Investigation of Tri-Calcium Phosphates Effect in Multi-Stage Production of Expandable Polystyrene with Applications of Artificial Neural Networks

نویسندگان

1 Department of chemical Engineering, Islamic Azad University, Ahar Branch, Ahar, I.R. IRAN

2 Department of chemical Engineering, Islamic Azad University, Ahar Branch, Ahar, I.R. IRAN

doi
10.30492/ijcce.2023.1989605.5868
چکیده

There are some polymers, like expandable polystyrene, which are mostly used in industries. The production of EPS had some issues, which made the process of its production hard and reduced the polymer produced. In this research, besides of implementation of the initiator injection method, adding Tri-Calcium Phosphate (TCP) with different percentages (3, 6, and 9%) in different states (polymerization of the first stage in 2.5, 3, 3.5, and 4 hours and the amount of used initiator in 70, 75, 80, and 100% of the conventional method, and the number of injections in 6, 8, 10, and 12 times) has been tested, and different tests have been conducted on the produced polymer. Artificial neural networks have simulated the results of obtained data from experiments, and the results of the RBF network had better prediction compared with the MLP network because of having more scientific foundations and filtering noises; therefore, the points that have not been experimented on can be predicted by it. Investigating the experimental data shows that in a constant percentage of TCP, by changing the initiator amount and dosing times, and increasing the time of polymerization, the PDI, absorbed pentane, residual monomer amount, and tension in yield point change. TCP change in different laboratory conditions changes the quality of the polymer, with attention to the market's needs, and the importance of each item. The information from this research can be used accordingly.