Visual Control of Weld Defects Using Computer Vision System on FANUC Robot

Abstract

The development of Industry 4.0 technology requires the automation of technological processes. Weld quality inspections are carried out predominantly manually and can combine different types of non-destructive testing depending on the structure's intended use. It significantly slows down the manufacturing process and negates the effect of robotized welding production. At the same time, when welding on a welding robot, it is possible to use the built-in vision system, which currently in its default configuration is not initially provided to inspect welds after welding. Typically, these systems are integrated with robot arms that locate the desired parts in a box or crate and feed them to the actuators, orienting them correctly for the task at hand. It should be noted that for visual inspection of welds, external specialized computer vision systems with pattern recognition systems are usually used. Thus, the actual task is to investigate the possibility of visual inspection of weld defects specific to surface defects such as pore, crack and undercut, using the integrated FANUC iRVision 3DL system. The visual inspection of weld defects using the iRVision 3DL computer vision system installed on the FANUC robot was established. The system has the highest sensitivity to pore-type defects. The developed technique allows the quality control of the weld in an automated mode. In this case, the quality assessment should be carried out primarily using a 3D Laser Vision Sensor and a photo of the weld.