Welding Sequence Optimization using Artificial Intelligence Techniques, an Overview

Abstract

With heightened emphasis to improve the product quality and process efficiency, the welding industry is challenged to consider innovative approaches like artificial intelligence (AI) techniques. In terms of quality, deformation and residual stress are one of the major concerns. It has been proved that the welding sequence has significant effects on deformation and lesser magnitude for residual stress. On the other hand, robot path planning is a crucial factor to efficiently weld large and complex structures. In this sense, Welding Sequence Optimization (WSO) is suitable for minimizing constraints in the design phase, reworks, quality cost and overall capital expenditure. Traditionally the welding sequence is selected by experience and sometimes a design of experiments is required. However, it is practically infeasible to run a full factorial design to find the optimal one, because, the amount of experiments grows exponentially with the number of welding beads. Virtual tools like finite element analysis (FEA) and robotics simulators allow to run corresponding optimization tasks. In this paper we overview the literature on AI techniques applied to WSO. Additionally, some relevant works that use other methods are taken into account. The reviewed works are categorized by AI technique.

Comparison between Finite Elements simulation of residual stress and Computer Vision measurements in a welding TIG process

“…Many effort is done on this topic. A recent work exploits the use of Genetic Algorithms to optimise the welding sequence [19]. In this work the coordinated use of FEA and robotic is explored and presented as low time-consuming.…”

Internet of Robotic Things in Smart Domains: Applications and Challenges

“…IoRT may include several applications in the manufacturing domain, such as spot welding and spray painting [ 60 ]. Specifically, spot welding refers to apply a welding tool to a certain object, such as a car body, at specified discrete locations [ 61 ], while spray painting involves covering a surface with an even coat of paint, pre-specifying the trajectory along which the robot will move [ 62 ]. Both applications may require real-time correction of the path to accommodate small deviations from the expected path, aiming to attain adequate production and avoid issues such as inaccuracy and collisions with both humans and robots.…”

Fabrication sequence optimization for minimizing distortion in multi-axis additive manufacturing

“…These issues have large impacts on the structural performance and dimensional accuracy, e.g., for assembly. In the related field of welding, the sequence of joining is found to significantly influence the development of residual stresses and distortion [12,13]. For instance, depending on the welding sequence, the distortion in pipes can vary by more than seven times [14].…”