Home Physical Sciences Correlations between Injection Molding Parameters, Morphology and Mechanical Properties of PPS Using Artificial Neural Networks
Article
Licensed
Unlicensed Requires Authentication

Correlations between Injection Molding Parameters, Morphology and Mechanical Properties of PPS Using Artificial Neural Networks

  • C. Lotti and R. E. S. Bretas
Published/Copyright: April 6, 2013
Become an author with De Gruyter Brill
Submit Manuscript Author Information
International Polymer Processing
From the journal International Polymer Processing Volume 21 Issue 2

Abstract

The processing conditions of injection molding have a complex influence on the morphology and on the mechanical properties of a semicrystalline polymer. Therefore, to establish correlations between processing conditions, morphology and mechanical properties constitutes a difficult task; finding these correlations is one of the goals of a materials engineer.

The purpose of this work was to study the influence of the injection molding conditions on the morphology and mechanical properties of poly(p-phenylene sulphide), PPS, using artificial neural networks, ANNs. First, a statistical analysis was done to find the more influential processing parameters that affect the morphology and mechanical properties of the PPS. Second, ANNs were applied to establish correlations between processing conditions, morphology and properties.

It was found that the variables with the highest influence on the morphology and the mechanical properties were the injection and mold temperatures (Tinj and Tmold, respectively), as they showed a straight relationship with the crystallinity index of the injection molded part.

Three different ANNs were built to predict the correlations. The ANN-1 predicted the crystallinity gradient along the thickness of the injection molded part from Tmold, Tinj, and flow rate, Q; the ANN-2 predicted the elastic and flexural modulus, E, and the yield stress from the crystallinity gradient, while the ANN-3 predicted the mechanical properties directly from the processing conditions. All ANNs were built with only fifteen experimental data and were trained with the group cross-validation method, GCV and with a training-test set method. Both methods showed similar and excellent performance. Thus, it can be concluded that ANNs can be used as a powerful tool in the learning of these complex correlations.

∗ Mail address: R. E. S. Bretas, Department of Materials Engineering, Universidade Federal de São Carlos, 13565-905 São Carlos, SP, Brasil. E-mail:

References

1Viana, J. C. M.: Thesis, Universidade de Minho, Portugal (1999)Search in Google Scholar

2Trotignon, J. P., Verdu, J.: J. of Appl. Polym. Sci. 34, p. 1 (1987)10.1002/app.1987.070340101Search in Google Scholar

3Trotignon, J. P., Verdu, J.: J. of Appl. Polym. Sci. 34, p. 19 (1987)10.1002/app.1987.070340102Search in Google Scholar

4Wenig, W., Herzog, F.: J. of Appl. Polym. Sci. 50, p. 2163 (1993)10.1002/app.1993.070501216Search in Google Scholar

5Fujiama, M., Wakino, T.: J. of Appl. Polym. Sci. 35, p. 29 (1988)10.1002/app.1988.070350104Search in Google Scholar

6Rudin, I. I.: Injection molding theory and practice, John Wiley& Sons, New York (1972)Search in Google Scholar

7Phillips, R., Herbert, G., News, J., Wolkiwicz, M.: Polym. Eng. Sci. 34, p. 1731 (1994)10.1002/pen.760342304Search in Google Scholar

8Guo, X., Isayev, A. V., Demiray, M.: Polym. Eng. Sci. 39, p. 2096 (1999)10.1002/pen.11601Search in Google Scholar

9Guo, X., Isayev, A. V., Demiray, M.: Polym. Eng. Sci. 39, p. 2132 (1999)10.1002/pen.11603Search in Google Scholar

10Hsiung, C. M., Cakmak, M.: Polym. Eng. Sci. 31, p. 1372 (1991)10.1002/pen.760311903Search in Google Scholar

11Hsiung, C. M., Cakamk, M., White, J. L.: Polym. Eng. Sci. 30, p. 967 (1990)10.1002/pen.760301606Search in Google Scholar

12Hsiung, C. M., Cakmak, M., Ulcer, Y.: Polym. Eng. Sci. 37, p. 4555 (1996)10.1016/0032-3861(96)00291-1Search in Google Scholar

13Postch, G., Michaeli, W.: Injection molding – an introduction, Hanser Publishers, Munich (1995)Search in Google Scholar

