Startseite Application of artificial intelligence techniques to select the objectives in the multi-objective optimization of injection molding
Artikel
Lizenziert
Nicht lizenziert Erfordert eine Authentifizierung

Application of artificial intelligence techniques to select the objectives in the multi-objective optimization of injection molding

  • António Gaspar-Cunha EMAIL logo , João Melo , Tomás Marques und António Pontes
Veröffentlicht/Copyright: 23. Mai 2025
Veröffentlichen auch Sie bei De Gruyter Brill
Manuskript einreichen Informationen für Autor*innen
International Polymer Processing
Aus der Zeitschrift International Polymer Processing Band 40 Heft 3

Abstract

Injection molding is a highly intricate manufacturing process where the design of the mold plays a pivotal role in mitigating defects such as incomplete parts, flash, sink marks, weld lines, air bubbles, warping, and shrinkage. Effective mold design, particularly during the cooling phase, is paramount for achieving high-quality parts and minimizing cycle time. However, optimizing the cooling phase remains challenging due to the extensive number of variables and their interdependent effects. This study addresses these challenges by focusing on the optimization of conformal cooling channels (CCCs), an advanced cooling technology engineered to significantly improve thermal efficiency and temperature uniformity compared to conventional cooling methods. The research utilizes advanced numerical simulation tools, such as Moldex3D, to assess the performance of CCCs and explore their potential to enhance injection molding outcomes. A key obstacle in optimizing CCCs is the multi-objective nature of the design problem, which initially involves 34 performance criteria, such as temperature gradients, cycle time, and defect rates. To manage this complexity, the primary aim of this study was to reduce the number of objectives while preserving the core attributes of the problem. Principal Component Analysis (PCA) was employed to condense these 34 objectives into four principal metrics, facilitating a streamlined and computationally efficient optimization process. To solve the reduced optimization problem, a suite of Artificial Intelligence (AI) methodologies, including data mining, Artificial Neural Networks (ANNs), and Multi-Objective Evolutionary Algorithms (MOEAs), was deployed. A case study involving a coffee-cup part validated the approach, demonstrating that CCCs achieved substantial improvements in temperature uniformity, defect reduction, and cycle time minimization. The findings underscore the efficacy of integrating AI-driven optimization with numerical modeling, highlighting the transformative potential of CCCs as a state-of-the-art solution for advancing injection molding processes.

Keywords: injection molding; conformal cooling channels; objectives selection; multi-objective optimization; principal component analysis; artificial neural networks
Corresponding author: António Gaspar-Cunha, Department of Polymer Engineering, Institute for Polymers and Composites/I3N, University of Minho, Guimarães, Portugal, E-mail:

Funding source: COMPETE 2020 Program and National Funds through FCT

Award Identifier / Grant number: UID-B/05256/2020

Funding source: COMPETE 2020 Program and National Funds through FCT

Award Identifier / Grant number: UID-P/05256/2020

Funding source: PRR/49/INOV.AM/EE

Award Identifier / Grant number: 02/C05-i01.01/2022.PC644865234-00000004

Acknowledgments

The authors acknowledge funding from FEDER funds through the COMPETE 2020 Program and National Funds through FCT (Portuguese Foundation for Science and Technology) under the projects UID-B/05256/2020 and UID-P/05256/2020, as well as the PhD grant 2020.08395.BD.

  1. Research ethics: Not applicable.

  2. Informed consent: Not applicable.

  3. Author contributions: A. Gaspar-Cunha: first draft and final manuscript writing, the definition of the global methodology, definition of the problem to study, and supervision; J.B. Melo: adaptation of Moldex3D to run automatically with the ANN and optimization algorithms, a first draft of the paper, obtention and analysis of the results; T. Marques: development/adaptation of the ANN and MOEA algorithms; A.J. Pontes: supervision and founding.

  4. Use of Large Language Models, AI and Machine Learning Tools: Used to improve language.

  5. Conflict of interest: The author states no conflict of interest.

  6. Research funding: The authors acknowledge the funding by FEDER funds through the COMPETE 2020 Program and National Funds through FCT (Portuguese Foundation for Science and Technology) under the projects UID-B/05256/2020, and UID-P/05256/2020, the PhD grant 2020.08395.BD and PRR/49/INOV.AM/EE (02/C05-i01.01/2022.PC644865234-00000004).

