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

This paper deals with the development of accurate warpage prediction model for plastic injection molded parts using soft computing tools namely, artificial neural networks and support vector machines. For training, validating and testing of the warpage model, a number of MoldFlow (FE) analyses have been carried out using Taguchi’s orthogonal array in the design of 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 Plastic Insight (MPI) 5.0 software. The artificial neural network model and support vector machine regression model have been developed using conjugate gradient learning algorithm and ANOVA kernel function respectively. The adequacy of the developed models is verified by using coefficient of determination. To judge the ability and efficiency of the models to predict the warpage values absolute relative error has been used. The finite element results show, artificial neural network model predicts with high accuracy compared with support vector machine model.

[1]  K. Jansen,et al.  Effect of processing conditions on shrinkage in injection molding , 1998 .

[2]  G. Salloum,et al.  Residual stresses, shrinkage, and warpage of complex injection molded products : Numerical simulation and experimental validation , 1998 .

[3]  Vijay K. Stokes,et al.  Solidification of thermoviscoelastic melts. Part I: Formulation of model problem , 1995 .

[4]  Vijay K. Stokes,et al.  Solidification of thermoviscoelastic melts. Part 4: Effects of boundary conditions on shrinkage and residual stresses , 1995 .

[5]  Alexander J. Smola,et al.  Regression estimation with support vector learning machines , 1996 .

[6]  Cheng-Hsien Wu,et al.  Effects of geometry and injection‐molding parameters on weld‐line strength , 2005 .

[7]  Yong-Taek Im,et al.  Prediction of shrinkage and warpage in consideration of residual stress in integrated simulation of injection molding , 1999 .

[8]  Marcel Crochet,et al.  Thermoviscoelastic Calculation of Residual Stresses and Residual Shapes of Injection Molded Parts** , 1992 .

[9]  G. Schennink,et al.  The measurement of thermal stress distributions along the flow path in injection‐molded flat plates , 1992 .

[10]  Shih-Jung Liu.  Modeling and simulation of thermally induced stress and warpage in injection molded thermoplastics , 1996 .

[11]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[12]  T. R. Bement,et al.  Taguchi techniques for quality engineering , 1995 .

[13]  Michael St. Jacques.  An analysis of thermal warpage in injection molded flat parts due to unbalanced cooling , 1982 .

[14]  Giuseppe Titomanlio,et al.  Effect of pressure history on shrinkage and residual stresses—injection molding with constrained shrinkage , 1996 .

[15]  Giuseppe Titomanlio,et al.  In‐mold shrinkage and stress prediction in injection molding , 1996 .

[16]  Yoshinori Inoue,et al.  Integrated simulation to predict warpage of injection molded parts , 1991 .

[17]  M. Akay,et al.  Prediction of process‐induced warpage in injection molded thermoplastics , 1996 .