Modeling of the plasma-induced graft polymerization of acrylic acid onto the Polypropylene (PP) fibers using artificial neural networks and particle swarm optimization (PSO)

In this study, the graft polymerization of acrylic acid (AA) was carried out on Polypropylene (PP) fibers to introduce carboxylic acid groups. The Polypropylene (PP) fibers is treated with oxygen plasma for the introduction of peroxides and subsequently grafted with acrylic acid (AA). Artificial neural networks (ANN) were used to predict the grafting ratio in the plasma grafting process and also particle swarm optimization (PSO) was applied to obtain the optimum values of operational parameters. The input parameters consist of a 4-dimensions vector which includes the reaction time, monomer concentration, time of plasma treatment and reaction temperature and also the output was grafting percentage. Topology and decision parameters have been calculated by trial and error and acceptable correlation coefficients (R = 0.95) were obtained. Finally the results justify that PSO-ANN could be effectively used for plasma grafting as a powerful estimation technique

Keywords:

Artificial neural network , Particle swarm optimization (PSO) , Plasma grafting , acrylic acid (AA) , graft polymerization