task. To realize this envisioned training system, two critical components are required. First, human response against the visual signal input needs to be studied and an arm movement controller can then calculate the needed visual signal for a welder to track a particular welding speed (Ref. 11). Second, the needed optimal welding speed given a 3D weld pool surface should be determined. This research aims to derive a machine algorithm that outputs the optimal welding speed, referred to as “super welder.” It can also be directly utilized to perform automated robotic welding in which the 3D weld pool surface can be controlled by adjusting the welding speed. Among all the welding parameters (including welding current and speed, welding gun orientation, arc length, etc.), both welding current and speed can significantly affect the heat input and thus influence the weld pool surface geometry and weld penetration considerably. In the authors’ previous studies (Refs. 12–14), welding current was controlled where the pipe rotated and the welding gun was always on 12 o’clock. However, in many pipe welding applications, the pipe stays stationary during welding and the welding gun moves along the weld joint (Ref. 15). In this case, welders choose a predefined welding current and move the torch along the pipe. The movement of the welding torch (i.e., the welding speed) thus is controlled by the human welder as a main source to compensate for possible process variations. In Ref. 10, a steady state correlation between the welding current and required welding speed was distilled from valuable human welder knowledge. Although this correlation can generate satisfactory welds with known welding currents, it is an open-loop control with no feedback from the welding process. In this study, a closed-loop control algorithm was derived with 3D weld pool characteristic parameters as feedback information. Experimental Setup Principle of Augmented Reality Welder Training System WELDING RESEARCH 126-s WELDING JOURNAL / APRIL 2015, VOL. 94 Fig. 2 — General view of the virtualized welding system (Ref. 10). Fig. 3 — Detailed view of the 3D weld pool sensing system (Ref. 10). Fig. 1 — Schematic of the augmented reality welder training system. Table 1 — Experimental and Imaging Parameters Welding Parameters Current (A) Welding Speed (mm/s) Arc Length (mm) Argon Flow Rate (L/min) 40–50 0.5–1.5 4 11.8 Monitoring Parameters Laser Projecting Angle (deg) Laser to Weld Pool Distance (mm) Imaging Plane to Weld Pool Distance (mm) 35.5 24.7 101 Camera Parameters Shutter Speed (ms) Frame Rate (ft/s) Camera to Imaging Plane Distance (mm) 2 30 57.8
Welding Journal | April 2015
To see the actual publication please follow the link above