Machine Learning for Optimizing Technological Properties of Wood Composite Filament-Timberfill Fabricated by Fused Deposition Modeling
- 63 Downloads
This work evaluates the applicability of machine learning (ML) tools in additive manufacturing (AM) processes. One of the most employed AM techniques is fused deposition modeling (FDM), where a part is created from a computer-aided design (CAD) model using layer-by-layer deposition of a feedstock plastic filament material extruded through a nozzle. Owing to the large number of parameters involved in the manufacturing process, it is necessary to identify printing parameters ranges to improve mechanical properties as yield and ultimate strength. In that sense, ML has proven to be a reliable tool in engineering and materials processing, where hybrid ML algorithms are the best alternative since one-part acts as a forecaster, and the other part acts as an optimizer. To evaluate the performance of wood composite filament fabricated by FDM a uniaxial tensile test was performed at room temperature. The experimental procedure was carried out with a design of experiments of four factors at three levels, where the statistical significance of layer thickness, fill density, printing speed and raster angle was obtained as well as their interactions. Furthermore, ML’s algorithm accuracy was explored, where a neuro-fuzzy system (ANFIS) was trained and tested with the experimental data. Through the development of the present work, it is concluded that layer thickness and raster angle play a significant role in FDM of a wood composite filament where fibers presence increases the layer thickness accelerating the FDM process.
KeywordsMachine learning ANFIS Additive Manufacturing Fused deposition modeling Wood composite filament
This study has been completed under the financial support of the State Secretariat for higher education, science, technology and innovation (SENESCYT) grant number ARSEQ-BEC-000329-2017 and the Research Center for Nanotechnology and Advanced Materials (CIEN-UC).
- 13.Subramaniam, S.R., et al.: 3D printing: overview of PLA progress. In: AIP Conference Proceedings, vol. 2059, January 2019Google Scholar
- 22.Siddique, N., Adeli, H.: Computational Intelligence: Synergies of Fuzzy Logic (2013)Google Scholar
- 29.Valčić, M., Antonić, R., Tomas, V.: ANFIS based model for ship speed prediction. Brodogradnja 62(4), 373–382 (2011)Google Scholar
- 30.Huang, C.-W., Baron, L., Balazinski, M., Achiche, S.: Comprehensive model optimization in pulp quality prediction: a machine learning approach. PeerJ PrePrints 5, 1–18 (2017)Google Scholar
- 39.Dillard, D.A.: Physical properties. In: Handbook of Adhesion Technology, 2nd edn, vol. 1–2, pp. 433–457 (2018)Google Scholar
- 40.American Society for Testing and Materials. D638 − 14 Standard Test Method for Tensile Properties of Plastics. Standard Test Method for Tensile Properties of Plastics, p. 17 (2014)Google Scholar
- 41.Motaparti, K.P., Leu, M.C., Chandrashekhara, A.K., Dharani, L.R.: Effect of build parameters on mechanical properties of Ultem 9085 parts by fused deposition modeling. In: Solid Freeform Fabrication. 2016 Proceedings of 26th Annual International Solid Freeform Fabrication. 2016 Proceedings of 27th Annual International Solid Freeform Fabrication Symposium – An Additive Manufacturing Conference, pp. 964–977 (2016)Google Scholar