A Weld Position Recognition Method Based on Directional and Structured Light Information Fusion in Multi-Layer/Multi-Pass Welding

Abstract

Multi-layer/multi-pass welding (MLMPW) technology is widely used in the energy industry to join thick components. During automatic welding using robots or other actuators, it is very important to recognize the actual weld pass position using visual methods, which can then be used not only to perform reasonable path planning for actuators, but also to correct any deviations between the welding torch and the weld pass position in real time. However, due to the small geometrical differences between adjacent weld passes, existing weld position recognition technologies such as structured light methods are not suitable for weld position detection in MLMPW. This paper proposes a novel method for weld position detection, which fuses various kinds of information in MLMPW. First, a synchronous acquisition method is developed to obtain various kinds of visual information when directional light and structured light sources are on, respectively. Then, interferences are eliminated by fusing adjacent images. Finally, the information from directional and structured light images is fused to obtain the 3D positions of the weld passes. Experiment results show that each process can be done in 30 ms and the deviation is less than 0.6 mm. The proposed method can be used for automatic path planning and seam tracking in the robotic MLMPW process as well as electron beam freeform fabrication process.

Welding Seam Trajectory Recognition for Automated Skip Welding Guidance of a Spatially Intermittent Welding Seam Based on Laser Vision Sensor

“…Having been extensively applied to robotic welding due to its high accuracy and non-contact, vision sensing is considered one of the most promising welding seam trajectory recognition technologies [ 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 ]. Great attention has been paid to welding seam detection methods based on structured light vision sensing [ 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 ]. Hascoet et al [ 23 ] first used a single-line laser vision sensor to detect V-shaped groove shape information, then generated a torch path based on this information, and finally proposed a welding strategy for automated welding of ships.…”

“…Li et al [ 25 ] developed a robotic welding tracking system based on a single-line laser vision sensor for the tracking of butt-jointed seams on the V-shaped groove of medium-thick plates of molten electrode gas shielded welding. Zeng et al [ 26 ] integrated fusion light and structured light information to identify the positions of multi-layer/multi-pass welding (MLMPW) seams. Zou et al [ 27 ] developed a robotic welding seam tracking system based on three-line laser vision to track the trajectory of the welding seams of complex curved overlap welding.…”

Closed-Loop Control of Droplet Transfer in Electron-Beam Freeform Fabrication

“…Heralić et al [14,15] detected the height of the deposition layer offline using optical methods, but could not achieve real-time control. Zeng et al [16][17][18] proposed a welding pass-detection method based on directional light and structure-light information fusion, aiming to tackle the problem that the structure-light laser could not obtain the welding pass information stably under the condition of strong mirror reflection. However, in the process of EBF3, the lens in front of the laser will be coated with a layer of metal vapor which makes the light transmittance drop sharply and, therefore, not meet the need of long-time stable work.…”

Online Measurement of Deposit Surface in Electron Beam Freeform Fabrication

“…Sun et al [14] achieved surface measurements on aero-engine blades based on laser triangulation. To solve for the problem that the line laser cannot stably obtain the bead information under the strong specular reflection condition, ZENG et al [15,16,17] proposed a bead detection method using uniform illumination, directional light, and structure light. However, in the manufacturing process of electron beam freeform fabrication, due to the large amount of metal vapor, the lens in front of the laser is contaminated by a layer of metal vapor during long-term operation, so that the light transmittance is drastically reduced.…”