Artificial Intelligence Design of Sustainable Aluminum Alloys: A Review

Sustainable aluminum alloys, renowned for their lower energy consumption and carbon emissions, present a critical path towards a circular materials economy. However, their design is fraught with challenges, including complex performance variability due to impurity elements and the time-consuming, cost-prohibitive nature of traditional trial-and-error methods. The high-dimensional parameter space in processing optimization and the reliance on human expertise for quality control further complicate their development. This paper provides a comprehensive review of Artificial Intelligence (AI) techniques applied to sustainable aluminum alloy design, analyzing their methodologies and identifying key challenges and optimization strategies. We review how AI methods such as knowledge graphs, evolutionary algorithms, and machine learning transform conventional processes into efficient, data-driven workflows, thereby enhancing development speed and precision. The review explicitly highlights existing bottlenecks, including insufficient data quality and standardization, the complexity of cross-scale modeling, and the need for industrial coordination. We conclude that AI holds immense potential to drive the recycled aluminum industry toward a more sustainable and intelligent future. Future research is poised to leverage generative AI, autonomous experimental platforms, and blockchain for improved life-cycle management, while also focusing on developing physics-informed models and establishing standardized data ecosystems.