Hossein Rahideh

A pressure swing adsorption (PSA) cycle model is implemented in Aspen Adsorption software, and to simulate the PSA process of three component gas mixture O2/N2/AR (0.21-0.78-0.01) With 13X zeolite used adsorbent. Oxygen gas has various applications and the pressure fluctuation Adsorption process is one of the economic processes in the separation of different gases especially oxygen. for the process (PSA) has been modelled through Aspen Adsorption software. The results of the simulation of the pressure swing adsorption process (PSA) have shown a good performance, and in the results of this research increasing the adsorption pressure and cycle time has increased the purity of Oxygen gas. Then an artificial neural network (ANN) was used to predict the performance of the PSA process and further optimized the operating parameters of the PSA cycle and the data obtained from Aspen adsorption was used to train the artificial neural network (ANN). The trained artificial neural network (ANN) model shows a good ability to predict the performance of oxygen gas separation from air in the process of adsorption of pressure fluctuations, although the artificial neural network has reasonable accuracy and significant speed. based on the artificial neural network model, the optimal parameters of the PSA process were selected, this research show that finding the optimal operating parameters of the process (PSA) by the optimization algorithm based on the artificial neural network (ANN) model, which is based on the data generated it is possible to learn from the Aspen Adsorption software by using.