Machine learning algorithms for defect detection in metal laser-based additive manufacturing: A review. (March 2022)

• Record Type: Journal Article
• Authors: Fu, Yanzhou; Downey, Austin R.J.; Yuan, Lang; Zhang, Tianyu; Pratt, Avery; Balogun, Yunusa
• Is Part Of: Journal of manufacturing processes. Volume 75(2022)
• Page Start: 693
• Page End: 710
• Publication Date: 2022-03
• Subjects: Laser-based additive manufacturing -- Machine learning -- Defect detection -- Product quality -- Artificial intelligence; Production management -- Data processing -- Periodicals; Manufacturing processes -- Periodicals; Procestechnologie; Productietechniek; Production -- Gestion -- Informatique -- Périodiques; Fabrication -- Périodiques; Manufacturing processes; Production management -- Data processing; Periodicals; 670.5
• DOI: 10.1016/j.jmapro.2021.12.061
• Languages: English
• ISSNs: 1526-6125

Abstract

Abstract: Laser-based additive manufacturing (LBAM), a series of additive manufacturing technologies, has unrivaled advantages due to its design freedom to manufacture complex parts with a wide range of applications. Although advancements in LBAM processes and materials have led to increased manufacturing capabilities, the printing process's repeatability, durability, and reliability still face significant challenges. Therefore, a defect detection system for the LBAM processes is essential, as it promises to guarantee product quality and increase the efficiency of the printing process. As a practical and widely applied technology, machine learning methods have been providing novel insights into the manufacturing process, which has proven advantages for defect detection in LBAM. This paper summarizes the machine learning algorithms for defect detection in the metal LBAM processes. To have a comprehensive and systematic summary, machine learning algorithm, material type, defect type, dataset type, and algorithm accuracy for various LBAM technologies are described.