Active disturbance rejection control of layer width in wire arc additive manufacturing based on deep learning. (July 2021)

• Record Type: Journal Article
• Authors: Wang, Yiming; Lu, Jun; Zhao, Zhuang; Deng, Wenxiang; Han, Jing; Bai, Lianfa; Yang, Xiaowei; Yao, Jianyong
• Is Part Of: Journal of manufacturing processes. Volume 67(2021)
• Page Start: 364
• Page End: 375
• Publication Date: 2021-07
• Subjects: Additive manufacturing -- Deep learning -- Semantic segmentation -- ADRC -- Feedback control; 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.2021.05.005
• Languages: English
• ISSNs: 1526-6125

Abstract

Abstract: In the process of wire arc additive manufacturing (WAAM), in order to improve the welding quality, the width of deposited layer needs to be monitored, and a feedback control strategy for the width of deposited layer must be developed. In this study, the feedback control of layer width based on melt pool vision was realized in WAAM process. The vision sensing system is used to collect the melt pool image during the welding process, and the weld width is determined according to the segmentation network EPNet designed. Finally, an active disturbance rejection control (ADRC) algorithm was designed to achieve real-time control of the melt pool width during welding. The experimental results show that the designed control algorithm can guarantee satisfactory control accuracy of melt pool width, which provides necessary strategies for online monitoring and control of weld width during WAAM.