Modeling of mass transfer in vacuum membrane distillation process for radioactive wastewater treatment using artificial neural networks

This study focuses on modeling the mass transfer process in the vacuum membrane distillation method (commonly used for radioactive wastewater) by means of artificial neural networks (ANNs). For this purpose, the permeate flux is modeled as a function of four system parameters (pollutant type, feed temperature, permeate temperature, and permeate pressure). To determine the best suitable model for the considered system, several structures of ANNs were analyzed. The results obtained indicated that a feed forward multilayer perceptron neural networks with a hidden layer and ten neurons in hidden layer and with determination of coefficient of 0.975 and maximum root mean squared error of 1.83% can predict the permeate flux with desirable accuracy.

Automated summary

This study models the mass transfer process in vacuum membrane distillation using artificial neural networks, and the best model identified is a feed forward multilayer perceptron neural network with one hidden layer and ten neurons, which can predict permeate flux with high accuracy.