Multi-Response Optimization of Robotic Welding Parameters Using a Taguchi-Based Random Forest Model for Dissimilar Joining Materials
Engineering, Technology & Applied Science Research · 06.10.2025 · 15 (5) · 27237-27243
DOI: 10.48084/etasr.12124 ↗Kurz gefasst
Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 06.10.2025. Verfasst von Amin Lawong und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Multi-Response Optimization (MRO) is critical for resolving conflicting criteria in robotic welding processes, particularly in dissimilar metal joining, where optimizing weld hardness typically conflicts with minimizing heat input. This study aims to optimize Gas Metal Arc Welding (GMAW) parameters for joining malleable ductile cast iron with AISI 1045 steel. A novel hybrid methodology is proposed, integrating the Taguchi experimental design (L9 orthogonal array), a multi-output Random Forest regression model, and a weighted scoring function. Results quantitatively identified optimal parameters (current = 135 A, voltage = 27.5 V, travel speed = 36 cm/min), achieving hardness of 203.85 HV and heat input of 6.27 kJ/cm, with a normalized score of 0.9061. Qualitative expert evaluation validated the approach's practicality and accuracy. The findings highlight the benefits of integrating classical experimentation with Artificial Intelligence (AI)-driven modeling to facilitate precise, data-driven decision-making in manufacturing optimization.
Zitieren
APA
Lawong, A., Nampromma, S., Sudsuansee, T., & Sergsiri, S. (2025). Multi-Response Optimization of Robotic Welding Parameters Using a Taguchi-Based Random Forest Model for Dissimilar Joining Materials. Engineering, Technology & Applied Science Research, 15(5), 27237-27243. https://doi.org/10.48084/etasr.12124
Vancouver
Lawong A, Nampromma S, Sudsuansee T, Sergsiri S. Multi-Response Optimization of Robotic Welding Parameters Using a Taguchi-Based Random Forest Model for Dissimilar Joining Materials. Engineering, Technology & Applied Science Research. 2025;15(5):27237-27243. doi:10.48084/etasr.12124
BibTeX
@article{Lawong2025,
author = {Lawong, Amin and Nampromma, Surachai and Sudsuansee, Thaithat and Sergsiri, Supakit},
title = {Multi-Response Optimization of Robotic Welding Parameters Using a Taguchi-Based Random Forest Model for Dissimilar Joining Materials},
journal = {Engineering, Technology & Applied Science Research},
year = {2025},
volume = {15},
number = {5},
pages = {27237--27243},
doi = {10.48084/etasr.12124}
}
EUVIMED