ARTIFICIAL NEURAL NETWORKS FOR PREDICTING THE GENERATION OF ACETALDEHYDE IN PET RESIN IN THE PROCESS OF INJECTION OF PLASTIC PACKAGES

Abstract

The industrial production of preforms for the manufacture of PET bottles, during the plastic injection process, is essential to regulate the drying temperature of the PET resin, to control the generation of Acetaldehyde (ACH), which alters the flavor of carbonated or non-carbonated drinks, giving the drink a citrus flavor and putting in doubt the quality of packaged products. In this work, an Artificial Neural Network (ANN) of the Backpropagation type (Cascadeforwardnet) is specified to support the decision-making process in controlling the ideal drying temperature of the PET resin, allowing specialists to make the necessary temperature regulation decisions for the best performance by decreasing ACH levels. The materials and methods were applied according to the manufacturer's characteristics on the moisture in the PET resin grain, which may contain between 50 ppm and 100 ppm of ACH. Data were collected for the method analysis, according to temperatures and residence times used in the blow injection process in the manufacture of the bottle preform, the generation of ACH from the PET bottle after solid post-condensation stage reached residual ACH levels below (3-4) ppm, according to the desired specification, reaching levels below 1 ppm. The results found through the Computational Intelligence (IC) techniques applied by the ANNs, where they allowed the prediction of the ACH levels generated in the plastic injection process of the bottle packaging preform, allowing an effective management of the parameters of production, assisting in strategic decision making regarding the use of temperature control during the drying process of PET resin.