JFET_V4_N1_RP3 B. Sidda Reddy K. Thirupathi Reddy K. Vijaya Kumar Reddy Journal on Future Engineering and Technology 2230 – 7184 4 1 21 27 Plastic injection molding, Shrinkage, Warpage, Artificial neural networks This paper deals with the development of accurate shrinkage and warpage prediction model for plastic injection molded part using artificial neural networks. For training, testing of the shrinkage and warpage model, a number of MoldFlow (FE) analyses have been carried out using Box-Behnken Response Surface (BBRS) design technique by considering the process parameters such as mold temperature, melt temperature, packing pressure, packing time, cooling time and injection pressure. The shrinkage and warpage values were found by analyses which were done by MoldFlow plastic insight (MPI) 5.0 software. The artificial neural network model was developed using multilayer perceptron back propagation algorithm using train data and tested using test data. To judge the ability and efficiency of the model to predict the shrinkage and warpage values, percentage deviation and average percentage deviation has been used. The finite element results show that the adaption of back propagation algorithm in artificial neural networks achieved a very satisfactory prediction accuracy of 91.920498%, 90.857614% for warpage and shrinkage respectively. August - October 2008 Copyright © 2008 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=570