Application Of Machine Learning Models To Predict Warping Of Plastic Automotive Parts

Evandro Menezes de Souza Amarante; João Paulo Rios Brandão de Oliveira; Pedro Guilherme Carvalho de Souza Marconi; Armando Sá Ribeiro Júnior

doi:10.63595/vetor.v35i1.18192

Autores

Evandro Menezes de Souza Amarante Universidade Federal da Bahia https://orcid.org/0000-0003-1619-1385
João Paulo Rios Brandão de Oliveira Universidade Federal da Bahia
Pedro Guilherme Carvalho de Souza Marconi Universidade Federal da Bahia https://orcid.org/0009-0001-7857-689X
Armando Sá Ribeiro Júnior Universidade Federal da Bahia https://orcid.org/0000-0002-5960-3696

DOI:

https://doi.org/10.63595/vetor.v35i1.18192

Palavras-chave:

Moldagem por injeção, Planejamento experimental, Métodos estatísticos, Modelos de Machine Learning

Resumo

Para a fabricação de peças plásticas com geometrias complexas e em grande escala, a moldagem por injeção é um dos processos de manufatura mais utilizados. Em relação ao aspecto dimensional, um dos critérios de qualidade comumente levado em consideração no desenvolvimento de novos produtos é a redução do empenamento da peça. Na indústria automotiva, a fabricação de peças exige alta precisão dimensional, pois muitos componentes têm um caráter estético ou necessitam de encaixes perfeitos. Dessa forma, este trabalho faz uso de planejamentos experimentais, simulações numéricas, métodos estatísticos e modelos de Machine Learning para a determinação do modelo de predição do empenamento de um porta-copo automotivo. Os polímeros utilizados foram o polipropileno (PP) e a acrilonitrila butadieno estireno (ABS). Os resultados revelaram que os modelos de regressão desenvolvidos para a predição do empenamento tiveram resultados melhores em relação aos dados do ABS. Com relação aos modelos de classificação, ambos atingiram uma taxa de precisão superior a 90%. Estes resultados fornecem ferramentas úteis durante a fase de experimentação do molde (tryout), ajudando a reduzir tempo, custo e desperdício de material.

Downloads

Não há dados estatísticos.

Referências

K. Cai, T. O'Leary, R. Mulyana, and J. M. Castro, “Effect of processing parameter changes on mechanical properties during injection molding: Amorphous versus semi‐crystalline materials,” Polymer Engineering & Science, vol. 4, no. 6, pp. 2868–2874, 2024. Available at: https://doi.org/10.1002/pen.26731

J. Shoemaker, Moldflow design guide: a resource for plastics engineers, Hanser Verlag, 2006.

J. G. Kovács and B. Sikló, “Investigation of cooling effect at corners in injection molding,” International Communications in Heat and Mass Transfer, vol. 38, no. 10, pp. 1330–1334, 2011. Available at: https://doi.org/10.1016/j.icheatmasstransfer.2011.08.007

P. Marconi, E. Amarante, C. Ferreira, V. Beal, and A. Ribeiro Júnior, “Steel and Aluminum Molds: The Effect of Thickness on Productivity and Part Quality,” SAE International Journal of Materials and Manufacturing, vol. 17, no. 4, pp. 341–353, 2024. Available at: https://doi.org/10.4271/05-17-04-0024

E. M. S. Amarante, P. G. C. S. Marconi, J. P. R. B. Oliveira, V. E. Beal, C. V. Ferreira, and A. S. Ribeiro Júnior, “Determining thermoplastic injection parameters using the gradient-based optimisation technique and the heuristic method,” in XII Congresso Nacional de Engenharia Mecânica, Natal-RN, Brasil, 2024.

D. C. Montgomery, Diseño y análisis de experimentos, México: Iberoamérica, 1991.

E. V. C. Galdamez and L. C. R. Carpinetti, “Aplicação das técnicas de planejamento e análise de experimentos no processo de injeção plástica,” Gestão & Produção, vol. 11, no. 1, pp. 121–134, 2004. Available at: https://doi.org/10.1590/S0104-530X2004000100011

Z. Obermeyer and E. J. Emanuel, “Predicting the future-big data, machine learning, and clinical medicine,” New England Journal of Medicine, vol. 375, no. 13, pp. 1216–1219, 2016. Available at: https://doi.org/10.1056/NEJMp1606181

C. O. Affonso and R. J. Sassi, “Aplicação de redes Neuro Fuzzy ao processamento de peças automotivas por meio de injeção de polímeros,” Production, vol. 25, no. 1, pp. 157–169, 2015. Available at: https://doi.org/10.1590/S0103-65132014005000005

R. Manickam, “Back Propagation Neural Network for Prediction of Some Shell Moulding Parameters,” Periodica Polytechnica Mechanical Engineering, vol. 60, no. 4, pp. 203–208, 2016. Available at: https://doi.org/10.3311/PPme.8684

R. J. Bensingh, R. Machayaram, R. Boopathy, and C. Jebaraj, “Injection molding process optimization of a bi-aspheric lens using hybrid artificial neural networks (ANNs) and particle swarm optimization (PSO)”, Measurement, vol. 134, pp. 359–374, 2019. Available at: https://doi.org/10.1016/j.measurement.2018.10.066

