Generative Artificial Intelligence to Optimize Lifting Lugs: Weight Reduction and Sustainability in AISI 304 Steel

Some of the critical components in industrial lifting operations are lifting lugs, elements traditionally designed with conservative approaches that prioritize safety over material efficiency, resulting in oversized designs. This study proposes an innovative methodological framework that employs Generative Artificial Intelligence (GAI) to optimize these components. The material used is AISI 304 steel, which is economical and widely available, with the goal of reducing mass without compromising structural strength. By utilizing finite element analysis (FEA) simulations in Autodesk Inventor and genetic algorithms in Autodesk Fusion 360, a comparison was made between a traditional design based on the DIN 580 standard and optimized designs generated by the software. Three manufacturing methods were also considered: additive manufacturing, three-axis milling, and casting. The results demonstrated a mass reduction of up to 91% in the additive manufacturing scenario, along with improvements in the safety factor of up to 2.765 and a notable enhancement in stress distribution uniformity. Another significant finding was the decrease in maximum displacement under dynamic loading, from 0.0189 mm (standard-based design) to 0.004 mm (generatively optimized design), which indicates increased stiffness. This methodology not only overcomes the limitations of conventional approaches but also offers flexibility to adapt to various production processes, with both economic (20% savings in material per unit) and environmental (reduced carbon footprint) benefits. The study validates the potential of GAI to optimize simple components using readily accessible materials, offering a replicable framework for sectors such as renewable energy and electric automotive applications. Future research should include experimental validations and fatigue studies to further consolidate these advances in real industrial environments.