An automated welding system is essential to ensure a stable and good welding quality and improve productivity in the gas metal arc welding (GMAW) process. Therefore, various studies have been conducted on the establishment of smart factories and the demand for good weldability in the fields of production and manufacturing. In shipbuilding welding and pipe welding, the uniformly generated back-bead is an important criterion for judging the mechanical properties and weldability of the welded structure, and is also an important factor that enables the realization of an automated welding system. Therefore, in this study, the welding current signal measured in real-time in the GMAW process was pre-processed by a short time Fourier transform (STFT) to obtain a time-frequency domain feature image (spectrogram). Based on this, a back-bead generation detection algorithm was developed. To accelerate the training speed of the proposed convolution neural network (CNN) model, we used non-saturating neurons and a highly efficient GPU implementation of the convolution operation. As a result of applying the proposed detection model to actual welding process, the detection accuracies with and without the back-bead regions were 95.8% and 94.2%, respectively, which confirmed the excellent classification performance for back-bead generation.
In response to global environment and fuel efficiency regulations aiming to reduce CO2 emissions, multi-material structures that use lightweight materials are currently being developed to realize the weight reduction of vehicles in automotive manufacturing. The dissimilar welding of aluminum alloy to steel has great importance, but it is still challenging due to their widely varying thermo-physical properties and the formation of intermetallic compounds. This study aimed to investigate the effect of process parameters on the wettability, mechanical properties, and microstructure in AC Pulse MIG welded joints of AA6061-T6 and galvanized steel sheets. A parametric study on torch aiming position and welding current with EN ratio variation was performed to optimize the process parameters. The result showed that the amount of metal deposition increased with EN ratio. When the EN ratio was higher, the wire feeding speed increased and the heat input process lowered. Moreover, the wetting length increased, ranging from 6.6 to 8.4 mm, and the wetting angle increased from 31.2 to 67.6°, respectively. As a result of the tensile shear test, the maximum tensile shear load of dissimilar welded joints produced at 70 A with a 20% EN ratio was approximately 8.8 kN. From the result of scanning electron microscopy with energy-dispersive spectrometry, FeAl3 IMC was observed at the joint interface, and the IMC layer thickness decreased with EN ratio at 70 A.
The IR laser welding of aluminum and copper materials for lithium-ion battery cells has limitation due to unsatisfactory joints strength caused by their low absorptivity and high re ectivity. To overcome these problems, this study has applied beam oscillation to increase the joint area of welded joints. A 1000 series aluminum alloy and oxygen-free copper sheets with a thickness of 0.5 mm were lap joints welded through 2.5 kW ber laser welding. The effect of the welding parameters of amplitudes (0, 0.2, 0.4, 0.6 mm) on weldability in welded joints has been investigated. The result con rmed that as the amplitude increases, the width at the interface increases, and penetration depth decreases. Furthermore, the maximum width at the interface could be obtained at approximately 1.23 mm under a travel speed of 100 mm/sec and amplitude of 0.6 mm. In addition, the tensile-shear load increased with higher amplitudes, and the maximum tensile-shear load was 1.1 kN in the amplitude of 0.6 mm with a travel speed of 400 mm/sec.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.