  7. Data availability: Not applicable.

References

Alam, K. and Kamal, M.R. (2004). Runner balancing by a direct genetic optimization of shrinkage. Polym. Eng. Sci. 44: 1949–1959, https://doi.org/10.1002/pen.20198.Suche in Google Scholar

Alam, K. and Kamal, M.R. (2005). A robust optimization of injection molding runner balancing. Comp. Chem. Eng. 29: 1934–1944, https://doi.org/10.1016/j.compchemeng.2005.04.005.Suche in Google Scholar

Arman, S. and Lazoglu, I. (2023). A comprehensive review of injection mold cooling by using conformal cooling channels and thermally enhanced molds. Int. J. Adv. Manuf. Technol. 127: 2035–2106, https://doi.org/10.1007/s00170-023-11593-w.Suche in Google Scholar

Beume, N., Naujoks, B., and Emmerich, M. (2007). SMS-EMOA: multiobjective selection based on dominated hypervolume. Eur. J. Oper. Res. 181: 1653–1669, https://doi.org/10.1016/j.ejor.2006.08.008.Suche in Google Scholar

Chen, P.H.A., Villarreal-Marroquín, M.G., Dean, A.M., Santner, T.J., Mulyana, R., and Castro, J.M. (2018). Sequential design of an injection molding process using a calibrated predictor. J. Qual. Technol. 50: 309–326, https://doi.org/10.1080/00224065.2018.1474696.Suche in Google Scholar

Chung, H. and Das, S. (2018). Functionally graded injection mold design via conformal cooling and hybrid additive manufacturing. J. Manuf. Process. 35: 345–354.Suche in Google Scholar

Coello, C.A.C., Lamont, G.B., and Van Veldhuizen, D.A. (2007). Evolutionary Algorithms for solving multi-objective problems. Springer, Boston, MA.Suche in Google Scholar

Deb, K., Pratap, A., Agarwal, S., and Meyarivan, T. (2000). A fast elitist non-dominated sorting genetic algorithm for multi-objective optimization: NSGA-II. In: Schoenauer, M., Deb, K., Rudolph, G., Yao, X., Lutton, E., Merelo, J.J., Schwefel, H. (eds.) Parallel problem solving from nature (PPSN) VI, vol. 1917, Springer, Paris, France, pp. 849-858.10.1007/3-540-45356-3_83Suche in Google Scholar

Deb, K., Pratap, A., Agarwal, S., and Meyarivan, T. (2002). A fast and elitist multi-objective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6: 182–197, https://doi.org/10.1109/4235.996017.Suche in Google Scholar

Deb, D., Jain, A., and Singh, R.K. (2014). An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, Part I: solving problems with box constraints. IEEE Trans. Evol. Comput. 18: 577–601, https://doi.org/10.1109/tevc.2013.2281535.Suche in Google Scholar

Farooque, R., Asjad, M., and Rizvi, S.J.A. (2020). A current state of art applied to injection moulding manufacturing process - a review. Mater. Today: Proc. 43: 441–446, https://doi.org/10.1016/j.matpr.2020.11.967.Suche in Google Scholar

Feng, J., Kanbur, Z., and Silva, M. (2021a). Optimization of cooling channels in injection molding. Polym. Eng. Sci. 61: 1234–1245.Suche in Google Scholar

Feng, S., Kamat, A.M., and Pei, Y. (2021b). Design and fabrication of conformal cooling channels in molds: review and progress updates. Int. J. Heat Mass Transfer 171: 121082, https://doi.org/10.1016/j.ijheatmasstransfer.2021.121082.Suche in Google Scholar

Fernandes, C., Pontes, A., Viana, J., and Gaspar-Cunha, A. (2010). Using multiobjective evolutionary algorithms in the optimization of operating conditions of polymer injection molding. Polym. Eng. Sci. 50: 1667–1678, https://doi.org/10.1002/pen.21652DO-10.1002/pen.21652.Suche in Google Scholar

Fernandes, C., Pontes, A., Viana, J., and Gaspar-Cunha, A. (2012). Using multi-objective evolutionary algorithms for optimization of the cooling system in polymer injection moulding. Int. Polym. Process. 27: 213–223, https://doi.org/10.3139/217.2511.Suche in Google Scholar

Fernandes, C., Pontes, A.J., Viana, J.C., and Gaspar-Cunha, A. (2018). Modeling and optimization of the injection-molding process: a review. Adv. Polym. Technol. 37: 429–449, https://doi.org/10.1002/adv.21683.Suche in Google Scholar

Forrester, A.I. and Keane, A.J. (2009). Recent advances in surrogate-based optimization. Prog. Aero. Sci. 45: 50–79, https://doi.org/10.1016/j.paerosci.2008.11.001.Suche in Google Scholar

