Thermodynamics-Informed Neural Network (TINN) for Phase Equilibrium Calculations Considering Capillary Pressure

The thermodynamic properties of fluid mixtures play a crucial role in designing physically meaningful models and robust algorithms for simulating multi-component multi-phase flow in subsurface, which is needed for many subsurface applications. In this context, the equation-of-state-based flash calcu...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Tao Zhang, Shuyu Sun
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	phase equilibrium flash calculation deep learning TINN Technology T
Acceso en línea:	https://doaj.org/article/97a773f3c05e433d8000ace225d25d35
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:97a773f3c05e433d8000ace225d25d35
record_format	dspace
spelling	oai:doaj.org-article:97a773f3c05e433d8000ace225d25d352021-11-25T17:28:15ZThermodynamics-Informed Neural Network (TINN) for Phase Equilibrium Calculations Considering Capillary Pressure10.3390/en142277241996-1073https://doaj.org/article/97a773f3c05e433d8000ace225d25d352021-11-01T00:00:00Zhttps://www.mdpi.com/1996-1073/14/22/7724https://doaj.org/toc/1996-1073The thermodynamic properties of fluid mixtures play a crucial role in designing physically meaningful models and robust algorithms for simulating multi-component multi-phase flow in subsurface, which is needed for many subsurface applications. In this context, the equation-of-state-based flash calculation used to predict the equilibrium properties of each phase for a given fluid mixture going through phase splitting is a crucial component, and often a bottleneck, of multi-phase flow simulations. In this paper, a capillarity-wise Thermodynamics-Informed Neural Network is developed for the first time to propose a fast, accurate and robust approach calculating phase equilibrium properties for unconventional reservoirs. The trained model performs well in both phase stability tests and phase splitting calculations in a large range of reservoir conditions, which enables further multi-component multi-phase flow simulations with a strong thermodynamic basis.Tao ZhangShuyu SunMDPI AGarticlephase equilibriumflash calculationdeep learningTINNTechnologyTENEnergies, Vol 14, Iss 7724, p 7724 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	phase equilibrium flash calculation deep learning TINN Technology T
spellingShingle	phase equilibrium flash calculation deep learning TINN Technology T Tao Zhang Shuyu Sun Thermodynamics-Informed Neural Network (TINN) for Phase Equilibrium Calculations Considering Capillary Pressure
description	The thermodynamic properties of fluid mixtures play a crucial role in designing physically meaningful models and robust algorithms for simulating multi-component multi-phase flow in subsurface, which is needed for many subsurface applications. In this context, the equation-of-state-based flash calculation used to predict the equilibrium properties of each phase for a given fluid mixture going through phase splitting is a crucial component, and often a bottleneck, of multi-phase flow simulations. In this paper, a capillarity-wise Thermodynamics-Informed Neural Network is developed for the first time to propose a fast, accurate and robust approach calculating phase equilibrium properties for unconventional reservoirs. The trained model performs well in both phase stability tests and phase splitting calculations in a large range of reservoir conditions, which enables further multi-component multi-phase flow simulations with a strong thermodynamic basis.
format	article
author	Tao Zhang Shuyu Sun
author_facet	Tao Zhang Shuyu Sun
author_sort	Tao Zhang
title	Thermodynamics-Informed Neural Network (TINN) for Phase Equilibrium Calculations Considering Capillary Pressure
title_short	Thermodynamics-Informed Neural Network (TINN) for Phase Equilibrium Calculations Considering Capillary Pressure
title_full	Thermodynamics-Informed Neural Network (TINN) for Phase Equilibrium Calculations Considering Capillary Pressure
title_fullStr	Thermodynamics-Informed Neural Network (TINN) for Phase Equilibrium Calculations Considering Capillary Pressure
title_full_unstemmed	Thermodynamics-Informed Neural Network (TINN) for Phase Equilibrium Calculations Considering Capillary Pressure
title_sort	thermodynamics-informed neural network (tinn) for phase equilibrium calculations considering capillary pressure
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/97a773f3c05e433d8000ace225d25d35
work_keys_str_mv	AT taozhang thermodynamicsinformedneuralnetworktinnforphaseequilibriumcalculationsconsideringcapillarypressure AT shuyusun thermodynamicsinformedneuralnetworktinnforphaseequilibriumcalculationsconsideringcapillarypressure
_version_	1718412299410079744

Thermodynamics-Informed Neural Network (TINN) for Phase Equilibrium Calculations Considering Capillary Pressure

Ejemplares similares