Viscosity prediction by computational method and artificial neural network approach: The case of six refrigerants

Ghaderi, Forouzan; Ghaderi, Amir; Najafi, Bijan; Ghaderi, Noushin

doi:10.1016/j.supflu.2013.04.017

Cited by 25 publications

(10 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…38 To make the use mixtures in these fields easy, it is desirable to know lying thermodynamic properties [10,11]. Although, ANN is an applicable 58 tool to predict the properties of mixtures such as heat capacity, viscosity 59 and liquid-liquid extraction data [12,13]. However, a survey of literatures 60 shows that limited publications have been made on the use of ANN to 61 prediction for the activity coefficients [14][15][16][17].…”

mentioning

confidence: 99%

Thermodynamic modeling of the KCl+formamide/glucose/proline+water ternary systems and activity coefficient prediction based on artificial neural network

Ghalami‐Choobar

Choobar

2015

Journal of Molecular Liquids

View full text Add to dashboard Cite

mentioning

confidence: 99%

Thermodynamic modeling of the KCl+formamide/glucose/proline+water ternary systems and activity coefficient prediction based on artificial neural network

Ghalami‐Choobar

Choobar

2015

Journal of Molecular Liquids

View full text Add to dashboard Cite

“…The success was limited, and the initially high interest declined temporarily before surging again after about 2010. Recent applications of machine learning in thermodynamics include solubility or phase equilibria , thermal ( pvT ) properties , , caloric properties , , transport properties , , and surface tension , to cite only a few. A substantial part of the recent work is dedicated to properties of ionic liquids , , , , , that are hard to describe otherwise.…”

Section: A Preliminary Look Into Machine Learningmentioning

confidence: 99%

Digitalization in Thermodynamics

Forte

Jirasek

Bortz

et al. 2019

Chemie Ingenieur Technik

View full text Add to dashboard Cite

Digitalization is about data and how they are used. This has always been a key topic in applied thermodynamics. In the present work, the influence of the current wave of digitalization on thermodynamics is analyzed. Thermodynamic modeling and simulation is changing as large amounts of data of different nature and quality become easily available. The power and complexity of thermodynamic models and simulation techniques is rapidly increasing, and new routes become viable to link them to the data. Machine learning opens new perspectives, when it is suitably combined with classical thermodynamic theory. Illustrated by examples, different aspects of digitalization in thermodynamics are discussed: strengths and weaknesses as well as opportunities and threats.

show abstract

“…From the analysis and calculation, it was found that the terminal velocity of marble is inversely proportional to the viscosity of fluid. If the viscosity of the fluid increases, the terminal velocity of the marble decreases [15][16][17][18][19][20][21].…”

Section: Introductionmentioning

confidence: 99%

Determination of Fluid Viscosity Coefficient Using jetAudio and Subtitle Edit

Rosdianto

Sulistri

Daud

2019

J. Ilmu. Pend. Fisika

View full text Add to dashboard Cite

The purpose of this study is to produce an experimental design for determining the viscosity coefficient using jetAudio and Subtitle Edit software, and determining the value of the fluid viscosity coefficient by using this experimental design. In this study, the type of fluid used is packaged cooking oil, and the object used is a magnetic ball. The method proposed by the author to measure the travel time of the magnetic ball in cooking oil is by using the combination of coil sensors, jetAudio, and Subtitle Edit. JetAudio software will record magnetic induction traces as the magnetic ball passes the coils into audio format, Subtitle Edit software is used to determine travel time of the magnetic ball based on jetAudio recording data. The results of this study are jetAudio and Subtitle Edit can be used in fluid viscosity coefficient experiments. The value of the cooking oil viscosity coefficient obtained from this study is 0,561431096 Pa.s.

show abstract

Viscosity prediction by computational method and artificial neural network approach: The case of six refrigerants

Cited by 25 publications

References 60 publications

Thermodynamic modeling of the KCl+formamide/glucose/proline+water ternary systems and activity coefficient prediction based on artificial neural network

Thermodynamic modeling of the KCl+formamide/glucose/proline+water ternary systems and activity coefficient prediction based on artificial neural network

Digitalization in Thermodynamics

Determination of Fluid Viscosity Coefficient Using jetAudio and Subtitle Edit

Contact Info

Product

Resources

About