Real-Time Defect Detection in Robotic Welding of Aluminum 5083 Integrating Predictive Analytics and Machine Learning
ASME Letters in Translational Robotics · 2026
DOI: 10.1115/1.4072728 ↗Kurz gefasst
Fachartikel in der Zeitschrift ASME Letters in Translational Robotics, 2026. Verfasst von Aman Nohwal und 3 weiteren Autor:innen. Die Arbeit nennt 18 Literaturangaben.
Abstract (Originalsprache)
Predictive analytics is applied to robotic welding cells to enhance the quality and reliability of aluminum 5083 welds, an alloy known for its high strength, corrosion resistance, and weldability. This research focuses on identifying and characterizing welding defects such as porosity and lack of fusion by analyzing the influence of key process parameters, including wire feed speed, torch speed, and gas flowrate, which are varied during experimentation. Advanced robotic metal inert gas welding systems are employed with real-time current data acquisition through an Open Platform Communications Unified Architecture server. Statistical analysis of signal features, root mean square value, standard deviation, skewness, kurtosis, and peak-to-peak value is performed to detect defects. Machine learning models, particularly artificial neural networks, are utilized to predict weld bead quality, with cross-validation ensuring model robustness and accuracy. Results indicate that the precise monitoring and analysis of process parameters can effectively identify defect patterns and improve understanding of weld quality. The integration of real-time monitoring and machine learning demonstrates significant potential for refining welding processes and advancing industrial production engineering.
Zitieren
APA
Nohwal, A., Kaler, N., Aravindan, S., & Jha, S. (2026). Real-Time Defect Detection in Robotic Welding of Aluminum 5083 Integrating Predictive Analytics and Machine Learning. ASME Letters in Translational Robotics. https://doi.org/10.1115/1.4072728
Vancouver
Nohwal A, Kaler N, Aravindan S, Jha S. Real-Time Defect Detection in Robotic Welding of Aluminum 5083 Integrating Predictive Analytics and Machine Learning. ASME Letters in Translational Robotics. 2026. doi:10.1115/1.4072728
BibTeX
@article{Nohwal2026,
author = {Nohwal, Aman and Kaler, Narendra and Aravindan, Sivanandam and Jha, Sunil},
title = {Real-Time Defect Detection in Robotic Welding of Aluminum 5083 Integrating Predictive Analytics and Machine Learning},
journal = {ASME Letters in Translational Robotics},
year = {2026},
doi = {10.1115/1.4072728}
}
EUVIMED