Preparation of expandable polystyrene by multi-stage initiator dosing/ styrene-butadiene-styrene blends with application of artificial neural networks

Abstract

Expandable Polystyrene (EPS) is one of the most used polymers. Preparation of this polymer by conventional method has some problems which causes the synthesis process to be difficult and quality of the prepared EPS to decrease. In this study, Styrene-Butadiene-Styrene (SBS) has been added to improve some properties of prepared polymer and Multi-stage Initiator Dosing (MID) method has been used to reduce the time of the polymerization which increases the polymer’s production capacity. SBS has been added to EPS in shares of 2%wt, 4%wt and 6%wt. Polydispersity index (PDI) test and the amount of the tension in yield point of the polymer has been checked. The amount of absorbed pentane on the polymer studied. The amount of residual monomer on the polymer has been investigated. All of the studies happened in different conditions like: different percentages of initiator, different number of dosings and different time periods of first stage of the polymerization. Experimental data has been simulated by Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF) methods of Artificial Neural Networks (ANN). The performance of simulation for RBF method was better than MLP method due to having strong scientific foundation and also the ability of filtering noises. The experimental data show that the increase in SBS causes improvement in properties like: elongation at break, better pentane absorption and PDI amount has improved, which show better distribution of molecular weight and decrease in residual monomer in products.