Realtime Prediction of Self-Pierce Riveting Joints - Prognosis and Visualization Based on Simulation and Machine Learning

Abstract:

Machine learning is used in many fields nowadays to predict events, be it a pure classification or the prediction of certain values. Thus, these methods are also increasingly used in mechanical joining technology, for example for the prediction of joint strengths, in the classification of defects and rivet head positions or in the prediction of discrete result values such as interlock. This paper further shows how the complete joint contour including the output of stresses, strains and damage can be predicted and visualized in real time for self-piercing riveting with semi-tubular rivet. First, classical sampling is carried out in experiments with steel and aluminum sheets of different types and thicknesses. These are used as a basis for the qualification of the numerical simulations. For this validation experiments and simulations are compared via joint contour and force curves. For the simulations validated in such way several tool variants are carried out in variation calculations for each material-thickness combination. The simulation meshes of the thus generated database are standardized with respect to comparability (same number of nodes) and a data reduction is performed. After testing different approximation approaches, the best possible results are predicted and can be visualized in the developed software demonstrator.

• Periodical: Key Engineering Materials (Volume 926)
• Pages: 1479-1488
• DOI: https://doi.org/10.4028/p-5fjp40
• Online since: July 2022
• Authors: Tobias Falk*, Christian Schwarz, Welf Guntram Drossel
• Keywords: Machine Learning, Prediction, Self-Pierce Riveting, Simulation

References

[1] Drossel, W.-G.; et al: Unerring Planning of Clinching Processes through the Use of Mathematical Methods, KEM 611–612, 1437–1444, (2014).

DOI: 10.4028/www.scientific.net/kem.611-612.1437

[2] Jäckel, M.; et al: Gathering of Process Data through Numerical Simulation for the Application of Machine Learning Prognosis Algorithms. Procedia Manufacturing, 47, 608-614, (2020).

DOI: 10.1016/j.promfg.2020.04.186

[3] Thoms, V.; Kalich J.: Prozessvorhersage beim Stanznieten mit neuronalen Netzen, EFB-Forschungsbericht, Nr. 179, Hannover, (2002).

[4] Tassler, T.; et al: Verbesserung der Vorhersagegenauigkeit von Metamodellen. Forschung im Ingenieurwesen 81-4, 373 – 382, (2017).

DOI: 10.1007/s10010-017-0215-3

[5] Jäckel, M.; et al: Gathering of Process Data through Numerical Simulation for the Application of Machine Learning Prognosis Algorithms, Procedia Manufacturing 47: 608-614, (2020).

DOI: 10.1016/j.promfg.2020.04.186

[6] Hahn, O.; Klemens, U.: Fügen durch Umformen, Nieten und Durchsetzfügen-Innovative Verbindungsverfahren für die Praxis, Studiengesellschaft Stahlanwendung, (1996).

[7] DVS/EFB 3410: Merkblatt Stanznieten-Überblick, DVS-Verlag, Düsseldorf, (2018).

[8] Breckweg, A.: Automatisiertes und prozessüberwachtes Radialclinchen höher-fester Blechwerkstoffe. Dissertation. Stuttgart (2006).

[9] Schromm, T.; Diewald, F.; Grosse, C.: An attempt to detect anomalies in car body parts using machine learning algorithms, IEEE Transactions on Systems, Man and Cybernetics 9-1, 62–66, (2019).

[10] Lambiase, F.; Di Ilio, A.: Optimization of the Clinching Tools by Means of Integrated FE Modeling and Artificial Intelligence Techniques. Procedia CIRP 12, 163–168, (2013).

DOI: 10.1016/j.procir.2013.09.029

[11] Oh, S.; et al: Deep-Learning-Based Predictive Architectures for Self-Piercing Riveting Process, IEEE Access 8, 116254–116267, (2020).

DOI: 10.1109/access.2020.3004337

[12] Karathanasopoulos, N.; Pandya, K. S.; Mohr, D.: Self-piercing riveting process: Prediction of joint characteristics through finite element and neural network modeling. Journal of Advanced Joining Processes 3, 100040, (2021).

DOI: 10.1016/j.jajp.2020.100040

[13] Tan, Y.: Vorhersage des Tragverhaltens von Clinchverbindungen unter quasi-statischer Scherzugbelastung mittels eines neuronalen Netzes, Universität Paderborn Dissertation, (2003).

[14] Lin, J.; et al: Prediction of cross-tension strength of self-piercing rivited joints using finite element simulation and XGBoost algorithm, Chinese Journal of Mechanical Engineering 34.1, (2021).

DOI: 10.1186/s10033-021-00551-w

[15] Wanner, M.-C.; et al: Numerische und experimentelle Untersuchung von Setzprozess-unregelmäßigkeiten bei Schließringbolzensystemen, Ergebnisse eines Forschungsvorhabens der industriellen Gemeinschaftsforschung (IGF), EFB-Forschungsbericht 426, Hannover (2015).

[16] Grimm, T.; et al: Technologies for the mechanical joining of aluminum die castings, AIP Conference Proceedings, Vol. 2113, No. 1, AIP Publishing LLC, (2019).

[17] Kraus, C.; et al: Development of a new self-flaring rivet geometry using finite element method and design of experiments, Procedia Manufacturing 47, pp.383-388, (2020).

DOI: 10.1016/j.promfg.2020.04.295

[18] Raschka, S.: Python machine learning – Unlock deeper insights into machine learning with this vital guide to cutting-edge predictive analytics, Packt publishing ltd, (2015).

[19] Pearson, K.: On lines and planes of closest fit to systems of points in space, Philosophical Magazin 2, 559-572, (1901).

[20] Hotelling, H.: Analysis of a complex of statistical variables into principal components, Journal of Educational Psychology 24 6, p.417–441, (1933).

DOI: 10.1037/h0071325

[21] Jolliffe, I.: Principal component analysis, Encyclopedia of statistics in behavioral science, (2005).

[22] Jackson, J. E.: Principal Components and Factor Analysis: Part I—Principal Components. Journal of Quality Technology 12-4, p.201–213, (1980).

DOI: 10.1080/00224065.1980.11980967

[23] Jäckel, M.; et al: Process-oriented Flow Curve Determination at Mechanical Joining, Procedia Manufacturing, Vol.47, 368-374, (2020).

DOI: 10.1016/j.promfg.2020.04.289

[24] McKay, M. D.; Beckman, R. J.; Conover, W. J.: A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code, Technometrics 21 2, p.239, (1979).

DOI: 10.2307/1268522

[25] Cockroft, M. G.; Latham, D. J.: Ductility and Workability of Metals, Journal of the Institute of Metals 96, 33-39, (1968).

[26] Clarkson, J. A., & Erdös, P.: Approximation by polynomials, Duke Mathematical Journal, 10(1), 5-11, (1943).