scholarly journals Automatic penetration bead welding technology in horizontal position using weld pool image recognition

2021 ◽  
Vol 39 (4) ◽  
pp. 309-321
Author(s):  
Keita OZAKI ◽  
Naohide FURUKAWA ◽  
Akira OKAMOTO ◽  
Keito ISHIZAKI ◽  
Yuji KIMURA ◽  
...  
2020 ◽  
Vol 404 ◽  
pp. 68-76
Author(s):  
Philipp Warnecke ◽  
Thomas Seefeld

Highly conductive copper alloys are used for several tools in casting and welding technology. In order to improve the poor wear resistance of these alloys, metal matrix composite (MMC) layers were generated by laser melt injection (LMI). During LMI, a weld pool is induced on a substrate by a laser beam and a wear-resistant filler material is injected into this weld pool by a powder nozzle. In contrast to laser cladding, the filler material remains in the solid state and the substrate works as matrix material. Thereby, specific material properties of the substrate - e.g. a high thermal conductivity - can be provided not only in the core of the part but also within the coating. Fused tungsten carbide (FTC) was used as reinforcing material. It was shown that homogeneous MMC layers out of the copper alloy Hovadur® CNCS and FTC can be produced by laser melt injection. High process velocities of 8.75 m/min could be reached. For assessing the wear resistance, oscillating wear tests with counterparts made of steel were carried out and the wear height and the wear volume were determined. The particle reinforcement lead to a significant increase in wear resistance. Only one wear mechanism - abrasion - was identified.


Author(s):  
Zhenmin Wang ◽  
Haoyu Chen ◽  
Qiming Zhong ◽  
Sanbao Lin ◽  
Jianwen Wu ◽  
...  
Keyword(s):  

2014 ◽  
Vol 488-489 ◽  
pp. 111-114
Author(s):  
Bo Chen ◽  
Ji Cai Feng

CO2welding technology is widely used nowadays, because the work environment is very bad, weld automation technology is urgently needed. To control the weld quality automatically, weld sensors should be first used to obtain information that could reflect the weld quality. This paper used arc and visual sensors to obtain the electrical and weld pool image of CO2weld process, and signal processing method was used to obtain the signal features of the information. Then neural network method was used to model the process, experiment results showed that the method could effectively predict the weld seam forming.


Sign in / Sign up

Export Citation Format

Share Document