Improving the laser cutting process design by machine learning techniques
In the field of manufacturing engineering, process designers conduct numerical simulation experiments to observe the impact of varying input parameters on certain outputs of the production process. The disadvantage of these simulations is that they are very time consuming and their results do not help to fully understand the underlying process. For instance, a common problem in planning processes is the choice of an appropriate machine parameter set that results in desirable process outputs. One way to overcome this problem is to use data mining techniques that extract previously unknown but valuable knowledge from simulation results. This paper presents a hybrid machine learning approach for applying clustering and classification techniques in a laser cutting planning process. In a first step, a clustering algorithm is used to divide large parts of the simulation data into groups of similar performance values and select those groups that are of major interest (e.g. high cut quality results). Next, classification trees are used to identify regions in the multidimensional parameter space that are related to the found groups. The evaluation shows that the models accurately identify multidimensional relationships between the input parameters and the output values of the process. In addition to that, a combination of appropriate visualization techniques for clustering with interpretable classification trees allows designers to gain valuable insights into the laser cutting process with the aim of optimizing it through visual exploration.
KeywordsClustering Classification tree Artificial intelligence Hybrid machine learning Data mining Manufacturing
The approaches presented in this paper are supported by the German Research Foundation (DFG) within the Cluster of Excellence “Integrative Production Technologies for High-Wage Countries” at RWTH Aachen University.
- 1.Brecher C (ed) (2012) Integrative production technology for high-wage countries. Springer, Berlin, HeidelbergGoogle Scholar
- 6.Witten IH, Frank E, Hall MA (2011) Data mining: practical machine learning tools and techniques, 3. ed. The Morgan Kaufmann series in data management systems. Kaufmann, San FranciscoGoogle Scholar
- 9.Al Khawli T, Eppelt U, Schulz W (2015) Advanced metamodeling techniques applied to multidimensional applications with piecewise responses. In: Pardalos P, Pavone M, Farinella GM et al (eds) Machine learning, optimization, and big data, vol 9432. Springer International Publishing, Cham, pp 93–104CrossRefGoogle Scholar
- 11.Fayyad UM, Piatetsky-Shapiro G, Smyth P (1996) From data mining to knowledge discovery: an overview: advances in knowledge discovery and data mining. In: Fayyad UM, Piatetsky-Shapiro G, Smyth P et al (eds). American Association for Artificial Intelligence, Menlo Park, pp 1–34Google Scholar
- 12.Gebhardt S, Hentschel B, Kuhlen T et al. (2013) Hyperslice visualization of metamodels for manufacturing processes. In: 2013 IEEE Visualization Conference (VIS): Atlanta, GA, USA, 13 Oct–18 Oct 2013. IEEEGoogle Scholar
- 13.Madić M, Radovanović M (2012) Comparative modeling of CO2 laser cutting using multiple regression analysis and artificial neural network. Int J Phys Sci 7(16):2422–2430Google Scholar
- 17.Feldkamp N, Bergmann S, Strassburger S (2015) Knowledge discovery in manufacturing simulations. In: Taylor SJ, Mustafee N, Son Y (eds) the 3rd ACM Conference, pp 3–12Google Scholar
- 19.Radovanovic M, Madic M (2011) Experimental investigations of CO2 laser cut quality: a review. Revista de Tehnologii Neconventionale 15(4):35Google Scholar
- 21.Vossen G, Schüttler J, Nießen M (2010) Optimization of partial differential equations for minimizing the roughness of laser cutting surfaces. In: Diehl M, Glineur F, Jarlebring E et al (eds) Recent advances in optimization and its applications in engineering. Springer Berlin Heidelberg, Berlin, pp 521–530CrossRefGoogle Scholar