Controlling 3D Weld Pool Surface by Adjusting Welding Speed Gas tungsten arc welding on pipe was used to demonstrate an alogorithm designed to predict weld pool surface at varying speeds so adjustments could be made Introduction In manual gas tungsten arc welding (GTAW) (Ref. 1), human welders can appraise the penetration status based on their observation of the welding process. Due to advantages in versatility and accessibility, human welders are often preferred in complex structure welding over mechanized or automated machines. Unfortunately, skills needed for critical welding operations typically require a long time to develop. Shortage of skilled welders has become an urgent issue the manufacturing industry is currently facing (Ref. 2). Developing an effective welder training system that can help accelerate the training process of the unskilled human welder is one of the keys to solving the skilled welder shortage issue and maintaining a competitive manufacturing industry. Recognizing the difficulty in training welders and the shortage of welding instructors, welder training systems WELDING RESEARCH have been investigated for the manufacturing industry (e.g., EWI AdvanceTrainer ™ (Ref. 3) and RealWeld Trainer™ (Ref. 4)). Recently, virtual reality (VR) has been recognized for its value in welder training (Ref. 5). Some sophisticated welder training systems with head-mounted display (HMD) have been proposed, such as ARC+ (Ref. 6), the Fronius virtual welding system (Ref. 7), and VRTEX 360® (Ref. 8). However, these systems do not employ a see-through method; instead, they apply fully simulated environment on the display. While these setups may be adequate for training purposes, they are unlikely to be able to simulate the complexity and possible variations in a real welding environment. In this study, the augmented reality (AR) technique (Ref. 9) was utilized. Augmented reality allows a user to see the real world, with virtual objects superimposed upon it. Although AR has been used in application areas including education, health care, the military, and entertainment, its application in welder training has not yet been reported (Ref. 10). The authors envision an innovative augmented reality welder training system to help accelerate the welder training process. In this teleoperated system, an unskilled welder (in virtual station) perceives a weld pool image with an auxiliary visual signal (arrow with direction and amplitude) superimposed upon, and makes speed adjustments accordingly. In a welding station, a robot arm equipped with sensors follows the human’s movement and performs the actual welding accordingly to help in training welders BY Y. K. LIU AND Y. M. ZHANG ABSTRACT Skills needed for critical manual welding operations typically require a long time to develop, and the shortage of skilled welders has become an urgent issue the manufacturing industry is currently facing. The authors envision an innovative augmented reality welder training system to help accelerate the welder training process, in which an unskilled welder perceives the weld pool image with an auxiliary visual signal (arrow with direction and amplitude) superimposed upon, and makes speed adjustment accordingly. A critical part of the envisioned training system is to determine the optimal welding speed for an unskilled welder to follow. This paper aims to establish a machine algorithm calculating the optimal welding speed given a 3D weld pool surface, referred to as “super welder.” To this end, dynamic experiments were conducted to model 3D weld pool surface characteristic parameters in response to the welding speed. A modelbased predictive control (MPC) algorithm is proposed to maintain 3D weld pool surface characteristic parameters at desired values. The proposed super welder can also be directly utilized to control 3D weld pool surface in automated welding. To demonstrate its performance, automated welding experiments are conducted for pipe GTAW. Results show the proposed super welder is able to track varying set points and is robust against different welding currents and speed disturbances. KEYWORDS • ModelBased Predictive Control • Welder Training • Augmented Reality • 3D Weld Pool • GTAW Y. K. LIU and Y. M. ZHANG (yuming.zhang@uky.edu) are with the Institute for Sustainable Manufacturing and Department of Electrical Engineering, University of Kentucky, Lexington, Ky. APRIL 2015 / WELDING JOURNAL 125-s
Welding Journal | April 2015
To see the actual publication please follow the link above