Neural network-based estimation and compensation of friction for enhanced deep drawing process control

–

Neural network-based estimation and compensation of friction for enhanced deep drawing process control

THIERY Sebastian, EL ABDINE Mazhar Zein, HEGER Jens, BEN KHALIFA Noomane

Abstract. Fluctuating process conditions, such as lubrication, can disturb the production process and lead to faulty components that have cracks or wrinkles. Real-time identification of process parameters can detect deviations in sheet forming operations and enable the process parameters to be adjusted. To increase process robustness, closed-loop control is often used to monitor and influence the material draw-in, which corresponds to the material flow and can be measured by camera systems inside the deep-drawing press. The aim of this work is to develop a control concept that can predict the optimum blank holder force by estimating the coefficient of friction based on the material draw-in of the last stroke. Using a cross-die geometry, it is shown how the material draw-in can be determined experimentally by means of a camera system and numerically by FE simulations. Finally, artificial neural network-based models are trained through simulations and are subsequently tested on a numerical case study in which the coefficient of friction is changed as a disturbance variable and must be compensated for. The widely applicable control concept has the potential to incorporate additional softsensors, for example to determine material properties, and other target variables, such as the punch force, into the optimization algorithm.

Keywords
Deep Drawing, Material Draw-In, Predictive Modelling, Friction Estimation, Closed-Loop Control, Process Monitoring and Stabilization, Particle Swarm Optimization

Published online 4/24/2024, 10 pages
Copyright © 2024 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA

Citation: THIERY Sebastian, EL ABDINE Mazhar Zein, HEGER Jens, BEN KHALIFA Noomane, Neural network-based estimation and compensation of friction for enhanced deep drawing process control, Materials Research Proceedings, Vol. 41, pp 1462-1471, 2024

