Iranian Journal of Chemical Engineering (IJChE)

Abstract The synthesized polystyrene has weaknesses in terms of mechanical, physical and thermal properties which limit the use of this polymer. Therefore, the use of the mixtures of polymers can improve these properties. Different parameters like the mixing speed can affect the quality of the properties of the polymer being prepared from the mixture of several polymers. In this study, different percentages of nanocomposites in different stirring speeds have been added to polystyrene. Different tests have been performed on the prepared polymer and investigating the tests shows that in different stirring speeds the values of the tensile strength and impact resistance of the prepared polymer can be increased while the values of the Vicat Softening Temperature (vicat) and Melt Flow Index (MFI) test numbers remain constant. The obtained results from the laboratory data have been simulated by Artificial Neural Networks (ANNs) in order to predict the results for the points which have not been tested and the simulated results show that the laboratory data covered the simulated data perfectly. The results of tests show that by increasing nanoparticles, the resistance of the polymer against impacts will be increased and in addition, increasing the rate of the stirrer causes all other values of tests to increase.

Abstract In this study, adsorption data for the case of energetically heterogeneous solid surface are modeled using artificial neural network. A neural network with three hidden neurons, including the bias, was able to predict very accurately the temperature dependency of adsorption data. The results were compared with experimental data (over temperature range 273-313 K and 0-2 MPa pressure) and it was found that the predictions of the artificial neural network model fit the experimental data very accurately.

Abstract In this contribution Artificial Neural Network (ANN) modeling of the hydrocracking process is presented. The input–output data for the training and simulation phases of the network were obtained from the Tehran refinery ISOMAX unit. Different network designs were developed and their abilities were compared. Backpropagation, Elman and RBF networks were used for modeling and simulation of the hydrocracking unit. The residual error (root mean squared difference), correlation coefficient and run time were used as the criteria for judging the best network. The Backpropagation model proved to be the best amongst the models considered. The trained networks predicted the yields of products of the ISOMAX unit (diesel, kerosene, light naphtha and heavy naphtha) with good accuracy. The residual error (root mean squared difference) between the model predictions and plant data indicated that the validated model could be reliably used to simulate the ISOMAX unit. A four-lumped kinetic model was also developed and the kinetic parameters were optimized utilizing the plant data. The result of the best ANN model was compared to the result of the kinetic model. The root mean square values for the kinetic model were slightly better than the ANN model but the ANN models are more versatile and more practical tools in such applications as fault diagnosis and pattern recognition.