ALL libraries (COBIB.SI union bibliographic/catalogue database)
13.
Correlation and prediction of second and third virial coefficients of gases using an artificial neural network [Elektronski vir]
Oreški, Severina
In the paper, two artificial neural networks are used as new methods to estimate second or third virial coefficients for pure gases at desired temperature. Different types of neural networks with ...different architecture were trained. Out of them two artificial neural network models were developed with the training variables: critical temperature Tc, critical pressure pc, critical volume Vc, acentric factor ù, dipole moment ì and temperature T. The target variable for the first model is the second virial coefficient B. The target variable for the second model is the third virial coefficient C. The trained artificial neural networks were used for prediction of virial coefficients for the temperature ranges of gases in the banks of data. At the moment the data for twenty gases are included in the bank for the second virial coefficient prediction, and the data for thirteen gases are included inthe bank for the third virial coefficients prediction. The banks of data caneasily be expanded for new gases and/or for new temperature ranges. The artificial neural networks can be trained to predict virial coefficients for the extended banks of data again. Second and third virial coefficients were predicted for different gases from the banks of data at temperatures not trained with the artificial neural network. Experimental virial coefficients for the gases were taken from the literature and compared with predictions by the trained neural networks. The accuracy of the modelling is discussed. The study shows that the neural network model for second virial coefficients prediction is a good alternative method for estimating virial coefficients. The model of neural network for third virial coefficients prediction gives bigger prediction errors at this stage of development because of bed experimental data used for training.
It was not necessary to add the material to the shelf.
Bibliographic material was successfully added on shelf.
Adding bibliographical material on shelf was not successful.
Material is already on the shelf.
Permalink
URL:
Impact factor
Access to the JCR database is permitted only to users from Slovenia. Your current IP address is not on the list of IP addresses with access permission, and authentication with the relevant AAI accout is required.
Year
Impact factor
Edition
Category
Classification
JCR
SNIP
JCR
SNIP
JCR
SNIP
JCR
SNIP
Impact factor
Select the library membership card:
DRS,
in which the journal is indexed
Database name
Field
Year
Links to authors' personal bibliographies
Links to information on researchers in the SICRIS system
Subject headings in COBISS General List of Subject Headings
Select pickup location
The material from the parent unit is free. If the material is delivered to the pickup location from another unit, the library may charge you for this service.
