using hybrid artificial neural network-particle swarm optimization for prediction of hips mechanical properties

Artificial neural networks (ann) have emerged as a useful artificial intelligence concept in various engineering applications. also, ann only recently has been used in modeling the mechanical behavior of polymers. this study aims to show the applicability of anns, to predict and determine the mechanical properties of high impact polystyrene (hips). moreover, izod, vicat, and mfi of pure hips were considered, and the effect of 25 different parameters on them investigated. by using ann, a blackbox model is considered as a calculator of mechanical properties. it is not easy to predict the accurate value of these properties without experimental works for two reasons: (1) the nonlinear behavior of the polymerization process and (2) the inaccuracy of experimental results of measurement of each of the properties. to overcome these problems, an alternative prediction model was proposed for calculating properties using a hybrid ann-pso model. all parameters in various cases have been gathered from the industrial dcs system and laboratory for the training of the ann. first, by using the ann model, the sensitivity analysis of parameters has been performed. it is then filtered using the effective ann-pso hybrid parameters. out of 25 proposed parameters, 14, 10, 11 of them were selected in mfi, izod, vicat, respectively, and used to predict new parameters in the modified ann. ultimately, according to the obtained results, it was found that the hybrid ann-pso model was powerful in predicting properties with an average relative error of 6, 5, and 1% for predicting considered properties between industrial and computed ann-pso hybrid model data.