R. Sedighi, M. S. Meiabardi, and M. Sedighi, “Optimisation of gate location based on weld line in plastic injection moulding using computer-aided engineering, artificial neural network, and genetic algorithm,” International Journal of Automotive and Mechanical Engineering, vol. 14, no. 3, pp. 4419-4431, 2017. Available at: https://doi.org/10.15282/ijame.14.3.2017.3.0350

O. Ogorodnyk, O. V. Lyngstad, M. Larsen, K Wang, and K. Martinsen, “Application of machine learning methods for prediction of parts quality in thermoplastics injection molding,” in Advanced Manufacturing and Automation VIII 8, Wang, K., Wang, Y., Strandhagen, J., Yu, T. (Eds). Changzhou: China, 2019, pp. 237–244. Available at: https://doi.org/10.1007/978-981-13-2375-1_30

D. O. Kazmer, Injection Mold Design Engineering, 2nd edition, Hanser, 2016.

S. Jayapalan, “8. Optimization of Injection Molding Process Parameters for Minimizing Volumetric Shrinkage and Warpage Using Moldflow Simulation and Taguchi Analysis Technique,” in Polymers and Composites Manufacturing, Kumar, K. and Paulo Davim, J. (Eds.), Berlin, Germany: De Gruyter, 2020, chap. 8, pp. 137–152. Available at: https://doi.org/10.1515/9783110655049-008

M. A. Barghash and F. A. Alkaabneh, “Shrinkage and Warpage Detailed Analysis and Optimization for the Injection Molding Process Using Multistage Experimental Design,” Quality Engineering, vol. 26, no. 3, pp. 319–334, 2014. Available at: https://doi.org/10.1080/08982112.2013.852679

R. A. Johnson and D.W. Wichern, Applied multivariate statistical analysis, Madison: Prentice Hall International, 1998.

Z. Mustaffa and Y. Yusof, “A Comparison of Normalization Techniques in Predicting Dengue Outbreak,” in 2010 International Conference on Information and Finance (ICIF 2010). Kuala Lumpur: Malaysia, 2010, pp. 345–349. Available at: https://repo.uum.edu.my/id/eprint/3163/

E. M. de S. Amarante, V. G. S. F. dos Santos, P. G. C. de S. Marconi, A. S. Ribeiro Júnior, V. E. Beal, and C. V. Ferreira, “Estimativa da vida útil em moldes em alumínio por meio de regressões não-lineares,” in 12º Congresso Brasileiro de Engenharia de Fabricação. Brasília-DF: Brasil, 2023.

F. Bre, J. M. Gimenez, and V. D. Fachinotti, “Prediction of wind pressure coefficients on building surfaces using artificial neural networks,” Energy and Buildings, vol. 158, pp. 1429-1441, 2018. Available at: https://doi.org/10.1016/j.enbuild.2017.11.045

S. Haykin, Neural Networks: a comprehensive foundation, New York: Willey & Sons, 2001.

H. Tercan, A. Guajardo, J. Heinisch, T. Thiele, C. Hopmann, and T. Meisen “Transfer-learning: bridging the gap between real and simulation data for machine learning in injection molding,” Procedia CIRP, vol. 72, pp. 185–190, 2018. Available at: https://doi.org/10.1016/j.procir.2018.03.087

K-M. Tsai and H-J. Luo. “An inverse model for injection molding of optical lens using artificial neural network coupled with genetic algorithm,” Journal of Intelligent Manufacturing, vol. 28, pp. 473–487, 2017. Available at: https://doi.org/10.1007/s10845-014-0999-z

K-M. Tsai and H-J. Luo “Comparison of injection molding process windows for plastic lens established by artificial neural network and response surface methodology,” The International Journal of Advanced Manufacturing Technology, vol. 77, pp. 1599–1611, 2015. Available at: https://doi.org/10.1007/s00170-014-6366-6

N. Arulsudar, N. Subramanian, and R. Murthy, “Comparison of artificial neural network and multiple linear regression in the optimization of formulation parameters of leuprolide acetate loaded liposomes,” Journal of Pharmacy & Pharmaceutical Sciences, vol. 8, no. 2, pp. 243–258, 2005. Available at: https://sites.ualberta.ca/~csps/JPPS8(2)/R.Murthy/leuprolide.htm

C. Hopmann, P. Bibow, T. Kosthorst, and Y. Lockner, “Process setup in injection moulding by human-machine-interfaces and AI,” in 30th International Colloquium Plastics Technology 2020, Aachen: Germany, 2020.

Y. Xu and R. Goodacre, “On Splitting Training and Validation Set: A Comparative Study of Cross-Validation, Bootstrap and Systematic Sampling for Estimating the Generalization Performance of Supervised Learning,” Journal of Analysis and Testing, vol. 2, pp. 249–262, 2018. Available at: https://doi.org/10.1007/s41664-018-0068-2

M. K. Uçar, M. Nour, H. Sindi, and K. Polat, “The Effect of Training and Testing Process on Machine Learning in Biomedical Datasets,” Mathematical Problems in Engineering, vol. 2020, p. 836236, 2020. Available at: https://doi.org/10.1155/2020/2836236

R. Kohavi, “A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection,” in Proceedings of the 14th International Joint Conference on Artificial intelligence, Montreal: Canada, 1995, pp. 1137–1143.

T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning, New York: Springer, 2009. Available at: https://doi.org/10.1007/978-0-387-84858-7

H. Rees, Mold Engineering, Munich-Germany: Hanser Publications, 2002.

D. M. Bryce, Plastic injection molding: Mold design and construction fundamentals, Society of Manufacturing Engineers, 1998.