Alloy Design Based on Artificial Intelligence and Machine Learning

The emergence of generative Artificial Intelligence (AI) and large language models has significantly enhanced the potential of machine learning and AI in the field of materials design. For example, the success of AlphaFold in protein structure prediction has demonstrated the powerful capabilities of generative AI in uncovering complex relationships between material composition, structure, and performance. However, the challenges in alloy design are even more daunting, with a broader compositional space, more complex synthesis processes, and deeper intrinsic mechanisms. Coupled with the smaller experimental datasets, the application of AI in this field is even more challenging. Applying cutting-edge AI technologies to alloy design can significantly improve design efficiency, shorten experimental cycles, and reveal underlying mechanisms, which is a major challenge we face. 

This webinar discusses the application of machine learning and AI in the design of high-entropy alloys, showcasing how to efficiently develop near-zero thermal expansion high-entropy Invar alloys. The webinar introduces PDGPT, a ChatGPT-based large language model designed to streamline the acquisition of magnesium alloys Phase Diagram information with high efficiency and accuracy. Enhanced by prompt-engineering, supervised fine-tuning and retrieval-augmented generation, PDGPT leverages the predictive and reasoning capabilities of large language models along with computational phase diagram data.