EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optimal binary thickness recognition for experimental comparative failure analysis in single point incremental forming

Mojtaba Hasanlu

Advanced Manufacturing Research · 2026

DOI: 10.21595/amr.2026.26574 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Manufacturing Research, 2026. Verfasst von Mojtaba Hasanlu. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Single point incremental forming (SPIF) has become a versatile and economical method to manufacture sheet metal components, especially for low volume and bespoke production. However, the approach is limitwed by the limited formability of materials and the development of failure modes (cracking) strongly dependent on process parameters. In this paper, a prediction framework is proposed to detect the failures in SPIF based on artificial neural network (ANN) and Non-dominated Sorting Genetic Algorithm II (NSGA-II). The experimental data were obtained from a three-axis CNC machine, using circular galvanized steel sheets, and the effects of spindle speed, feed rate and tool path movement on the thickness distribution and crack formation were investigated. The prediction task is defined as a binary classification problem (crack vs. non-crack). To enhance the performance of the model, a multi-objective optimization method is applied in which the accuracy, precision, recall, mean squared error (MSE) and feature selection are assessed simultaneously. In this multi-objective framework, the NSGA-II approach is used to determine the optimal configuration of the ANN. The results from different simulation scenarios demonstrate that the proposed NSGA-II-ANN model can achieve a desirable trade-off between the predictive accuracy and the generalization ability. This model has great potential for early prediction of thickness related failures, allowing selection of parameters prior to physical investigation. This approach provides a practical decision support tool to improve the process reliability in industrial SPIF applications.

Zitieren

APA

Hasanlu, M. (2026). Optimal binary thickness recognition for experimental comparative failure analysis in single point incremental forming. Advanced Manufacturing Research. https://doi.org/10.21595/amr.2026.26574

Vancouver

Hasanlu M. Optimal binary thickness recognition for experimental comparative failure analysis in single point incremental forming. Advanced Manufacturing Research. 2026. doi:10.21595/amr.2026.26574

BibTeX
@article{Hasanlu2026,
  author = {Hasanlu, Mojtaba},
  title = {Optimal binary thickness recognition for experimental comparative failure analysis in single point incremental forming},
  journal = {Advanced Manufacturing Research},
  year = {2026},
  doi = {10.21595/amr.2026.26574}
}
Kostenlos starten →