Improving the mechanical property of dissimilar Al/Mg hybrid friction stir welding joint by PIO-ANN. (15th September 2020)

• Record Type: Journal Article
• Authors: Hu, Wei; Ma, Zhongwei; Ji, Shude; Qi, Song; Chen, Mingfei; Jiang, Wenhui
• Is Part Of: Journal of materials science & technology. Volume 53(2020)
• Page Start: 41
• Page End: 52
• Publication Date: 2020-09-15
• Subjects: Hybrid friction stir welding -- Al/Mg dissimilar alloys -- Artificial neural network -- Pigeon-inspired optimization -- Ultrasonic; Metals -- Periodicals; Materials science -- Periodicals; Materials science; Metals; Periodicals; 620.1105
• DOI: 10.1016/j.jmst.2020.01.069
• Languages: English
• ISSNs: 1005-0302

Abstract

Abstract: Ultrasonic-stationary shoulder assisted friction stir welding (U-SSFSW) is a novel hybrid welding technique, which reveals promising prospect in joining Al/Mg dissimilar alloys. A thorough understanding of U-SSFSW process is imperative for the further application of this technique. Pigeon-inspired optimization (PIO) is a swarm intelligent optimization algorithm and is proposed in mathematical modeling and process optimization by artificial intelligence. In this study, PIO optimized artificial neural network (PIO-ANN) was firstly established to acquire the relationships between the inputs and output of the Al/Mg welding process by U-SSFSW technique. A reliable PIO-ANN was achieved and the joint with a tensile strength of 161 MPa was acquired under the PIO optimized parameters. This tensile strength is higher than any ever-reported results with the similar welding condition. The joint formation, microstructure, microhardness and fracture behaviors were systemically investigated based on the reported studies and the confirmation experiment of this study to explore the enhancing mechanism of U-SSFSW Al/Mg joint.