Hybrid approaches for sheet metal formability prediction: A synergy of experimental, numerical and machine learning tools
DOI:
https://doi.org/10.15282/jmes.19.4.2025.3.0851Keywords:
Forming tests, Sheet metal, Microstructural analysis, Plasticity and damage models, Machine learningAbstract
The optimization of sheet metal forming processes is a main goal in the mechanical industry, particularly in the widely used drawing technique. However, the lack of material databases concerning metal ductility presents significant challenges. To address this issue, this study develops machine learning (ML) methods to optimize the sheet metal forming process. The Erichsen cupping tests are employed to evaluate the formability and damage characteristics of A36 sheet parts, aiming for successful drawing outcomes. These tests consider three key parameters: punch diameter, friction between tools and sheet metal, and sheet thickness. Experimental findings show that punch diameter greatly affects the Erichsen index (IE). Microstructural analysis reveals a notable impact of sheet thickness on the maximum punch force (Fmax), which is further confirmed by X-ray diffraction analysis. A finite element (FE) model based on the Johnson–Cook material law is developed to simulate the deep drawing tests. Numerical predictions show good agreement with experiments, with an average error of less than 4% for IE and 5% for Fmax. By comparing numerical and experimental results, the isotropic model demonstrates satisfying and consistent performance. Using both experimental and numerical datasets, ML models are trained to predict IE and Fmax. Among the tested algorithms (LR, RF, DT, SVR, and XGB), XGBoost (XGB) provides the most accurate predictions, with R² values of 99.60% for IE and 97.46% for Fmax. The results indicate that XGB offers a robust and efficient approach for optimizing sheet metal forming processes through accurate prediction of formability and damage indicators.
References
[1] S. Moakhar, H. Hentati, M. Barkallah, J. Louati, M. Haddar, C. Bonk, “Modeling of ductile damage: Application for bar shearing,” Materialwissenschaft und Werkstofftechnik, vol. 50, pp. 1353–1363, 2019.
[2] P. R. Ferreira Rocha, G. F. Gonçalves, G. dos Reis, R. M. Guedes, “Mechanisms of component degradation and multi-scale strategies for predicting composite durability: Present and future perspectives,” Journal of Composites Science, vol. 8, no. 6, p. 204, 2024.
[3] O. Kayode, E. T. Akinlabi, “Investigation of microstructural and mechanical properties of AA1050–AZ91D dissimilar friction stir welding,” Journal of Mechanical Engineering and Sciences, vol. 15, no. 3, pp. 8332–8343, 2021.
[4] H. Hentati, Y. Kriaa, G. Haugou, M. Haddar, “Influence of elastic waves on crack nucleation: Experimental and computational investigation of brittle fracture,” Applied Acoustics, vol. 128, pp. 45–54, 2017.
[5] G. R. Johnson, W. H. Cook, “A constitutive model and data for metals subjected to large strains, high strain rates and high temperatures,” in Proceedings: 7th International Symposium on Ballistics, The Hague, The Netherlands, 1983, pp. 541–547.
[6] G. R. Johnson, W. H. Cook, “Fracture characteristics of three metals subjected to various strains, strain rates, temperatures and pressures,” Engineering Fracture Mechanics, vol. 21, no. 1, pp. 31–48, 1985.
[7] G. Li, S. Suril, T. Özel, “Material ductile failure-based finite element simulations of chip serration in orthogonal cutting of Ti-6Al-4V,” Journal of Manufacturing Science and Engineering, vol. 141, no. 4, p. 041017, 2019.
[8] L. Y. Kou, W. Y. Zhao, X. Y. Tuo, G. Wang, C. R. Sun, “Effect of stress triaxiality on fracture failure of 6061 aluminium alloy,” Journal of Mechanical Engineering and Sciences, vol. 14, no. 2, pp. 6961–6970, 2020.
[9] L. Ben Said, H. Hentati, T. Kamoun, M. Trabelsi, “Experimental and numerical investigation of folding process: Prediction of folding force and springback,” Mathematics, vol. 11, p. 4103, 2023.
[10] L. Ben Said, M. Wali, “Accuracy of variational formulation to model thermomechanical problems and predict failure in metallic materials,” Mathematics, vol. 10, no. 19, P. 3555, 2022.
[11] H. Hentati, I. B. Naceur, W. Bouzid, A. Maalej, “Numerical analysis of damage thermo-mechanical models,” Advances in Applied Mathematics and Mechanics, vol. 7, no. 5, pp. 625–643, 2015.
[12] P. Löschner, M. K. Gupta, P. Niesłony, M. E. Korkmaz, M. Jamil, “Determination and verification of the Johnson–Cook constitutive model parameters in the precision machining of Ti6Al4V alloy,” Machines, vol. 12, no. 10, p. 709, 2024.
[13] F. S. Sorce, S. Ngo, C. Lowe, A. C. Taylor, “Quantification of coating surface strains in Erichsen cupping tests,” Journal of Materials Science, vol. 54, pp. 7997–8009, 2019.
[14] B. Ben Fraj, T. Kamoun, H. Hentati, M. Trabelsi, N. Ghazouani, M. Ahmed, “Optimization of forming force and Erichsen index using Taguchi design of experiments,” Proceedings of the Institution of Mechanical Engineers B, vol. 238, no. 9, pp. 1316–1326, 2024.
[15] R. O. Santos, A. B. Pereira, M. C. Butuc, G. Vincze, A. J. Festas, L. P. Moreira, “Development of a device compatible with a universal testing machine to perform hole expansion and Erichsen cupping tests,” Machines, vol. 8, no. 1, p. 2, 2020.
[16] D. Farioli, M. Fabrizio, E. Kaya, M. Strano, V. Mussi, “Reshaping of thin steel parts by cold and warm flattening,” International Journal of Material Forming, vol. 16, p. 35, 2023.
