Back Propagation neural network modeling for warpage prediction and optimization of plastic products during injection molding

Abstract

Warpage of plastic products is an important evaluation index for Plastic Injection Molding (PIM). A Back Propagation (BP) neural-network model for warpage prediction and optimization of injected plastic parts has been developed based on key process variables including mold temperature, melt temperature, packing pressure, packing time and cooling time during PIM. The approach uses a BP neural network trained by the input and output data obtained from the Finite Element (FE) simulations which are performed on Moldflow software platform. In addition, a kind of automobile glove compartment cap was utilized in this study. Trained by the results of FE simulations conducted by orthogonal experimental design method, the prediction system got a mathematical equation mapping the relationship between the process parameter values and warpage value of the plastic. It has been proved that the prediction system has the ability to predict the warpage of the plastic within an error range of 2%. Process parameters have been optimized with the help of the prediction system. Meanwhile energy consumption and production cycle were also taken into consideration. The optimized warpage value is 1.58mm, which is shortened by 32.99% comparing to the initial warpage result 2.358mm. And the cooling time has been decreased from 20s to 10s, which will greatly shorten the production cycle. The final product can satisfy with the matching requirements and fit the automobile glove compartment well.