Weld bead geometry real-time control in gas metal arc welding processes using intelligent systems

Abstract Gas metal arc welding (GMAW) process is one of the most important in industry, so different efforts have been made to anticipate parameters convert this into a stable capable joining parts with minimum human interference. In sense, controlling essential for automated applications because properties such as weld mechanical strength are defined by composition, microstructure, and bead geometry. Nevertheless, performing automatic control guarantee quality characteristics similar expert’s mechanized systems still tricky. Nowadays, although various sensors used monitoring control, it hard detect effective options real-time identify geometry formation welds. Furthermore, even today, much more complex than parameter simultaneously or penetration using single sensor. Then, research describes two intelligence GMAW process. The first passive vision system sensor fusion that controls width height; second an active penetration. Results indicate proposed methodology can be applied external geometrical without predefined model case penetration, fuzzy controller neural network-based help adapt input variations throughout process, thus correcting instabilities under changing operating conditions.