Physics-Informed Neural Network for Unreacted-Core Shrinking Model of Coal Gasification

Physics-informed neural network (PINN) has achieved success in many science and engineering disciplines by encoding physical laws into the loss functions of the neural network. Compared with traditional numerical method, PINN transformed the problem of solving differential equations into the optimiz...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ming Jian Li, Zengrong Su, Chang He, Bingjian Zhang, Qinglin Chen
Formato:	article
Lenguaje:	EN
Publicado:	AIDIC Servizi S.r.l. 2021
Materias:	Chemical engineering TP155-156 Computer engineering. Computer hardware TK7885-7895
Acceso en línea:	https://doaj.org/article/2dd7470c37d64f4389bfa627e61f6f2b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:2dd7470c37d64f4389bfa627e61f6f2b
record_format	dspace
spelling	oai:doaj.org-article:2dd7470c37d64f4389bfa627e61f6f2b2021-11-15T21:48:22ZPhysics-Informed Neural Network for Unreacted-Core Shrinking Model of Coal Gasification10.3303/CET21880742283-9216https://doaj.org/article/2dd7470c37d64f4389bfa627e61f6f2b2021-11-01T00:00:00Zhttps://www.cetjournal.it/index.php/cet/article/view/11867https://doaj.org/toc/2283-9216Physics-informed neural network (PINN) has achieved success in many science and engineering disciplines by encoding physical laws into the loss functions of the neural network. Compared with traditional numerical method, PINN transformed the problem of solving differential equations into the optimization of loss functions by automatic differentiation. In this work, PINN is apply to solve the coal gasification chemical kinetic problems of gas-solid reactions in the form of the unreacted-core shrinking model with governing ordinary differential equations (ODEs). The results show that the prediction performance of the developed PINN is comparable with that of the widely-used Runge-Kutta method, and thus it opens the possibility for the application of deep learning to the modelling of complex chemical kinetics systems.Ming Jian LiZengrong SuChang HeBingjian ZhangQinglin ChenAIDIC Servizi S.r.l.articleChemical engineeringTP155-156Computer engineering. Computer hardwareTK7885-7895ENChemical Engineering Transactions, Vol 88 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Chemical engineering TP155-156 Computer engineering. Computer hardware TK7885-7895
spellingShingle	Chemical engineering TP155-156 Computer engineering. Computer hardware TK7885-7895 Ming Jian Li Zengrong Su Chang He Bingjian Zhang Qinglin Chen Physics-Informed Neural Network for Unreacted-Core Shrinking Model of Coal Gasification
description	Physics-informed neural network (PINN) has achieved success in many science and engineering disciplines by encoding physical laws into the loss functions of the neural network. Compared with traditional numerical method, PINN transformed the problem of solving differential equations into the optimization of loss functions by automatic differentiation. In this work, PINN is apply to solve the coal gasification chemical kinetic problems of gas-solid reactions in the form of the unreacted-core shrinking model with governing ordinary differential equations (ODEs). The results show that the prediction performance of the developed PINN is comparable with that of the widely-used Runge-Kutta method, and thus it opens the possibility for the application of deep learning to the modelling of complex chemical kinetics systems.
format	article
author	Ming Jian Li Zengrong Su Chang He Bingjian Zhang Qinglin Chen
author_facet	Ming Jian Li Zengrong Su Chang He Bingjian Zhang Qinglin Chen
author_sort	Ming Jian Li
title	Physics-Informed Neural Network for Unreacted-Core Shrinking Model of Coal Gasification
title_short	Physics-Informed Neural Network for Unreacted-Core Shrinking Model of Coal Gasification
title_full	Physics-Informed Neural Network for Unreacted-Core Shrinking Model of Coal Gasification
title_fullStr	Physics-Informed Neural Network for Unreacted-Core Shrinking Model of Coal Gasification
title_full_unstemmed	Physics-Informed Neural Network for Unreacted-Core Shrinking Model of Coal Gasification
title_sort	physics-informed neural network for unreacted-core shrinking model of coal gasification
publisher	AIDIC Servizi S.r.l.
publishDate	2021
url	https://doaj.org/article/2dd7470c37d64f4389bfa627e61f6f2b
work_keys_str_mv	AT mingjianli physicsinformedneuralnetworkforunreactedcoreshrinkingmodelofcoalgasification AT zengrongsu physicsinformedneuralnetworkforunreactedcoreshrinkingmodelofcoalgasification AT changhe physicsinformedneuralnetworkforunreactedcoreshrinkingmodelofcoalgasification AT bingjianzhang physicsinformedneuralnetworkforunreactedcoreshrinkingmodelofcoalgasification AT qinglinchen physicsinformedneuralnetworkforunreactedcoreshrinkingmodelofcoalgasification
_version_	1718426774178627584

Physics-Informed Neural Network for Unreacted-Core Shrinking Model of Coal Gasification

Ejemplares similares