Type Identification and Feature Extraction of Weld Joint for Adaptive Robotic Welding

Abstract

In recent years, intelligent robotic welding has been an active research area. Vision sensors have been widely used in robotic welding systems for information collection and processing. For better welding quality and efficiency, it is necessary to achieve accurate and fast information processing and intelligent decision-making for welding robot. For weld joint information processing, most of the reported works focus on the feature extraction of weld joint concerning a specific type or a regular shape. In this chapter, an algorithm is proposed to identify joint type and extract relevant feature values by extracting three feature lines and two key turning points. Three types of weld joints are inspected and the results indicate that the algorithm is of high efficiency and robustness.