Artificial neural network approach for predicting optimum cure time of rubber compounds

Artificial neural network (ANN) technique has emerged as a powerful tool which can be used for many scientific and/or engineering applications such as process control and system modelling. ANNs are inspired by the nervous biological architecture systems consisting of relatively simple systems working in parallel to facilitate quick decisions. In this study, three different ANN architectures: multilayer perceptron (MLP), Elman network and generalized regression neural network (GRNN) were used for modelling cure curves of a selected rubber compound at different temperatures. The ability of selected ANN architectures on predicting optimum cure times of 11 different rubber compounds in a model tire was studied. Equivalent cure concept, that is traditionally used in rubber and tire industries, was also applied to pre-determine optimum cure times of the same compounds. The results of two techniques, i.e. ANN and equivalent cure concept were compared in view of percentage error criteria. It has been concluded that ANN could be used as a powerful and simple alternative technique for prediction of optimum cure time.