A recurrent neural network for warpage prediction in injection molding

Abstract

Injection molding is classified as one of the most flexible and economical manufacturing processes with high volume of plastic molded parts. Causes of variations in the process are related to the vast number of factors acting during a regular production run, which directly impacts the quality of final products. A common quality trouble in finished products is the presence of warpage. Thus, this study aimed to design a system based on recurrent neural networks to predict warpage defects in products manufactured through injection molding. Five process parameters are employed for being considered to be critical and have a great impact on the warpage of plastic components. This study used the finite element analysis software Moldflow to simulate the injection molding process to collect data in order to train and test the recurrent neural network. Recurrent neural networks were used to understand the dynamics of the process and due to their memorization ability, warpage values might be predicted accurately. Results show the designed network works well in prediction tasks, overcoming those predictions generated by feedforward neural networks. Copyright © 2011 Universidad Nacional Autónoma de México.