Gao, Z., Dong, G., Tang, Y., and Zhao, Y.F. (2023). Machine learning aided design of conformal cooling channels for injection molding. J. Intell. Manuf. 34: 1183–1201, https://doi.org/10.1007/s10845-021-01841-9.Suche in Google Scholar

Gaspar-Cunha, A., Covas, J.A., and Vergnes, B. (2005). Defining the configuration of co-rotating twin-screw extruders with multiobjective evolutionary algorithms. Polym. Eng. Sci. 45: 1159–1173, https://doi.org/10.1002/pen.20391DO-10.1002/pen.20391.Suche in Google Scholar

Gaspar-Cunha, A., Covas, J.A., and Sikora, J. (2022). Optimization of polymer processing: a review (Part II-molding technologies). Materials 15: 1–20, https://doi.org/10.3390/ma15031138.Suche in Google Scholar PubMed PubMed Central

Gaspar-Cunha, A., Melo, J., Marques, T., and Pontes, A. (2025). Methodology for Designing Injection Molds: Data Mining and Multi-objective Optimization. In: García-Sánchez, P., Hart, E., and Thomson, S.L. (Eds.), Applications of Evolutionary Computation. EvoApplications 2025. Lecture Notes in Computer Science, 15612. Springer, Cham.10.1007/978-3-031-90062-4_10Suche in Google Scholar

Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep learning. MIT Press, Cambridge, MA.Suche in Google Scholar

Hotelling, H. (1933a). Analysis of a complex of statistical variables into principal components. J. Educ. Psychol. 24: 417, https://doi.org/10.1037/h0071325.Suche in Google Scholar

Hotelling, H. (1933b). Simplified calculation of principal components. J. Educ. Psychol. 24: 498, https://doi.org/10.1037/h0070839.Suche in Google Scholar

Jin, Y. (2011). Surrogate-assisted evolutionary computation: recent advances and future challenges. Swarm Evol. Comput. 1: 61–70, https://doi.org/10.1016/j.swevo.2011.05.001.Suche in Google Scholar

Jolliffe, I.T. and Cadima, J. (2016). Principal component analysis: a review and recent developments. Philos. Trans., Math. Phys. Eng. Sci.: 374.10.1098/rsta.2015.0202Suche in Google Scholar PubMed PubMed Central

Jolliffe, I.T. (2002). Principal component analysis, 2nd ed. Springer, New York.Suche in Google Scholar

Kanbur, B.B., Suping, S., and Duan, F. (2020). Design and optimization of conformal cooling channels for injection molding: a review. Int. J. Adv. Manuf. Technol. 106: 3253–3271, https://doi.org/10.1007/s00170-019-04697-9.Suche in Google Scholar

Kitayama, S., Tamada, K., Takano, M., and Aiba, S. (2018). Numerical optimization of process parameters in plastic injection molding for minimizing weldlines and clamping force using conformal cooling channel. J. Manuf. Process. 32: 782–790, https://doi.org/10.1016/j.jmapro.2018.04.007.Suche in Google Scholar

Konuskan, Y., Yılmaz, A.H., Tosun, B., and Lazoglu, I. (2024). Machine learning-aided cooling pro-file prediction in plastic injection molding. Int. J. Adv. Manuf. Technol. 130: 2957–2968, https://doi.org/10.1007/s00170-023-12879-9.Suche in Google Scholar

Osswald, T.A. and Hernández-Ortiz, J.P. (2006). Polymer processing. Hanser, Munich.10.3139/9783446412866.fmSuche in Google Scholar

Rosato, D.V., Rosato, D.V., and Rosato, M.G. (2000). Injection molding handbook. Springer, Boston, MA.10.1007/978-1-4615-4597-2Suche in Google Scholar

Schölkopf, B., Smola, A., and Müller, K.R. (1998). Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput. 10: 1299–1319, https://doi.org/10.1162/089976698300017467.Suche in Google Scholar

Scholz, M., Kaplan, F., Guy, C.L., Kopka, J., and Selbig, J. (2005). Non-linear PCA: a missing data approach. Bioinformatics 21: 3887–3895, https://doi.org/10.1093/bioinformatics/bti634.Suche in Google Scholar PubMed

Shayfull, Z., Sharif, S., Zain, A.M., Ghazali, M.F., and Saad, R.M. (2014). Potential of conformal cooling channels in rapid heat cycle molding: a review. Adv. Polym. Technol. 33, https://doi.org/10.1002/adv.21381.Suche in Google Scholar

