Force data-driven machine learning for defects in friction stir welding. (August 2022)

• Record Type: Journal Article
• Authors: Guan, Wei; Zhao, Yanhua; Liu, Yongchang; Kang, Su; Wang, Dongpo; Cui, Lei
• Is Part Of: Scripta materialia. Number 217(2022)
• Publication Date: 2022-08
• Subjects: Friction stir welding -- Defect identification -- Welding force -- Machine learning; Materials -- Periodicals; Metallurgy -- Periodicals; Metalen; Legeringen; Materiaalkunde; Metals, metalworking and machinery industries; Metals; Electronic journals; 620.11
• DOI: 10.1016/j.scriptamat.2022.114765
• Languages: English
• ISSNs: 1359-6462

Abstract

Abstract: This study proposes a strategy for developing force-data-driven machine learning models to precisely predict defects and their types in friction stir welding (FSW). The characteristics of the three component forces in FSW, including traverse force ( F x ), lateral force ( F y ), and plunge force ( F Z ) are studied. The change in the force wave corresponded well with the variation in the defect. F y a v g had the best correlation with the characteristics of tunnel defects, whereas some other time-frequency features had negligible effects on the defect variation. The machine learning models built with the input of 15 force features could detect defects with an accuracy of 95.8% and classify them into tunnels and porosities with an accuracy of 98.0%. The abnormal increase in F y a v g, caused by the buildup of redundant material transported to the retreating side, was the main characteristic of force change when a defect was formed. Graphical abstract: Image, graphical abstract