Application of Soft Computing for the Prediction of Warpage of Plastic Injection

This paper deals with the development of accurate warpage prediction model for plastic injection molded parts using softcomputing tools namely, artificial neural networks and support vector machines. For training, validating and testing of thewarpage model, a number of MoldFlow (FE) analyses have been carried out using Taguchi’s orthogonal array in the designof experimental technique by considering the process parameters such as mold temperature, melt temperature, packing pressure,packing time and cooling time. The warpage values were found by analyses which were done by MoldFlow PlasticInsight (MPI) 5.0 software. The artificial neural network model and support vector machine regression model have beendeveloped using conjugate gradient learning algorithm and ANOVA kernel function respectively. The adequacy of the developedmodels is verified by using coefficient of determination. To judge the ability and efficiency of the models to predictthe warpage values absolute relative error has been used. The finite element results show, artificial neural network modelpredicts with high accuracy compared with support vector machine model.