Silva, H.M., Noversa, J.T., Fernandes, L., Rodrigues, H.L., and Pontes, A.J. (2022). Design, simulation and optimization of conformal cooling channels in injection molds: a review. Int. J. Adv. Manuf. Technol. 120: 4291–4305, https://doi.org/10.1007/s00170-022-08693-4.Suche in Google Scholar

Simpson, T.W., Peplinski, J.D., Koch, P.N., and Allen, J.K. (2001). Metamodels for computer-based engineering design: survey and recommendations. Eng. Comput. 17: 129–150, https://doi.org/10.1007/pl00007198.Suche in Google Scholar

Wei, X., Silva, M., and Zhang, Y. (2020a). Advances in conformal cooling channels for injection molding. Addit. Manuf. J. 28: 1024–1035.Suche in Google Scholar

Wei, Z., Wu, J., Shi, N., and Li, L. (2020b). Review of conformal cooling system design and additive manufacturing for injection molds. Math. Biosci. Eng. 17: 5414–5431, https://doi.org/10.3934/MBE.2020292.Suche in Google Scholar PubMed

Xu, X., Li, Q., and Hu, B. (2012). Multi-objective optimal approach for injection molding based on surrogate model and particle swarm optimization algorithm. Front. Mech. Eng. 7: 419–426, https://doi.org/10.1007/s11465-012-0342-2.Suche in Google Scholar

Zhang, Y. and Friedrich, K. (2020). Artificial neural networks for optimizing manufacturing processes. Manuf. Sci. Eng. 52: 782–795.Suche in Google Scholar

Zhang, Q. and Li, H. (2007). MOEA/D: a multiobjective evolutionary algorithm based on decom-position. IEEE Trans. Evol. Comput. 11: 712–731, https://doi.org/10.1109/tevc.2007.892759.Suche in Google Scholar
Received: 2024-12-23
Accepted: 2025-04-09
Published Online: 2025-05-23
Published in Print: 2025-07-28

© 2025 Walter de Gruyter GmbH, Berlin/Boston

Artikel in diesem Heft

  1. Frontmatter
  2. Editorial
  3. PPS2024 Ferrol: advances and perspectives in polymer processing
  4. Research Articles
  5. Applying network theory to the modeling of multilayer flows in slot dies: a use case for symbolic regression-based co-extrusion prediction models
  6. Multiscale polyethylene fiber – bacterial nanocellulose composites through combined laser fusion and bacterial in situ synthesis
  7. Novel approach to produce reinforced plastic weld seams using an additive friction stir welding process
  8. Local thermal activation for a combined thermoforming and 3D-printing process
  9. A new recycling strategy for airbag waste
  10. Highly electro-conductive PEDOT based thermoplastic composites: effect of filler form factor on electrical percolation threshold
  11. Cavity balance improvement for injection molded parts via automated flow leader generation
  12. Application of artificial intelligence techniques to select the objectives in the multi-objective optimization of injection molding
  13. Modeling melt conveying and power consumption of conveying elements in co-rotating twin-screw extruders
https://doi.org/10.1515/ipp-2024-0174
Schlagwörter für diesen Artikel
injection molding; conformal cooling channels; objectives selection; multi-objective optimization; principal component analysis; artificial neural networks

Artikel in diesem Heft

  1. Frontmatter
  2. Editorial
  3. PPS2024 Ferrol: advances and perspectives in polymer processing
  4. Research Articles
  5. Applying network theory to the modeling of multilayer flows in slot dies: a use case for symbolic regression-based co-extrusion prediction models
  6. Multiscale polyethylene fiber – bacterial nanocellulose composites through combined laser fusion and bacterial in situ synthesis
  7. Novel approach to produce reinforced plastic weld seams using an additive friction stir welding process
  8. Local thermal activation for a combined thermoforming and 3D-printing process
  9. A new recycling strategy for airbag waste
  10. Highly electro-conductive PEDOT based thermoplastic composites: effect of filler form factor on electrical percolation threshold
  11. Cavity balance improvement for injection molded parts via automated flow leader generation
  12. Application of artificial intelligence techniques to select the objectives in the multi-objective optimization of injection molding
  13. Modeling melt conveying and power consumption of conveying elements in co-rotating twin-screw extruders
Jetzt anmelden und 20% sparen
Institutioneller Zugang
Wie funktioniert Authentifizierung?
Haben Sie eine Idee, wie wir unsere Website verbessern können?
Bitte schreiben Sie uns.
© 2025 De Gruyter Brill
Heruntergeladen am 29.10.2025 von https://www.degruyterbrill.com/document/doi/10.1515/ipp-2024-0174/pdf
Button zum nach oben scrollen