Modeling of an artificial intelligence system to predict structural integrity in robotic GMAW of UHSS fillet welded joints

Abstract

The use of welded lightweight steels in structural applications is increasing due to the greater design possibilities offered by such materials and the lower costs compared to conventional steels. Ultra-high-strength steels (UHSS) having tensile strength of up to 1700 MPa with a high strength-to-weight ratio offer a unique combination of qualities for diverse industrial applications. For productivity and quality reasons, gas metal arc welding (GMAW) is usually utilized for welding of UHSS. However, for full penetration fillet welded joints, the need for high heat input to gain acceptable weld penetration is problematic when welding UHSS. This is due to UHSS sensitivity to heat input and possible heat-affected zone (HAZ) softening. In this paper, an attempt is made, on the basis of analysis of experimental reviews, to identify and define relationships between nonlinear weldability factors to enable creation of an artificial intelligence model to predict full penetration in robotic GMAW fillet welded joints of UHSS S960QC. Welding variables and parameters associated with GMAW are first evaluated by reviewing scientific literature. The possibility of employing an artificial neural network (ANN) to predict full penetration fillet weld characteristics is then examined. It is noted that nonlinear variables associated with the GMAW process, such as heat input, contact tip to work distance (CTWD), and torch angle, and their related parameters, which pose weldability challenges, can be modeled by applying artificial intelligence systems. Ensuring full penetration in fillet welded joints of UHSS using artificial intelligence is thus feasible. Further, an optimized control system could potentially be developed by incorporating adaptive robotic GMAW with an artificial intelligence-based system to guarantee sound structural integrity that conforms to EN ISO 5817. The paper increases awareness of welding aspects of UHSS S960QC and presents an approach for overcoming existing limits to GMAW via adaptive robotic welding and artificial intelligence systems.