AI-Based Optimization of Submerged Arc Welding Using AISA Algorithm

The precision of parameter selection in submerged arc welding (SAW) significantly influences weld quality, strength, and efficiency in industrial manufacturing. Artificial intelligence offers advanced tools for addressing the complex, non-linear optimization challenges in welding processes where traditional trial-and-error methods fall short. This paper introduces the Adolescent Identity Search Algorithm (AISA), an AI-based, human-inspired optimization technique, to optimize SAW parameters. Implemented in MATLAB, the algorithm was applied to minimize bead width (BW)—a critical indicator of weld quality—by refining welding current, voltage, speed, and wire feed. Comparative analysis with the Rao-1 algorithm was conducted under varying population sizes and iteration counts. Results show that AISA consistently achieved a minimum bead width of 17.06 mm with a success rate exceeding 99%, outperforming Rao-1, which recorded a minimum of 17.23 mm under the same conditions. These findings demonstrate AISA’s robustness, stability, and adaptability in parameter optimization, confirming its potential as an effective tool for enhancing manufacturing precision.