14Cox, H., Mentzer, C. C.: Polym. Eng. Sci. 26, p. 448 (1986)10.1002/pen.760260707Search in Google Scholar

15Kalay, G., Bevis, M.: J. of Appl. Polym. Sci.,: Polym. Phys. 35, p. 265 (1997)10.1002/(SICI)1099-0488(19970130)35:2<265::AID-POLB6>3.0.CO;2-RSearch in Google Scholar

16Perkins, W. G.: Polym. Eng. Sci. 39, p. 2445 (1999)10.1002/pen.11632Search in Google Scholar

17Helps, C. R. G., Brent-Strong, A., Al-Zubi, R., Kawls, V. D., Kohkonen, K. E.: J. of Inj. Mold. Tech. 3, p. 201 (1999)Search in Google Scholar

18Garvey, E. B.: Thesis, Department of Computer Science, Royal Melbourne Institute of Technology, Melbourne, Australia (1997)Search in Google Scholar

19Petrova, T., Kazmer, D.: Adv. Polym. Tech. 18, p. 19 (1999)10.1002/(SICI)1098-2329(199921)18:1<19::AID-ADV3>3.0.CO;2-USearch in Google Scholar

20Sadeghi, B. H. M.: J. of Mat. Proc. Tech.103, p. 411 (2000)10.1016/S0924-0136(00)00498-2Search in Google Scholar

21Abu Fara, D., Rawabdeh, I, Abu-Al-Nadi, D.: J. of Inj. Mold. Tech. 5, p. 105 (2001)Search in Google Scholar

22Lotti, C., Ueki, M. M., Bretas, R. E. S.: J. of Inj. Mold. Tech. 6, p. 157 (2002)Search in Google Scholar

23Kim, H. D., Kim, S. Y.: Int. Polym. Proc. XII, p. 378 (1997)10.1049/ip-cds:19971288Search in Google Scholar

24Nagae, S., Nagura, K., Yamagiwa, N., Yamane, Y., Miyake, K., Inoue, K.: Int. Polym. Proc. XII, p. 116 (1997)10.3139/217.970116Search in Google Scholar

25Sun, Q., Zhang, D., Chen, B., Wadsworth, L. C.: J. of Appl. Polym. Sci. 62, p. 1605 (1996)10.1002/(SICI)1097-4628(19961205)62:10<1605::AID-APP12>3.0.CO;2-0Search in Google Scholar

26Kesharaj, R., Tock, R. W., Haycook, D.: J. of Appl. Polym. Sci. 60, p. 2329 (1996)10.1002/(SICI)1097-4628(19960627)60:13<2329::AID-APP4>3.0.CO;2-GSearch in Google Scholar

27Huang, H.-X., Liao, C.-M.: Polym. Test. 21, p. 745 (2002)10.1016/S0142-9418(02)00005-3Search in Google Scholar

28Moldflow user's manual, v. 4. 1 (2004)Search in Google Scholar

29Bretas, R. E. S., Colias, D., Baird, D. G.: Polym. Eng. Sci. 34, p. 1492 (1994)10.1002/pen.760341909Search in Google Scholar

30XPENETER, http://www.ccp14.ac.uk/ccp/web-mirrors/bca-spreadsheets, (1999)Search in Google Scholar

31Hay, J. N., Luck, D. A.: Polym. 42, p. 8297 (2001)10.1016/S0032-3861(01)00335-4Search in Google Scholar

32ScobboJr., J. J., in: Polymer blends, Performance, Vol. 2, Paul, D. R., Bucknall, C. B. (Eds.), John Wiley & Sons, New York, Chichester, Weinhein, Brisbane, Singapore, Toronto, p. 335/357 (2000)Search in Google Scholar

33Coit, D. W., Jackson, B. T., Smith, A. E.: Int. J. of Prod. Res. 36, p. 2953 (1998)10.1080/002075498192229Search in Google Scholar

34Twomwy, J. M., Smith, A. E., in: Artificial Neural Networks for Civil Engineers: Fundamentals and applications, ASCE Press, 1996Search in Google Scholar

35Sounder, B., Woll, S.: Paper presented at the Annual Technical Conference (ANTEC), San Francisco, USA, 1994Search in Google Scholar

36SNNS – “Stuttgart Neural Network Simulator”, User's guide, version4.2, Tübingen University, www-ra.informatik.uni-tuebingen.de/SNNS, Denmark (2001)Search in Google Scholar

