Studying the Effect of Short Carbon Fiber on Fused Filament Fabrication Parts Roughness via Machine Learning

García-Collado, Alberto; Romero-Carrillo, Pablo Eduardo; Dorado-Vicente, Rubén; Gupta, Munish Kumar

doi:10.1089/3DP.2021.0304

Studying the Effect of Short Carbon Fiber on Fused Filament Fabrication Parts Roughness via Machine Learning

1 Department of Mechanical and Mining Engineering, University of Jaén, EPS de Jaén, Jaén, Spain.
2 Faculty of Mechanical Engineering, Opole University of Technology, Opole, Poland.

Revista:

3D Printing and Additive Manufacturing

ISSN: 2329-7662, 2329-7670

Año de publicación: 2022

Volumen: 0

Número: 0

Tipo: Artículo

DOI: 10.1089/3DP.2021.0304 GOOGLE SCHOLAR Acceso abierto editor

Otras publicaciones en: 3D Printing and Additive Manufacturing

Objetivos de desarrollo sostenible

Resumen

Along with the characteristic staircase effect, short carbon fibers, added to reinforce Fused Filament Fabrication parts, can significantly worsen the resulting surface finishing. Concerning this topic, the present work intends to improve the existing knowledge by analyzing 2400 measurements of arithmetic mean roughness Ra corresponding to different combinations of six process parameters: the content by weight of short carbon fibers in polyethylene terephthalate glycol (PETG) filaments f, layer height h, surface build angle θ, number of walls w, printing speed s, and extruder diameter d. The collected measurements were represented by dispersion and main effect plots. These representations indicate that the most critical parameters are θ, f, and h. Besides, up to a carbon fiber content of 12%, roughness is mainly affected by the staircase effect. Hence, it would be likely to obtain reinforced parts with similar roughness to unreinforced ones. Different machine learning methods were also tested to extract more information. The prediction model of Ra using the Random Forest algorithm showed a correlation coefficient equal to 0.94 and a mean absolute error equal to 2.026 μm. In contrast, the J48 algorithm identified a combination of parameters (h = 0.1 mm, d = 0.6 mm, and s = 30 mm/s) that, independent of the build angle, provides a Ra < 25 μm when using a 20% carbon fiber PETG filament. An example part was printed and measured to check the models. As a result, the J48 algorithm correctly classified surfaces with low roughness (Ra < 25 μm), and the Random Forest algorithm predicted the Ra value with an average relative error of less than 8%.

Referencias bibliográficas

10.1177/1687814020925232
10.1007/s00366-015-0407-0
Pérez M, (2021), Handbooks in Advanced Manufacturing, pp. 369
4. Nasr ESA, Al-Ahmari A, Moiduddin K. CAD issues in additive manufacturing. In: Saleem Hashmi, Gilmar Ferreira Batalha, Van Tyne CJ, Yilbas BS, (eds.), Comprehensive Materials Processing. Volume 10: Advances in Additive Manufacturing and Tooling. Oxford: Elsevier, 2014; pp. 375–399.
10.1108/13552540310502185
10.1007/978-981-13-8281-9
10.3390/ma11081382
10.1016/j.jmatprotec.2017.07.019
10.1016/j.jmapro.2018.11.023
10.1016/j.jmatprotec.2016.10.003
11. Kam M, Ipekci A, Sengul O. Investigation of the effect of FDM process parameters on mechanical properties of 3D printed PA12 samples using Taguchi method. J Thermoplast Compos Mater 2021. https://doi.org/10.1177/08927057211006459
10.3390/polym11101581
10.1016/j.polymertesting.2018.05.020
10.1016/j.compositesb.2018.02.012
10.1007/s00170-012-4687-x
10.1108/RPJ-06-2015-0075
Bhandari S, (2019), Addit Manuf, 30, pp. 100922
10.1016/j.polymertesting.2020.106925
10.1016/j.compscitech.2014.10.009
10.1016/j.compositesb.2020.108175
10.1016/j.compositesb.2017.05.013
10.1007/s10845-020-01715-6
10.1007/s11837-020-04155-y
24. Witten IH, Frank E, Hall MA, et al. Data Mining: Practical Machine Learning Tools and Techniques. 4th ed. Cambridge: Morgan Kaufmann, 2017; CP1–CP621 p.
10.1016/j.eng.2019.04.012
Wang C, (2020), Addit Manuf, 36, pp. 101538
10.3390/ma12162574
Delli U, (2018), Procedia Manuf, 26, pp. 5
10.3390/polym12040840
Aoyagi K, (2019), Addit Manuf, 27, pp. 353
10.1007/s00170-015-7576-2
10.1007/s12541-016-0185-7
10.1243/09544054JEM724
35. Jiju A. Design of Experiments for Engineers and Scientists. 2nd ed. London: Elsevier, 2014.
36. Farin G. Curves and Surfaces for CAGD. 5th ed. San Diego: Academic Press, 2002.
Bustillo A, (2016), J Comput Des Eng, 3, pp. 11
10.1016/j.jmsy.2018.06.004
10.1007/s00170-021-07300-2
10.1007/s00170-016-9695-9
10.1080/0951192X.2016.1247991
10.1016/j.polymertesting.2020.106860
10.1038/srep43401
10.1080/00207543.2018.1505058