; Li, Z.G.; Davidson, J.H.
	2020-05-01
Source Publication	Chemical Engineering Journal
ISSN	1385-8947
Pages	125257-125257
Abstract	An artificial intelligence (AI) enhanced optimization framework is developed to reduce computational costs forevaluating transport performance of buoyancy driven heat and mass transfer in porous structures. The presentoptimization framework integrates prediction with artificial neural networks (ANNs), optimization with theweighted objective function, and physics-based simulations with high performance computing (HPC). Multi-dimensional governing parameters and objectives are investigated by ANNs with sparse scattered training dataobtained from HPC with controllable structure generation scheme (CSGS) and parallel non-dimensional latticeBoltzmann method (P-NDLBM). The macroscopic prediction results based on ANNs are validated by comparisonwith HPC results. Full maps of the objective function values versus structure and physical parameters are illu-strated. The maximum objective function value subjected to constraints is obtained together with the corre-sponding optimal structure and physical parameters. The optimal parameters are further applied in HPC toobtain mesoscopic physical fields. The underlying mechanism is also revealed by comparing the physical fieldswith optimal and off-optimal parameters.
Keyword	Artificial neural network Controllable structure generation scheme High performance computing Objective function Parallel non-dimensional lattice Boltzmann method
Language	英語English
The Source to Article	PB_Publication
PUB ID	51708
Document Type	Journal article
Collection	DEPARTMENT OF ELECTROMECHANICAL ENGINEERING
Corresponding Author	Su, Y.
Recommended Citation GB/T 7714	Su, Y.,Ng, T.I.,Li, Z.G.,et al. Sparse scattered high performance computing data driven artificial neural networks for multi-dimensional optimization of buoyancy driven heat and mass transfer in porous structures[J]. Chemical Engineering Journal, 2020, 125257-125257.
APA	Su, Y.., Ng, T.I.., Li, Z.G.., & Davidson, J.H. (2020). Sparse scattered high performance computing data driven artificial neural networks for multi-dimensional optimization of buoyancy driven heat and mass transfer in porous structures. Chemical Engineering Journal, 125257-125257.
MLA	Su, Y.,et al."Sparse scattered high performance computing data driven artificial neural networks for multi-dimensional optimization of buoyancy driven heat and mass transfer in porous structures".Chemical Engineering Journal (2020):125257-125257.

Files in This Item:
There are no files associated with this item.

If you have any objections to this item, please fill out the form below and the administrator will contact you as soon as possible.
Content:
Email：	*
Affiliation No.
Verification Code:	Refresh

Any comments and suggestions are welcomed.
Title:	*
Content:
Email：	*
Verification Code:	Refresh