Leveraging Materials Informatics to Uncover the Aluminum Alloy Heat Treatment Processes with Optimal Strengthening Effect and Minimal Carbon Footprint

Aluminum alloys continue to be highly relevant across a wide array of industries, including automotive, aerospace, and numerous manufacturing sectors. The increasing demand for improved physical and mechanical performance necessitates a concerted focus on optimizing heat treatment processes for aluminum alloys. Gravitating toward the mid 21st century, the concept of “materials sustainability” is gaining momentum in the materials, manufacturing and heat treating industries. Nevertheless, the community may now confront emerging regulatory frameworks that may impose constraints on processing capabilities. Therefore, it becomes imperative to integrate carbon footprint considerations into the optimization of heat treatment processes.

In this work, we introduce an approach that combines machine learning capabilities with emission analysis to identify an optimized heat treatment pathway for select 2000s, 5000s, and 6000s series aluminum alloys. The objective is to maximize yield strength, tensile strength, and elongation while minimizing the carbon footprint. Specific process recommendations were provided for selected temper conditions. Machine learning analysis was conducted using multiple regression models within the MatDash platform. The outcomes of this work contribute to the field of materials informatics and industry 4.0 by showcasing a practical application of materials informatics. The integration of machine learning and environmental considerations introduces a fresh perspective to materials processing, offering a promising solution to meet the global demand for high-performance materials in a sustainable manner.