Optimal Imaging Band Selection for Laser-vision System Based on Welding Arc Spectrum Analysis

Laser-vision system (LVS), which provides the effective sensing of weld seams, is widely used in robotic welding. Due to the harsh visual noise during the welding process, the accurate real-time detection of weld seams is difficult. Since the optical propagation of the laser is affected by the arc light, the traditional passive vision system (PVS) filtering method for detecting weld seams is not applicable. This paper exploits the selection of an optimal imaging band for the LVS to eliminate the arc noise. We first measure the arc spectral distribution under various welding conditions, and we identify five spectral bands with lower arc intensity. Based on extensive investigations, we select the optimal imaging band for LVS with the lower arc intensity and optimal clarity. Extensive experiments show that our method can filter most arc noise under different conditions. To demonstrate the superiority of our approach, we compare our method with a variety of well-known commercial laser-vision systems (LVSs). This work also reveals the arc spectral distributions under different welding conditions and the influence of arc light on optical filter devices, providing guidance in enhancing the intelligence of welding manufacturing to the community.