Abstract
The prediction of workpiece quality in process planning, using machine learning models, is a common-researched topic. Until now, trained models were static and could not update themselves with new data. However, this aspect is crucial when considering the continuously changing manufacturing circumstances in regards to new process parameters, materials, and workpiece geometries. In addition, repeatedly training process models with an extended mixed dataset decreases the prediction quality due to the increased data divergence. This paper presents an approach to automatically generate sub-models, which maintain the prediction quality even if novel data is considered. The challenge is to define the amount and content of these sub-models through clustering. Tool grinding experiments will be conducted with different process parameters, materials, and workpiece geometries in order to obtain a divergent dataset. Subsequently, cluster approaches are compared to obtain dynamic growing models, which enable optimized planning for a more resource efficient process. Finally, the method will be generalized in order to ensure a process-independent usage.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Backhaus, K., Erichson, B., Plinke, W., Weiber, R.: Multivariate Analysemethoden (14. Aufl.). Springer, Berlin, Heidelberg (2016). https://doi.org/10.1007/978-3-662-46076-4
Brecher, C., Ochel, J., Lohrmann, V., Fey, M.: Maschinelles Lernen zur Prädiktion der Bauteilqualität. Zeitschrift für wirtschaftlichen Fabrikbetrieb 115(11), 834–837 (2020)
Brecher, C., Lohrmann, V., Wiesch, M., Fey, M.: Clustering zur Bestimmung von Werkzeugverschleiß. Zeitschrift für wirtschaftlichen Fabrikbetrieb 117(4), 218–223 (2022)
Brinksmeier, E., et al.: Advances in modeling and simulation of grinding processes. CIRP Ann. 55(2), 667–696 (2006)
Deichmueller, M., et al.: Determination of static and dynamic deflections in tool grinding using a dexel-based material removal simulation. In: CIRP 2nd International Conference Process Machine Interactions 2010. Vancouver, Canada (2010)
Denkena, B., Dittrich, M.-A., Böß, V., Wichmann, M., Friebe, S.: Self-optimizing process planning for helical flute grinding. Prod. Eng. Res. Devel. 13(5), 599–606 (2019)
Denkena, B., Dittrich, M.-A., Lindauer, M., Mainka, J., Stürenburg, L.: Using AutoML to optimize shape error prediction in milling processes. MIC Procedia 20(1), 160–165 (2020)
Dittrich, M.-A., Uhlich, F.: Self-optimizing compensation of surface deviations in 5-axis ball-end milling based on an enhanced description of cutting conditions. CIRP J. Manuf. Sci. Technol. 31(1), 224–232 (2020)
Dittrich, M.-A.: Autonome Werkzeugmaschinen - Definition, Elemente und technische Integration. Habilitation, Gottfried Wilhelm Leibniz Universität Hannover (2021)
Frades, I., Matthiesen, R.: Overview on techniques in cluster analysis. In: Bioinformatics Methods in Clinical Research, pp. 81–107. Humana Press, Totowa, USA (2010)
Königs, M., Wellmann, F., Wiesch, M., Epple, A., Brecher, C.: A scalable, hybrid learning approach to process-parallel estimation of cutting forces in milling applications. In: WGP-Jahreskongress Aachen 2017, vol. 7, pp. 425–432. Apprimus, Aachen (2017)
Krüger, J., Fleischer, J., Franke, J., Groche, P.: WGP-Standpunkt KI in der Produktion. Wissenschaftliche Gesellschaft für Produktionstechnik WGP e.V. (2019)
Möhring, H.-C., Wiederkehr, P., Erkorkmaz, K., Kakinuma, Y.: Self-optimizing machining systems. CIRP Ann. 69(2), 740–763 (2020)
Myttenaere, A.D., Golden, B., Le Grand, B., Rossi, F.: Mean Absolute Percentage Error for regression models. Neurocomputing 192, 38–48 (2016)
Ochel, J., Fey, M., Brecher, C.: Semantically meaningful segmentation of milling process data. In: Behrens, B.A., Brosius, A., Drossel, W.G., Hintze, W., Ihlenfeldt, S., Nyhuis, P. (eds.) Production at the Leading Edge of Technology, pp. 319–327. WGP 2021. LNPE. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-78424-9_36
Uhlich, F.: Lernende Prozesssimulation für die Prognose und Kompensaiton von Formabweichungen in der Einzelteilfertigung. Dr.-Ing. Diss., Gottfried Wilhelm Leibniz Universität Hannover (2022)
Ward, J.H.: Hierarchical grouping to optimize an objective function. J. Am. Stat. Assoc. 58(301), 236–244 (1963)
Acknowledgement
The authors would like to thank the German Research Foundation (DFG) for funding the project LearnWZS - Learning process adaptation for tool grinding (number 445811009), which enables this investigation. Furthermore, the authors thank the Sieglinde-Vollmer Foundation for supporting this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Denkena, B., Wichmann, M., Wulf, M. (2024). Clustering of Learning Sub-models for Quality Prediction in a Resource-Efficient Tool Grinding Process. In: Bauernhansl, T., Verl, A., Liewald, M., Möhring, HC. (eds) Production at the Leading Edge of Technology. WGP 2023. Lecture Notes in Production Engineering. Springer, Cham. https://doi.org/10.1007/978-3-031-47394-4_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-47394-4_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47393-7
Online ISBN: 978-3-031-47394-4
eBook Packages: EngineeringEngineering (R0)