Data Analysis of Production Data for Continuous Casting of Aluminum Rolling Ingots

Abstract:

Optimizing the manufacturing process to increase the product quality is a major challenge most industry branches just like aluminum production have to face. To continuously improve the production quality, it is necessary to develop new methods to identify parameters which may influence the product quality. Influencing parameters can be found at various production steps. Production data is recorded by numerous sensors throughout the entire manufacturing process. The goal is to develop methods for analysing the sensor data from each step of the production process to effectively identify specific patterns that may indicate critical process parameters along the production chain. The work shows feature extraction methods to find characteristics in the sensor data that could affect the product-quality.

• Periodical: Key Engineering Materials (Volume 968)
• Pages: 95-101
• DOI: https://doi.org/10.4028/p-AsJ82o
• Online since: December 2023
• Authors: Manuela Schreyer*, Alexander Gerber, Steffen Neubert
• Keywords: Aluminum Rolling Ingot, Continuous Casting, Critical Process Parameters Sensors, Data Analysis, Product Quality

References

[1] J. Lee, H.-A. Kao, S. Yang, Service innovation and smart analytics for industry 4.0 and big data environment, Procedia Cirp. 16 (2014), 3–8.

DOI: 10.1016/j.procir.2014.02.001

[2] A.K. Vasudevan, R.D. Doherty, Aluminum Alloys-Contemporary Research and Applications: Contemporary Research and Applications, Elsevier (2012).

[3] B. Prillhofer, H. Antrekowitsch, H. Bottcher, P. En-Right., Nonmetallic inclusions in the secondary aluminium industry for the production of aerospace alloys. In LIGHT METALS-WARRENDALE-PROCEEDINGS, TMS (2008), 603.

[4] M.R. Berthold, C. Borgelt, F. Höppner, F. Klawonn, Guide to Intelligent Data Analysis: How to Intelligently Make Sense of Real Data, Springer London (2010)

DOI: 10.1007/978-3-030-45574-3

[5] Information on https://rstudio-pubs-static.s3.amazonaws.com/223423_ 8ca6fccca1e44939be 3f85ecbfa9598f.html

[6] D.P. Kroese, T. Brereton, T. Taimre, Z.I. Botev, Why the Monte Carlo method is so important today, WIREs Comput Stat. (2014), 386–392.

DOI: 10.1002/wics.1314

[7] R Core Team, R: A Language and Environment for Statistical Computing, R Foundation for Statistical Computing, Vienna, Austria (2022).

[8] G. Walz, Lexikon der Mathematik, first ed., Spektrum Akademischer Verlag, Mannheim/ Heidelberg, 2000.

[9] Information on https://www.spektrum.de/lexikon/physik/diskretisierung/3173.

[10] T. Hastie, R. Tibshirani, J. Friedman, The Elements of Statistical Learning, Springer (2001)

[11] M. Wand, KernSmooth: Functions for Kernel Smoothing Supporting Wand & Jones (1995), (2021) on https://CRAN.R-project.org/package=KernSmooth

[12] M. p. Wand, M. C. Jones:,Kernel Smoothing, Chapman and Hall, London (1995)

[13] W.W. Burchett, A.R. Ellis, S.W. Harrar, A. C. Bathke, Nonparametric Inference for Multivariate Data: The R Package npmv, Journal of Statistical Software (2017), 1-18

DOI: 10.18637/jss.v076.i04

[14] L. Sachs, J. Hedderich, Angewandte Statistik: Methodensammlung mit R, 8 ed., Springer Spektrum, Berlin/ Heidelberg (2018)

[15] H. Wickham, Elegant Graphics for Data Analysis, Springer-Verlag New York (2016) on https://ggplot2.tidyverse.org