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 PET bottles requires strict control of the PET resin drying temperature to minimize the generation of acetaldehyde (ACH), a compound that can alter the taste of beverages. This study proposes the use of Artificial Neural Networks (ANN) of the Backpropagation type (Cascadeforwardnet) to support decision-making in controlling the ideal drying temperature. The methodology included data collection from the preform injection process and the application of Computational Intelligence techniques to predict ACH levels. The results demonstrate that ANN can optimize the management of production parameters, reducing waste and improving the quality of the final product.