Abstract
Digitisation and cross-linking in high-pressure die casting technology (HPDC) have developed greatly over the past few years. In modern HPDC cells, almost all parameters are recorded and evaluated with the aim of achieving optimum casting production in terms of quality, cycle time, and energy efficiency. However, the focus of this process data analysis and recording is particularly on the HPDC system itself and less on the periphery. This leads to possible interactions remaining undetected and avoidable casting defects continuing to occur. Therefore, the so-called tempering process, which is gaining more and more importance due to the shift towards minimum quantity spraying, is investigated in this research work. In particular, the process parameters of all tempering circuits, which change over time, are analysed with machine learning, and linked with quality-relevant machine key performance data of the HPDC machine. The resulting prediction functions generate process control options to holistically optimise casting production.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hermann C, Pries H, Hartmann G (2013), Energie- und ressourceneffiziente Produktion von Aluminiumdruckguss, Springer-Verlag Berlin Heidelberg
Ostermann F (2014), Anwendungstechnologie Aluminium, Springer-Verlag Berlin Heidelberg
Wilhelm C, Kallien LH (2018), Die deutsche Automobilindustrie als Teil des globalen Fahrzeugmarktes, Giesserei 105, Nr. 07, S. 48–55
Nogowizin B (2011), Theorie und Praxis des Druckgusses, Fachverlag Schiele & Schön GmbH, Berlin
Wissenschaftliche Gesellschaft für Produktionstechnik e.V. (2016), WGP-Standpunkt Industrie 4.0, Darmstadt
Lenz J, Wuest T, Westkämper E (2018), Holistic approach to machine tool data analytics, Journal of Manufacturing Systems, 48, S. 180–191
Chen Y (2017), Integrated and Intelligent Manufactering; Perspectives and Enablers, Engineering; 3, S. 588–595
Zaki MJ, Wagner M (2020), Data Mining and Machine Learning: Fundamental Concepts and Algorithms, Cambridge University Press
Hastie T, Tibshirani R, Friedman J (2009), The elements of statistical learning: Data Mining, Inference, and Prediction, Springer, New York
Bishop CM (2006), Pattern Recognition and Machine Learning. Springer-Verlag, New York
Witten IH, Frank E, Hall MA (2011), Data Mining Practical Machine Learning Tools and Techniques, Elsevier Inc., Amsterdam
Breiman L (2001), Random Forests, Machine Learning, 45, S. 5.32
Principe JC, Euliano NR, Lefebvre WC (1999), Neural and Adaptive Systems: Fundamentals through Simulations, John Wiley & Sons, Inc., New York
Ertel W (2016), Grundkurs Künstliche Intelligenz, Springer Fachmedien, Wiesbaden
Bankhofer U, Vogel J (2008), Datenanalyse und Statistik, GWV Fachverlage GmbH, Wiesbaden
James G, Witten D, Hastie T, Tibshirani R (2013). An introduction to statistical learning. Springer, New York
Kruse A (2000), Antragsprüfung und Kartenüberwachung von privaten Kreditkartenkunden mit künstlichen Neuronalen Netzen, Schriftenreihe innovative betriebswirtschaftliche Forschung und Praxis, Band 110, Hamburg
Crone SF (2010), Neuronale Netze zur Prognose und Disposition im Handel, Dissertation, Ph.D. Thesis, University Hamburg
Wiedmann K-P, Buchler F (2003), Neuronale Netze im Marketing-Management, Praxisorientierte Einführung in modernes Data-Mining, Springer Fachmedien Wiesbaden, Wiesbaden
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Minerals, Metals & Materials Society
About this paper
Cite this paper
Disselhoff, T., Tewes, S., Biehl, S. (2022). Adaptive Tempering in High-Pressure Die Casting Through Prediction Functions. In: Eskin, D. (eds) Light Metals 2022. The Minerals, Metals & Materials Series. Springer, Cham. https://doi.org/10.1007/978-3-030-92529-1_100
Download citation
DOI: https://doi.org/10.1007/978-3-030-92529-1_100
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92528-4
Online ISBN: 978-3-030-92529-1
eBook Packages: Chemistry and Materials ScienceChemistry and Material Science (R0)