A neural network-based method for estimation of binary gas diffusivity

In this study, a feedforward three-layer neural network is developed to predict binary diffusion coefficient (DAB) of gases at atmospheric pressure over a wide range of temperatures based on the critical temperature (Tc), critical volume (Vc) and molecular weight (M) of each component in the binary mixture. The accuracy of the method is evaluated through a test data set not used in the training stage of the network. Furthermore, the performance of the neural network model is compared with that of well known correlations suggested in the literature. The results of this comparison show that our developed method outperforms other correlations, with respect to accuracy as well as extrapolation capabilities.