EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Using Machine Learning Tools in Reverse-Engineering Processes to Identify Printing Parameters in FDM-Manufactured Parts

Brian Cruz, Álvaro Rojas, Antonio José Amell, Carlos Alberto Narváez-Tovar, Marco Antonio Velasco, Everardo Barcenas, John E. Bermeo, Yamid Gonzalo Reyes, Alejandro García-Rodríguez

Journal of Manufacturing and Materials Processing · 31.03.2026 · 10 (4) · 122

DOI: 10.3390/jmmp10040122 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Manufacturing and Materials Processing, online erschienen am 31.03.2026. Verfasst von Brian Cruz und 8 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Escuela Tecnológica Instituto Técnico Central.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fused Deposition Modeling (FDM) components require accurate identification of printing parameters to ensure reliable quality assessment and support scalable reverse-engineering workflows. The objective of this study is to evaluate whether mechanical response curves obtained from tensile tests can be used to infer key manufacturing parameters, specifically part orientation, layer thickness, and infill density. Force–displacement and stress–strain data were transformed into image-based representations and classified using several individual and ensemble machine learning models. In addition, the influence of applying a moving-average filter to smooth the curve-derived images was analyzed. Ensemble methods, particularly the AdaBoost classifier, achieved the best performance across the evaluated variables, with the highest accuracy obtained from unfiltered stress–strain images. Under limited-data conditions, ensemble models consistently outperformed individual classifiers, whereas Multilayer Perceptron and Support Vector Machine models exhibited more stable but lower predictive accuracy. These results demonstrate that mechanical response curves contain relevant information about manufacturing conditions and can be used to infer FDM printing parameters. The proposed approach offers a potential non-destructive framework for parameter identification in additively manufactured components, thereby improving traceability and quality control in additive manufacturing processes.

Förderung

  • Escuela Tecnológica Instituto Técnico Central

Zitieren

APA

Cruz, B., Rojas, Á., Amell, A. J., Narváez-Tovar, C. A., Velasco, M. A., Barcenas, E., Bermeo, J. E., Reyes, Y. G., & García-Rodríguez, A. (2026). Using Machine Learning Tools in Reverse-Engineering Processes to Identify Printing Parameters in FDM-Manufactured Parts. Journal of Manufacturing and Materials Processing, 10(4), 122. https://doi.org/10.3390/jmmp10040122

Vancouver

Cruz B, Rojas Á, Amell AJ, Narváez-Tovar CA, Velasco MA, Barcenas E, et al. Using Machine Learning Tools in Reverse-Engineering Processes to Identify Printing Parameters in FDM-Manufactured Parts. Journal of Manufacturing and Materials Processing. 2026;10(4):122. doi:10.3390/jmmp10040122

BibTeX
@article{Cruz2026,
  author = {Cruz, Brian and Rojas, Álvaro and Amell, Antonio José and Narváez-Tovar, Carlos Alberto and Velasco, Marco Antonio and Barcenas, Everardo and Bermeo, John E. and Reyes, Yamid Gonzalo and García-Rodríguez, Alejandro},
  title = {Using Machine Learning Tools in Reverse-Engineering Processes to Identify Printing Parameters in FDM-Manufactured Parts},
  journal = {Journal of Manufacturing and Materials Processing},
  year = {2026},
  volume = {10},
  number = {4},
  pages = {122},
  doi = {10.3390/jmmp10040122}
}
Kostenlos starten →