37Lee, T. H., Boey, F. Y., Khor, K. A.: Polym. Compos. 16, p. 481 (1995)10.1002/pc.750160606Search in Google Scholar

38Murphy, N. S., Correale, S. T., Minor, H.: Macromol. 24, p. 1185 (1991)10.1021/ma00005a033Search in Google Scholar

39Lu, S. X., Cebe, P., Capel, M.: Macromol. 30, p. 6243 (1997) Statistica v.2.0, User's guide10.1021/ma961600eSearch in Google Scholar

Received: 2005-4-4
Accepted: 2005-11-4
Published Online: 2013-04-06
Published in Print: 2006-05-01

© 2006, Hanser Publishers, Munich

Articles in the same Issue

  1. Contents
  2. Contents
  3. Regular Contributed Articles
  4. Pressure and Temperature Dependence of LDPE Viscosity and Free Volume: The Effect of Molecular Structure
  5. Correlations between Injection Molding Parameters, Morphology and Mechanical Properties of PPS Using Artificial Neural Networks
  6. Investigations into Kinematic Reversal in Non-isothermal Flows in Single-screw Machines
  7. The Effect of Post-extrusion Conditions in Ribbon Extrusion of Polymer Blends
  8. Effect of the Chemical and Morphological Conditions of the Die Wall on the Extrusion of Linear Polyolefins
  9. Investigation of the Heat Affected Zone of Hot-gas Welded PP Joints
  10. Method for the Optimisation of Screw Elements for Tightly Intermeshing, Co-rotating Twin Screw Extruders
  11. Rheology and Processing of Molten Poly(methyl methacrylate) Resins
  12. PLLA Morphology Controlled by Dry-cast Process
  13. Two Component Injection Molding of Phase Separating Blends
  14. A Low Force Valve for Dynamic Control of Molten Plastics in a Mold
  15. Influence of Drawing and Temperature on the Optical and Structural Properties of Monofilament PP Sutures
  16. Mechanical Properties of Rubber-toughened Post-industrial Glass-fiber-reinforced PA66
  17. Thermal Flow Instability in Metal Injection Molding: Experiment and Simulation
  18. Review Paper
  19. State of the Art: Recycling of EPDM Rubber Vulcanizates
  20. PPS News
  21. PPS News
  22. Seikei-Kakou Abstracts
  23. Seikei-Kakou Abstracts
https://doi.org/10.3139/217.0050

Articles in the same Issue

  1. Contents
  2. Contents
  3. Regular Contributed Articles
  4. Pressure and Temperature Dependence of LDPE Viscosity and Free Volume: The Effect of Molecular Structure
  5. Correlations between Injection Molding Parameters, Morphology and Mechanical Properties of PPS Using Artificial Neural Networks
  6. Investigations into Kinematic Reversal in Non-isothermal Flows in Single-screw Machines
  7. The Effect of Post-extrusion Conditions in Ribbon Extrusion of Polymer Blends
  8. Effect of the Chemical and Morphological Conditions of the Die Wall on the Extrusion of Linear Polyolefins
  9. Investigation of the Heat Affected Zone of Hot-gas Welded PP Joints
  10. Method for the Optimisation of Screw Elements for Tightly Intermeshing, Co-rotating Twin Screw Extruders
  11. Rheology and Processing of Molten Poly(methyl methacrylate) Resins
  12. PLLA Morphology Controlled by Dry-cast Process
  13. Two Component Injection Molding of Phase Separating Blends
  14. A Low Force Valve for Dynamic Control of Molten Plastics in a Mold
  15. Influence of Drawing and Temperature on the Optical and Structural Properties of Monofilament PP Sutures
  16. Mechanical Properties of Rubber-toughened Post-industrial Glass-fiber-reinforced PA66
  17. Thermal Flow Instability in Metal Injection Molding: Experiment and Simulation
  18. Review Paper
  19. State of the Art: Recycling of EPDM Rubber Vulcanizates
  20. PPS News
  21. PPS News
  22. Seikei-Kakou Abstracts
  23. Seikei-Kakou Abstracts
Sign up now to receive a 20% welcome discount
Institutional Access
How does access work?
Have an idea on how to improve our website?
Please write us.
© 2026 De Gruyter Brill
Downloaded on 7.2.2026 from https://www.degruyterbrill.com/document/doi/10.3139/217.0050/html
Scroll to top button