Application of Artificial Neural Network (ANN) for modelling H^sub 2^O/KCOOH (potassium formate) dynamic viscosity

This study presents an Artificial Neural Network (ANN) model for predicting the dynamic viscosity of H2O/KCOOH (potassium formate) solution. The model accounts for the effect of temperature and concentration in salt and it covers the concentrations typical for brine (0–50%) and desiccant (60–80%) ap...

Full description

Saved in:
Bibliographic Details
Published inInternational journal of refrigeration Vol. 86; p. 435
Main Authors Longo, Giovanni A, Ortombina, Ludovico, Zigliotto, Mauro
Format Journal Article
LanguageEnglish
Published Paris Elsevier Science Ltd 01.02.2018
Subjects
Artificial neural networks
Desiccants
Drying agents
Mathematical models
Neural networks
Potassium
Saline water
Salt
Temperature effects
Viscosity
Online AccessGet full text

Cover

More Information
Summary:This study presents an Artificial Neural Network (ANN) model for predicting the dynamic viscosity of H2O/KCOOH (potassium formate) solution. The model accounts for the effect of temperature and concentration in salt and it covers the concentrations typical for brine (0–50%) and desiccant (60–80%) applications, including also pure water. The model shows a fair agreement in predicting experimental data: the mean absolute percentage error (MAPE) is 0.92%. The characteristic parameters of the ANN model are fully reported in the paper.
ISSN:0140-7007
1879-2081