A novel surface temperature sensor and random forest-based welding quality prediction model

Shugui Wang, Yunxian Cui, Yuxin Song, Chenggang Ding, Wanyu Ding and Junwei Yin ()
Additional contact information
Shugui Wang: Dalian Jiaotong University
Yunxian Cui: Dalian Jiaotong University
Yuxin Song: Dalian Jiaotong University
Chenggang Ding: Dalian Jiaotong University
Wanyu Ding: Dalian Jiaotong University
Junwei Yin: Dalian Jiaotong University

Journal of Intelligent Manufacturing, 2024, vol. 35, issue 7, No 16, 3314 pages

Abstract: Abstract Temperature variation directly affects the melting and solidification process of welding and has a significant impact on weld quality and mechanical properties. Accurately acquiring real-time temperature variations during the welding process is crucial for the real-time detection of welding defects. In this study, a novel thin-film thermocouple (TFTC) sensor that offers fast response, easy installation and no damage to the temperature measurement surface was designed and developed to obtain real-time temperature variations during the metal inert gas (MIG) welding process of aluminium alloys. A random forest-based weld defect identification model was established with an accuracy of 97.14% for the four typical defects of incomplete penetration, nonfusion, undercutting and collapses, which occur in the three-layer, three-pass welding process. Subsequently, a random forest model based on the temperature signal was used to analyse the hardness, bending and tensile properties of the welded joints, demonstrating the feasibility of directly using the weld temperature signal to assess the mechanical properties of welded joints.

Keywords: Thin-film thermocouple; Welding real time inspection; Random forest (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10845-023-02203-3 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joinma:v:35:y:2024:i:7:d:10.1007_s10845-023-02203-3

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10845

DOI: 10.1007/s10845-023-02203-3

Access Statistics for this article

Journal of Intelligent Manufacturing is currently edited by Andrew Kusiak

More articles in Journal of Intelligent Manufacturing from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().