Artificial Neural Network Modeling for Estimating the Depth of Penetration and Weld Bead Width from the Infra Red Thermal Image of the Weld Pool during A-TIG Welding

It is necessary to estimate the weld bead width and depth of penetration using suitable sensors during welding to monitor weld quality. Infra red sensing is the natural choice for monitoring welding processes as welding is inherently a thermal processing method. An attempt has been made to estimate the bead width and depth of penetration from the infra red thermal image of the weld pool using artificial neural network models. Real time infra red images were captured using IR camera during A-TIG welding. The image features such as length and width of the hot spot, peak temperature and other features are extracted using image processing techniques. These parameters along with their respective current values are used as inputs while the measured bead width and depth of penetration are used as output of the neural network models. Accurate ANN models predicting weld bead width and depth of penetration have been developed.