Vision based seam tracking system for underwater flux cored arc welding

Abstract

Manual underwater welding is usually time consuming, expensive and hard to perform because of the rigorous underwater environment. Automatic underwater welding can be performed faster at less cost and with higher quality. An automatic seam tracking system for underwater flux cored arc welding has been developed. It consists of a vision sensing module, a seam recognition module, a fuzzy controller (FC) and an X–Y travel platform. The vision sensing module can capture clear seam images during welding, successfully resolving the problem of welding arc interference during underwater flux cored arc welding. The seam recognition module filters, enhances and thresholds the seam images and then recognises the seam deviation angle with a three layer back propagation neural network. The FC outputs the control parameters according to the seam deviation angle and then controls the X–Y platform to drive the torch to the centre of the seam. In this study, three different welds were considered: a straight line, a kinked straight line and an S curved line. These welds were tracked real timely during underwater flux cored arc welding. The results show that this seam tracking system can meet the requirements of the automatic underwater flux cored arc welding.