Optimization of injection molding process for contour distortions of polypropylene composite components by a radial basis neural network

This study analyzes the contour distortions of polypropylene (PP) composite components applied to the interior of automobiles. Combining a trained radial basis network (RBN) [1] and a sequential quadratic programming (SQP) method [2], an optimal parameter setting of the injection molding process can be determined. The specimens are prepared under different injection molding conditions by varying melting temperatures, injection speeds and injection pressures of three computer-controlled progressive strokes. Minimizing the contour distortions is the objective of this study. Sixteen experimental runs based on a Taguchi orthogonal array table are utilized to train the RBN and the SQP method is applied to search for an optimal solution. In this study, the proposed algorithm yielded a better performance than the design of experiments (DOE) approach. In addition, the analysis of variance (ANOVA) is conducted to identify the significant factors for the contour distortions of the specimens.

[1]  M. Jeng,et al.  The study on the tribological properties of fiber-reinforced PBT composites for various injection molding process parameters , 2002 .

[2]  Prasun Das.  CONCURRENT OPTIMIZATION OF MULTIRESPONSE PRODUCT PERFORMANCE , 1999 .

[3]  Stephen N. Kukureka,et al.  A study of the tribological behaviour of polyamide 66 with varying injection-moulding parameters , 2001 .

[4]  Chun-Chia Hsu,et al.  The Effect of Injection Molding Process Parameters on the Tensile Properties of Short Glass Fiber-Reinforced PBT , 2003 .

[5]  Chao-Ton Su,et al.  Optimizing the IC wire bonding process using a neural networks/genetic algorithms approach , 2003, J. Intell. Manuf..

[6]  Hanafi Ismail,et al.  A Comparative Study of the Effect of Degradation on the Properties of PP/NR and PP/RR Blends , 2004 .

[7]  R. H. Myers,et al.  Response Surface Methodology: Process and Product Optimization Using Designed Experiments , 1995 .

[8]  Tsann-Tay Tang,et al.  Parameter optimization in melt spinning by neural networks and genetic algorithms , 2006 .

[9]  S. Chen,et al.  Study on the Molding Characteristics and Mechanical Properties of Injection-molded Foaming Polypropylene Parts , 2004 .

[10]  Pei-Jen Wang,et al.  Predictions on surface finish in electrical discharge machining based upon neural network models , 2001 .

[11]  Hung-Chang Liao,et al.  A data envelopment analysis method for optimizing multi-response problem with censored data in the Taguchi method , 2004, Comput. Ind. Eng..

[12]  L. An,et al.  Elongational Properties of Biaxially Oriented Polypropylenes with Different Processing Properties , 2005 .

[13]  Kun-Lin Hsieh,et al.  Parameter optimization of a multi-response process for lead frame manufacturing by employing artificial neural networks , 2006 .

[14]  R. Roy.  A Primer on the Taguchi Method , 1990 .

[15]  Mohini Sain,et al.  Interface Modification and Mechanical Properties of Natural Fiber-Polyolefin Composite Products , 2005 .

[16]  R. Fletcher.  Practical Methods of Optimization , 1988 .

[17]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[18]  David G. Wilson,et al.  2. Constrained Optimization , 2005 .

[19]  M. Modesti,et al.  Effect of processing conditions on morphology and mechanical properties of compatibilized polypropylene nanocomposites , 2005 .

[20]  Jie-Ren Shie,et al.  Optimization of Dry Machining Parameters for High-Purity Graphite in End-Milling Process by Artificial Neural Networks: A Case Study , 2006 .

[21]  Byungwhan Kim,et al.  Modeling plasma etching process using a radial basis function network , 2005 .

[22]  The Influence of Processing Parameters on Thin-Wall Gas Assisted Injection Molding of Thermoplastic Materials , 2003 .

[23]  Chao-Ton Su,et al.  The optimization of multi‐response problems in the Taguchi method , 1997 .

[24]  Snehasis Mukhopadhyay,et al.  Selecting an artificial neural network for efficient modeling and accurate simulation of the milling process , 2002 .