DOI: https://doi.org/10.21741/9781644903131-162

The article was published as article 162 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] B. Endelt, J. Danckert, Iterative Learning and Feedback Control Applied on a Deep Drawing Process, Int. J. Mater. Form. 3 (2010) 25–28. https://doi.org/10.1007/s12289-010-0698-z
[2] J. Heingärtner, D. Bonfanti, D. Harsch, F. Dietrich, P. Hora, Implementation of a tribology-based process control system for deep drawing processes, IOP Conf. Ser.: Mater. Sci. Eng. 418 (2018) 12112. https://doi.org/10.1088/1757-899X/418/1/012112
[3] J.M. Allwood, S.R. Duncan, J. Cao, P. Groche, G. Hirt, B. Kinsey, T. Kuboki, M. Liewald, A. Sterzing, A.E. Tekkaya, Closed-loop control of product properties in metal forming, CIRP Annals. 65 (2016) 573–596. https://doi.org/10.1016/j.cirp.2016.06.002
[4] S.-W. Lo, T.-C. Yang, Closed-loop control of the blank holding force in sheet metal forming with a new embedded-type displacement sensor, Int. J. Adv. Manuf. Technol. 24 (2004) 553–559. https://doi.org/10.1007/s00170-003-1711-1
[5] K. Siegert, M. Ziegler, S. Wagner, Closed loop control of the friction force. Deep drawing process, J. Mater. Proc. Technol. 71 (1997) 126–133. https://doi.org/10.1016/S0924-0136(97)00158-1
[6] M. Traversin, R. Kergen, Closed-loop control of the blank-holder force in deep-drawing: finite-element modeling of its effects and advantages, J. Mater. Proc. Technol. 50 (1995) 306–317. https://doi.org/10.1016/0924-0136(94)01389-I
[7] B.A. Behrens, J.W. Yun, M. Milch, Closed-Loop-Control of the Material Flow in the Deep Drawing Process, AMR. 6-8 (2005) 321–328. https://doi.org/10.4028/www.scientific.net/AMR.6-8.321
[8] F. Gayubo, J.L. Gonzalez, E. de La Fuente, F. Miguel, J.R. Peran, On-line machine vision system for detect split defects in sheet-metal forming processes, in: 18th International Conference on Pattern Recognition (ICPR’06), IEEE, 2006, pp. 723–726. https://doi.org/10.1109/ICPR.2006.902
[9] J. Heger, G. Desai, M.Z. El Abdine, Anomaly detection in formed sheet metals using convolutional autoencoders, Procedia CIRP. 93 (2020) 1281–1285. https://doi.org/10.1016/j.procir.2020.04.106
[10] M. Kraft, U. Bürgel, Novel concept for measurement of global blank draw-in when deep drawing outer skin automotive components, J. Phys.: Conf. Ser. 896 (2017) 12034. https://doi.org/10.1088/1742-6596/896/1/012034
[11] S. Maier, T. Schmerbeck, A. Liebig, T. Kautz, W. Volk, Potentials for the use of tool-integrated in-line data acquisition systems in press shops, J. Phys.: Conf. Ser. 896 (2017) 12033. https://doi.org/10.1088/1742-6596/896/1/012033
[12] S. Maier, Inline-Qualitätsprüfung im Presswerk durch intelligente Nachfolgewerkzeuge, Dissertation, Technical University of Munich, TUM.University Press, München, 2018.
[13] A. Pierer, T. Wiener, L. Gjakova, J. Koziorek, Zero-error-production through inline-quality control of presshardened automotive parts by multi-camera systems, IOP Conf. Ser.: Mater. Sci. Eng. 1157 (2021) 12074. https://doi.org/10.1088/1757-899X/1157/1/012074
[14] P. Fischer, J. Heingärtner, Y. Renkci, P. Hora, Experiences with inline feedback control and data acquisition in deep drawing, Proc. Manuf. 15 (2018) 949–954. https://doi.org/10.1016/j.promfg.2018.07.401
[15] P. Fischer, J. Heingärtner, S. Duncan, P. Hora, On part-to-part feedback optimal control in deep drawing, J. Manuf. Process. 50 (2020) 403–411. https://doi.org/10.1016/j.jmapro.2019.10.019
[16] W. Homberg, B. Arian, V. Arne, T. Borgert, A. Brosius, P. Groche, C. Hartmann, L. Kersting, R. Laue, J. Martschin, T. Meurer, D. Spies, A.E. Tekkaya, A. Trächtler, W. Volk, F. Wendler, M. Wrobel, Softsensors: key component of property control in forming technology, Prod. Eng. Res. Devel. (2023). https://doi.org/10.1007/s11740-023-01227-1
[17] J. Zhao, F. Wang, Parameter identification by neural network for intelligent deep drawing of axisymmetric workpieces, J. Mater. Proc. Technol. 166 (2005) 387–391. https://doi.org/10.1016/j.jmatprotec.2004.08.020
[18] K. Manabe, M. Yang, S. Yoshihara, Artificial intelligence identification of process parameters and adaptive control system for deep-drawing process, J. Mater. Proc. Technol. 80-81 (1998) 421–426. https://doi.org/10.1016/S0924-0136(98)00121-6
[19] H. Hoffmann, M.F. Zäh, I. Faass, R. Mork, M. Golle, B. Griesbach, M. Kerschner, Automatic Process Control in Press Shops, KEM. 344 (2007) 881–888. https://doi.org/10.4028/www.scientific.net/KEM.344.881
[20] R. Mork, Qualitätsbewertung und -regelung für die Fertigung von Karosserieteilen in Presswerken auf Basis Neuronaler Netze, Dissertation, Technical University of Munich, Herbert Utz Verlag, München, 2012.
[21] C.C. Tai, J.C. Lin, The optimisation deep-draw clearance design for deep-draw dies, Int. J. Adv. Manuf. Technol. 14 (1998) 390–398. https://doi.org/10.1007/BF01304617
[22] M. Manoochehri, F. Kolahan, Integration of artificial neural network and simulated annealing algorithm to optimize deep drawing process, Int. J. Adv. Manuf. Technol. 73 (2014) 241–249. https://doi.org/10.1007/s00170-014-5788-5
[23] I. El Mrabti, A. Touache, A. El Hakimi, A. Chamat, Springback optimization of deep drawing process based on FEM-ANN-PSO strategy, Struct. Multidisc. Optim. 64 (2021) 321–333. https://doi.org/10.1007/s00158-021-02861-y
[24] D. Wang, D. Tan, L. Liu, Particle swarm optimization algorithm: an overview, Soft Comput. 22 (2018) 387–408. https://doi.org/10.1007/s00500-016-2474-6