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

  • Jie-Ren ShieEmail author


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.


Design of experiments ANOVA Optimization Radial basis neural network Injection molding 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Chen S, Cowan CFN, Grant PM (1991) Orthogonal least squares learning algorithm for radial basis function networks. IEEE Trans Neural Netw 2(2):302–309CrossRefGoogle Scholar
  2. 2.
    Fletcher R (1981) Practical methods of optimizations, vol. 1. Unconstrained Optimization, and vol. 2, Constrained Optimization. John Wiley and Sons Inc., New YorkGoogle Scholar
  3. 3.
    Liu SJ, Chang CY (2003) The influence of processing parameters on Thin-Wall Gas assisted injection molding of thermoplastic materials. J Reinf Plast Compos 22(8):711–731CrossRefGoogle Scholar
  4. 4.
    Chien RD, Chen SC, Lee PH, Huang JS (2004) Study on the molding characteristics and mechanical properties of injection-molded foaming polypropylene parts. J Reinf Plast Compos 23(4):429–444CrossRefGoogle Scholar
  5. 5.
    Ismail H, Suryadiansyah (2004) A comparative study of the effect of degradation on the properties of PP/NR and PP/RR Blends. Polym-Plast Technol Eng 43(2):319–340CrossRefGoogle Scholar
  6. 6.
    Sain M, Suhara P, Law S, Bouilloux A (2005) A. Bouilloux, interface modification and mechanical properties of natural fiber-polyolefin composite products. J Reinf Plast Compos 24(2):121–130CrossRefGoogle Scholar
  7. 7.
    Yao W, Jia Y, An L, Li B (2005) Elongational properties of biaxially oriented polypropylene with different processing properties. Polym-Plast Technol Eng 44(3):447–462CrossRefGoogle Scholar
  8. 8.
    Modesti M, Lorenzetti A, Bon D, Besco S (2005) Effect of processing conditions on morphology and mechanical properties of compatibilized polypropylene nanocomposites. Polymer 46:10237–10245CrossRefGoogle Scholar
  9. 9.
    Apichartpattanasiri S, Hay JN, Kukureka SN (2001) A study of the tribological behavior of polyamide 66 with varying injection-molding parameters. Wear 251:1557–1566CrossRefGoogle Scholar
  10. 10.
    Jeng MC, Fung CP, Li TC (2002) The study on tribological properties of short glass fiber-reinforced PBT composites for various injection molding process parameters. Wear 252:934–945CrossRefGoogle Scholar
  11. 11.
    Fung CP, Hwang JR, Hsu CC (2003) The effect of injection molding process parameters on the tensile properties of short glass fiber-reinforced PBT. Polym-Plast Technol Eng 42:45–63CrossRefGoogle Scholar
  12. 12.
    Das P (1999) Concurrent optimization of multi-response product performance. Qual Eng 11:365–368CrossRefGoogle Scholar
  13. 13.
    Tong L-I, Su C-T, Wang C-H (1997) The optimization of multi-response problems in Taguchi method. Int J Qual Reliab Manage 14:367–380CrossRefGoogle Scholar
  14. 14.
    Liao H-C (2004) A data envelopment analysis method for optimizing multi-response problem with censored data in the Taguchi method. Comput Indust Eng 46:817–835CrossRefGoogle Scholar
  15. 15.
    Su C-T, Chiang T-L (2003) Optimizing the IC wire bonding process using a neural network/genetic algorithms approach. J Intell Manuf 14(2):229–238, AprilCrossRefGoogle Scholar
  16. 16.
    Hsieh K-L (2005) Parameter optimization of a multi-response process for lead frame manufacturing by employing artificial neural networks. Int J Adv Manuf Technol, DOI  10.1007/s00170-004-2383-1
  17. 17.
    Huang C-C, Tang T-T (2005) Parameter optimization in melt spinning by neural networks and genetic algorithms. Int J Adv Manuf Technol, DOI  10.1007/s00170-004-2302-5
  18. 18.
    Shie J-R (2006) Optimization of dry machining parameters for high-purity graphite in end-milling process by artificial neural networks: a case study. Mater Manuf Process 21:838–845CrossRefGoogle Scholar
  19. 19.
    Briceno FJ, El-Mounayri H, Mukhopadhyay S (2002) Selecting an artificial neural network for efficient modeling and accurate simulation of the milling process. Mach Tools Manuf 42:663–674CrossRefGoogle Scholar
  20. 20.
    Tsai H-M, Wang P-J (2001) Predictions on surface finish in electrical discharge machining based upon neural network models. Mach Tools Manuf 41:1385–1403CrossRefGoogle Scholar
  21. 21.
    Kim B, Park K (2005) Modeling plasma etching process using a radial basis function. Microelectron Eng 77:150–157CrossRefGoogle Scholar
  22. 22.
    Neural Network Toolbox User’s Guide Version. 3.0 (1997) The MathWorks, Inc., 24 Prime Park Way, Natick, MA 01760-1500Google Scholar
  23. 23.
    Douglas CM (1997) Design and analysis of experiments, 4th edn. John Wiley & Sons, Inc., pp 101–630Google Scholar
  24. 24.
    Ranjit KR (1990) A primer on the Taguchi Method. Van Nostrand Reinhold, New YorkzbMATHGoogle Scholar
  25. 25.
    Myers RH, Montgomery DC (2002) Response surface methodology, 2nd edn. John Wiley and Sons Inc., New YorkGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2007

Authors and Affiliations

  1. 1.Department of Mechanical EngineeringMing Hsin University of Science and TechnologyHsinchuTaiwan, Republic of China

Personalised recommendations