Abstract
In the current study, an artificial neural network (ANN) and multiple linear regressions (MLR) have been used to develop predictive models for the estimation of molecular diffusion coefficients of 1252 polar and non-polar binary gases at multiple pressures over a wide range of temperatures and substances. The quality and reliability of each method were estimated in terms of the correlation coefficient (R), mean squared errors (MSE), root mean squared error (RMSE), and in terms of external validation coefficients (Q2ext). The comparison between the artificial neural network (ANN) and the multiple linear regressions (MLR) revealed that the neural network models showed a good predicting ability with lower errors (the roots of the mean squared errors in the total database were 0.1400 for ANN1 and 0.1300 for ANN2), and (root mean squared errors in the total databases were 0.5172 for MLR1 and 0.5000 for MLR2).
Highlights
Mass transfer is a term generally used to describe the transport of a substance in liquid and gaseous media
4.2 Multiple linear regressions The models obtained for the prediction of the diffusion coefficient are linear models (Eqs. (9) and (10)): (9)
A good agreement was observed between the experimental values and the predicted values for each neural model
Summary
Mass transfer is a term generally used to describe the transport of a substance (mass) in liquid and gaseous media. It commonly appears in different industrial applications, including the chemical reactions and petroleum industry, as well as ecological natural processes.[1] The mass transfer process mainly includes two aspects: molecular diffusion and convective mass transfer. The knowledge of diffusion coefficient is essential to describe several processes and chemical reactions.[1,2,3,4] Diffusion is normally a slow process, and is a rate-determining factor in many cases of mass transfer. Motivated by the development in theoretical concepts such as the molecular kinetic theory, several studies have suggested various theoretical and semi-empirical models for the estimation of diffusion coefficients of binary gas mixture, such as Stefan-Maxwell (SM), Chapman–Enskog,[5] Gilliland,[6] Arnold,[7] Hirschfelder–Bird–Spotz (HBS),[8] Chen and Othmer,[9] Fuller–Schettler–Giddings,[10] Huang et al.[11]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have