Artificial neural network modeling of O2 separation from air in a hollow fiber membrane module

In this study artificial neural network (ANN) modeling of a hollow fiber membrane module for separation of oxygen from air was conducted. Feed rates, transmembrane pressure, membrane Surface area, and membrane permeability for the present constituents in the feed were network input data. Output data were rate of permeate from the membrane, the amount of N-2 in the remaining flow, and the amount of O-2 in the permeate flow. Experimental data were obtained from software developed by Research Institute of Petroleum Industry (RIPI). A part of the data generated by this software was confirmed by experimental results available in literature. Two third of the data v,,ere employed for training ANNs. Based on different training algorithms, radial basis function (RBF) was found as the best network with minimum training error. Generalization capability of best RBF networks was checked by one third of unseen data. The network was able to properly predict new data that incorporate excellent performance of the network. The developed model can be used for optimization and online control. (c) 2008 Curtin University of Technology and John Wiley & Sons, Ltd.