Vision Algorithm for Seam Tracking in automatic Welding System

Abstract

Arc welding is an important technology for joining metals and repairing metal products in manufacturing industries. It is usually performed by a skilled worker. Due to the shortage of skilled workers and due to the hazardous and unpleasant working conditions, the automation of arc welding is gaining importance nowadays. Existing welding robots require that the dimensions, position and orientation to be programmed prior to the process. These robots suffer from an evident lack of flexibility. This paper presents an automatic welding system assisted by a machine vision system to compute the dimension, position and orientation of the workpieces. By analysing the image taken by the camera, a simple algorithm is developed to detect the dimension, position and orientation of the workpieces. The calculated data is then fed to a controller which controls the welding electrode movement. Use of machine vision system has eliminated the need to pre feed the workpiece data to the robot and hence the system is made flexible.