Uncertainty analysis in sheet metal forming processes: Troubleshooting with machine learning
Tomás Parreira, Daniel Cruz, Armando Marques, Pedro Prates, Marta Oliveira1, Diogo Neto, Abel Santos, Valdemar Fernandes, André Pereira
Abstract. The quality of deep-drawn parts can be significantly affected by various sources of uncertainty associated with the forming process, such as variations in material properties, tool geometry, or process conditions. Due to the complexity of forming processes, pinpointing the source of uncertainty responsible for observed nonconformities in the part is often time-consuming. In this work, a machine learning approach is used to identify the source of uncertainty based on deviations observed in the forming results of a cylindrical cup. Neural networks were employed to build metamodels that link the sources of uncertainty to the forming results. The performance of the metamodels was evaluated using three metrics, namely, the mean absolute error, the root mean squared error and the coefficient of determination. The results demonstrate that the proposed machine learning approach effectively identifies the source of uncertainty based on deviations in the cylindrical cup forming results.
Keywords
Uncertainty, Machine Learning, Forming Processes, Cylindrical Cup
Published online 5/7/2025, 10 pages
Copyright © 2025 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Tomás Parreira, Daniel Cruz, Armando Marques, Pedro Prates, Marta Oliveira1, Diogo Neto, Abel Santos, Valdemar Fernandes, André Pereira, Uncertainty analysis in sheet metal forming processes: Troubleshooting with machine learning, Materials Research Proceedings, Vol. 54, pp 1577-1586, 2025
DOI: https://doi.org/10.21741/9781644903599-170
The article was published as article 170 of the book Material Forming
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] Marques, A.E.; Prates, P.A.; Pereira, A.F.G.; Oliveira, M.C.; Fernandes, J. V.; Ribeiro, B.M. Performance Comparison of Parametric and Non-Parametric Regression Models for Uncertainty Analysis of Sheet Metal Forming Processes. Metals 2020. https://doi.org/10.3390/met10040457
[2] Pereira, A.F.G.; Prates, P.A.; Oliveira, M.C.; Fernandes, J.V. Normal Stress Components during Shear Tests of Metal Sheets. Int J Mech Sci 2019. https://doi.org/10.1016/j.ijmecsci.2019.105169
[3] Pereira, A.F.G.; Marques, A.E.; Oliveira, M.C.; Prates, P.A. Sensitivity Analysis of the of the Square Cup Stamping Process Using a Polynomial Chaos Expansion. 2023. https://doi.org/10.21741/9781644902479-129.
[4] Col, A. Investigation on Press Forming Scatter Origin. In Proceedings of the 6th international conference on material forming; 2003.
[5] de Souza, T.; Rolfe, B.F. Characterising Material and Process Variation Effects on Springback Robustness for a Semi-Cylindrical Sheet Metal Forming Process. Int J Mech Sci 2010. https://doi.org/10.1016/j.ijmecsci.2010.09.009.
[6] Li, Y.Q. Application of Six Sigma Robust Optimization in Sheet Metal Forming. In Proceedings of the AIP Conference Proceedings; 2005.
[7] Hancock, W.; Zayko, and M.; Autio, M.; Ponagajba, D. Analysis of Components of Variation in Automotive Stamping Processes. Qual Eng 1997. https://doi.org/10.1080/08982119708919114.
[8] Arnst, M.; Ponthot, J.-P.; Boman, R. Comparison of Stochastic and Interval Methods for Uncertainty Quantification of Metal Forming Processes. Comptes Rendus Mécanique 2018. https://doi.org/10.1016/j.crme.2018.06.007.
[9] Shahi, V.J.; Masoumi, A.; Franciosa, P.; Ceglarek, D. Quality-Driven Optimization of Assembly Line Configuration for Multi-Station Assembly Systems with Compliant Non-Ideal Sheet Metal Parts. Procedia CIRP 2018. https://doi.org/10.1016/j.procir.2018.02.022.
[10] Dwivedy, M.; Kalluri, V. The Effect of Process Parameters on Forming Forces in Single Point Incremental Forming. Procedia Manuf 2019. https://doi.org/10.1016/j.promfg.2019.02.116.
[11] Prates, P.A.; Adaixo, A.S.; Oliveira, M.C.; Fernandes, J. V. Numerical Study on the Effect of Mechanical Properties Variability in Sheet Metal Forming Processes. The International Journal of Advanced Manufacturing Technology 2018. https://doi.org/10.1007/s00170-018-1604-y.
[12] Huang, C.; Radi, B.; Hami, A. El Uncertainty Analysis of Deep Drawing Using Surrogate Model Based Probabilistic Method. The International Journal of Advanced Manufacturing Technology 2016. https://doi.org/10.1007/s00170-016-8436-4.
[13] Majeske, K.D.; Hammett, P.C. Identifying Sources of Variation in Sheet Metal Stamping. International Journal of Flexible Manufacturing Systems 2003. https://doi.org/10.1023/A:1023993806025.
[14] Habraken, A.M.; Aksen, T.A.; Alves, J.L.; et al. Analysis of ESAFORM 2021 Cup Drawing Benchmark of an Al Alloy, Critical Factors for Accuracy and Efficiency of FE Simulations. International Journal of Material Forming 2022. https://doi.org/10.1007/s12289-022-01672-w.
[15] Hama, T.; Takamura, M.; Makinouchi, A.; Teodosiu, C.; Takuda, H. Effect of Tool-Modeling Accuracy on Square-Cup Deep-Drawing Simulation. Mater Trans, 2008 doi:10.2320/matertrans.PMRA2007885.
[16] Pereira, A.F.G.; Ruivo, M.F.; Oliveira, M.C.; Fernandes, J.V.; Prates, P.A. Numerical Study of the Square Cup Stamping Process: A Stochastic Analysis. ESAFORM 2021. https://doi.org/10.25518/esaform21.2158.
[17] Li, Y.Q.; Cui, Z.S.; Ruan, X.Y.; Zhang, D.J. CAE-Based Six Sigma Robust Optimization for Deep- Drawing Process of Sheet Metal. International Journal of Advanced Manufacturing Technology 2006. https://doi.org/10.1007/s00170-005-0121-y.
[18] Gutiérrez Regueras, J.M.; Camacho López, A.M. Investigations on the Influence of Blank Thickness (t) and Length/Wide Punch Ratio (LD) in Rectangular Deep Drawing of Dual-Phase Steels. Comput Mater Sci, 2014. https://doi.org/10.1016/j.commatsci.2014.04.024.
[19] Bayraktar, E.; Altintaş, S. Square Cup Deep Drawing Experiments. In Proceedings of the NUMISHEET ’93; 1993.
[20] Pereira, A.; Prates, P.; Parreira, T.; Oliveira, M. Influence of the Sheet Thickness Variability on the Deep Drawing of a Cylindrical Cup. In Proceedings of the Materials Research; 2024.
[21] Amaral, R. Development of Accurate Numerical Methodologies Applied to the Stamping of Advanced High Strength Steels and Experimental Validation, PhD Thesis, Uni. of Porto 2020.
[22] Menezes, L.F.; Teodosiu, C. Three-Dimensional Numerical Simulation of the Deep-Drawing Process Using Solid Finite Elements. J Mater Process Technol 2000. https://doi.org/10.1016/S09240136(99)00345-3.
[23] Sobol’, I.M. On the Distribution of Points in a Cube and the Approximate Evaluation of Integrals. USSR Computational Mathematics and Mathematical Physics 1967. https://doi.org/10.1016/0041-553(67)90144-9.
