Prediction of Membrane Desalination Process Performance in The Water Industrial Units by Artificial Neural Networks (ANN)
Volume Title: 1
1Department of Chemical Engineering Petroleum and Gas, University of Semnan, Iran
2Faculty of Chemical, Petroleum and Gas Engineering, Semnan University, Semnan, Iran
Desalination of all membrane-based devices is one of the promising applications of Membrane Distillation (MD) systems. The development of detailed models to predict the performance of membrane distillation systems plays an important role in the design of such an industrial application. In this paper, a business model of Permeate Gap Membrane Distillation (PGMD) is modeled using Artificial Neural Networks (ANN). Condenser inlet temperature, evaporator inlet temperature, feed flow flux and feed water-salt concentration were selected as model inputs, while product flux and Specific Thermal Energy Consumption (STEC) were selected as the response. The results show that the artificial neural networks model is able to predict module behavior more accurately for all input variables. The results show that the artificial neural networks model is able to predict module behavior more accurately for all input variables. Since all the data used are industrial data, the results of this modeling are very useful for industry use and better utilization of membrane-based units.