In order to obtain sound welded joints in the welding of horizontal fixed pipes, it is important to control the back bead width in the first pass. However, it is difficult to obtain optimum back bead width, because the proper welding conditions change with welding position. In this paper, in order to fully automize the welding of fLxed pipes, a new method is developed to control the back bead width by monitoring the shape and dimensions of the molten pool from the reverse side. Welding was performed in a pressure vessel that can pressurize up to 0.6MPa. Artificial Neural Network is used to estimate the relations among the parameters including the weld pool shape, welding conditions and the penetration of weld. The back bead width is controlled by optimizing the welding current based on the output of the Artificial Neural Network As a result of the welding control experiments, the effectiveness of this system for the penetration control of fixed pipes is demonstrated.
Recently, automation and robotization of welding has been widely investigated. Many new intelligent welding robots incorporate some sensors, such as arc-sensor and vision sensor 1). One area of particular interest is the adaptive control of welding conditions, in which the welding arc processes and the molten pool conditions are monitored for the purpose of controlling the welding conditions in real-time. For instance, a method is being developed to control the penetration of weld, in which the shape and dimensions of the molten pool are visually monitored and welding conditions are controlled and optimized 2–6). On the other hand, in automatic butt welding of pipes, it is difficult to control the weld heat input, because the temperature of the joint area increases drastically with time during welding.
