Recently, not only robotic welders have replaced human welders in many welding applications, but also reasonable seam tracking systems are commercially available. However, fully adequate process control systems have not been developed due to a lack of reliable sensors and mathematical models that correlate welding parameters to the bead geometry for the automated welding process. Especially, real-time quality control in automated welding process is an important factor contributing to higher productivity, lower costs and greater reliability of the bead geometry. In this paper, on-line empirical models with experimental results are proposed in order to be applicable for the prediction of bead geometry. For development of the proposed predicting model, an attempt has been made to apply for a several methods. For the more accurate prediction, the prediction variables are first used to the surface temperatures measured using infrared thermometers with the welding parameters (welding current, arc voltage, CTWD and gas flow rate) because the surface temperature are strongly related to the formation of the bead geometry. And the developed model has been carried out a learning each time data acquired.