Sensing of groove gap and torch position using neural network in pulsed MIG welding

Abstract

It is important to realize intelligent welding robots to obtain a good quality of the weld. For this purpose, it is required to detect root gap of the groove and deviation from center of the gap to center of the weaving. In order to simultaneously detect those, the authors propose an arc sensor using neural networks (NN). Both arc length and wire extension are found by NN. The root edges of the groove and its center are estimated geometrically. Training data are made from experimental results. Performance of the arc sensor is examined by giving testing data to the neural networks.