A model-free adaptive control of welding pool dynamics during arc welding

Abstract

Arc welding process is characterized as nonlinear, time varying, and uncertain. So it is very difficult to design an effective control scheme by conventional modeling and control methods. Quality control of arc welding process is the key component in robotic welding system. This paper addresses model-free adaptive control with functional reinforce of Al alloy weld pool dynamics during pulsed gas tungsten arc welding (GTAW). This control method only needs the observed input output data and also has functional reinforce to improve the performance of the controller. The shape and size parameters for the weld pool are used to describe the weld pool geometry. The welding current is selected as the control variable, and the backside width of weld pool is selected as the controlled variable. To achieve the goal of full penetration and fine weld seam formation, a model-free adaptive controller with functional reinforce is designed for control of the maximum backside width. This controller of weld pool is independent on mathematic model. Numerical simulations confirmed that the developed control system is effective in achieving the desired fusion state.