Modeling of human welder response to 3D weld pool surface: Part I - Principles

Understanding and modeling of human welders' response to a three-dimensional (3D) weld pool surface may help develop intelligent welding robotic systems and train welders faster. In this first effort to model human welders' behavior, a novice welder's adjustment on the welding current as a response to the 3D weld pool surface as characterized by its width, length, and convexity is studied. In this part of the paper, the human welders' behavior is analyzed from modeling's point of view. A unique, innovative machine vision system that can measure in real time the specular 3D weld pool surface under strong arc in gas tungsten arc welding (GTAW) was used to record the weld pool surface the welder observes. Experiments were conducted to train this novice welder to gain a minimal level of operation consistency such that his response to the 3D weld pool surface was not purely random. A criterion has been proposed accordingly to quantify the response consistency. Further preparation experiments were conducted to determine the time interval during which the welder responded to the weld pool surface. The resultant time interval will be used together with data from the identification experiment, specially designed to ensure modeling accuracy, to identify the welder response model in the second part of this paper.