IIT Madras AI alloy database has been developed to speed up the discovery of sustainable, high-performance metallic alloys for applications including electric vehicles, aerospace, renewable energy and marine infrastructure. Researchers used Large Language Models to extract and organise information from more than 10,000 scientific papers. The platform contains more than 185,000 structured records covering alloy compositions, manufacturing processes, testing conditions and over 350 material properties. It uses an automated AI pipeline and Retrieval-Augmented Generation to extract relevant information from scientific literature. The databases are publicly available through the Alloy Tattvasar platform and GitHub, allowing researchers, startups and industries to use the resources for materials innovation. The system also incorporates environmental, economic and social indicators alongside technical performance. The IIT Madras team plans to expand the platform to polymers, ceramics and composite materials, while adding information from figures and microstructural images.
IIT Madras AI Alloy Database: 1.85 Lakh Records for Research