[17] K. A. Francy and C. S. Rao, “Experimental investigation on the effect of process variables on quality characteristics of AA2024 processed by cold extrusion,” Journal of Mechanical Engineering and Sciences, vol. 17, no. 3, pp. 9616–9628, 2023.
[18] M. Aydin, X. Wu, K. Cetinkaya, M. Yasar, I. Kadi, “Application of digital image correlation technique to Erichsen cupping tests,” Engineering Science and Technology, an International Journal, vol. 21, no. 4, pp. 760–768, 2018.
[19] M. T. Nasri, F. Abbassi, F. Ahmad, W. Makhloufi, M. Ayadi, H. Mehboob, et al., “Experimental and numerical investigation of sheet metal failure based on Johnson–Cook model and Erichsen test,” Mechanics of Advanced Materials and Structures, vol. 30, no. 7, pp. 2087–2100, 2022.
[20] W. Więckowski, J. Adamus, M. Dyner, M. Motyka, “Tribological aspects of sheet titanium forming,” Materials, vol. 16, no. 6, p. 2224, 2023.
[21] J. Xia, J. Zhao, S. Dou, X. Shen, “A novel method for friction coefficient calculation in axis-symmetric deep drawing,” Symmetry, vol. 14, no. 2, p. 414, 2022.
[22] S. Szalai, H. Csótár, D. Kurhan, A. Németh, M. Sysyn, S. Fischer, “Testing of lubricants for DIC-based forming limit diagram measurements,” Infrastructures, vol. 8, p. 32, 2023.
[23] Q. Chen, Q. Xie, Q. Yuan, H. Huang, Y. Li, “Real-time monitoring of tool wear based on a convolutional Bi-LSTM model,” Symmetry, vol. 11, no. 10, p. 1233, 2019
[24] R. Bobbili and V. Madhu, “Machine learning-based failure prediction of perforated plates under impact,” Mechanics Based Design of Structures and Machines, vol. 50, no. 7, pp. 2582–2590, 2020.
[25] B. Ben Fathallah, R. Saidi, S. Belhadi, M. A. Yallese, and T. Mabrouki, “Modelling of cutting forces and surface roughness during straight turning of Stellite-6,” Journal of Mechanical Engineering and Sciences, vol. 15, pp. 8540–8554, 2021.
[26] A. du Preez and G. A. Oosthuizen, “Machine learning in cutting processes as an enabler for smart sustainable manufacturing,” Procedia Manufacturing, vol. 33, pp. 810–817, 2019.
[27] D. Umbrello, G. Ambrogio, L. Filice, R. Shivpuri, “A hybrid finite element method–artificial neural network approach for predicting residual stresses in hard turning,” Materials & Design, vol. 29, no. 4, pp. 873–883, 2008.
[28] P. Zhang, Y. Chen, W. Xiao, D. Ping, X. Zhao, “Twin structure of lath martensite in low-carbon steel,” Progress in Natural Science: Materials International, vol. 26, no. 2, pp. 169–172, 2016.
[29] M. Slewa, “Crystalline phase change due to high-speed impact on steel,” Journal of Material Sciences & Manufacturing Research, vol. 6, no. 5, pp. 1–26, 2025.
[30] Y. Bai, X. Teng, and T. Wierzbicki, “Application of stress triaxiality in plane strain fracture testing,” J. Eng. Mater. Technol., vol. 131, no. 2, p. 021002, 2009.
[31] C. Hammami, N. Kammoun, H. Hentati, M. B. Amar, M. Haddar, “Parametric analysis of damage characterization tests of aluminium bulk material,” Journal of Mechanical Science and Technology, vol. 36, pp. 5019–5025, 2022.
[32] M. Brünig, M. Zistl, S. Gerke, “Numerical analysis of damage and fracture behavior of preloaded aluminium alloy specimens,” Metals, vol. 11, no. 3, p. 381, 2021.
[33] Y. Bao, T. Wierzbicki, “On fracture locus in equivalent strain and stress triaxiality space,” International Journal of Mechanical Sciences, vol. 46, no. 1, pp. 81–98, 2004.
[34] Y. Aiman, S. Syahrullail, and A. H. Kameil, “Tribology in metal forming and bio-lubricants: A review,” Jurnal Teknologi, vol. 86, no. 1, pp. 95–114, 2023.
[35] S. Bhandari, A. Shukla, “Prediction of responses in CNC milling using random forest regression,” Facta Universitatis, Series: Mechanical Engineering, vol. 21, no. 4, pp. 685–700, 2023.
[36] M. Kateb, S. Safarian, “Machine learning-driven predictive modeling of mechanical properties in diverse steels,” Machine Learning with Applications, vol. 20, p. 100634, 2025.
[37] S. Chakraborty, S. Bhattacharya, “Application of XGBoost as a predictive tool in CNC turning,” Reports in Mechanical Engineering, vol. 2, no. 1, pp. 190–201, 2021.
[38] L. Ben Said, T. Kamoun, J. Mars, S. Alharbi, W. Rajhi, M. Turki, M. Wali, “Data-driven deep drawing optimization: Response surface methodology and machine learning,” Journal of Engineering Research, in press, corrected proof, 2025.
[39] H. Dabiri, V. Farhangi, M. J. Moradi, M. Zadehmohamad, M. Karakouzian, “Tree-based machine learning for analysing ultimate strain of reinforcement bars,” Applied Sciences, vol. 12, no. 10, p. 4851, 2022.
[40] Z. Che, C. Peng, “Improved support vector regression for predicting mechanical properties of low-alloy steel,” Mathematics, vol. 12, no. 8, p. 1153, 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 The Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
