| Abstract Scope |
The integration of large language models (LLMs) into materials science and manufacturing offers transformative opportunities for accelerating innovation in lightweight alloy development. We demonstrate how LLMs can automatically extract and synthesize critical information from vast unstructured texts, including alloy compositions, mechanical properties, processing parameters, and synthesis pathways, to build comprehensive datasets for machine learning applications. In materials discovery, LLMs assist in formulating hypotheses for novel lightweight aluminum- and titanium-based alloys by predicting plausible compositional spaces and estimating mechanical performance using natural language descriptions. For additive manufacturing processes, LLMs analyze technical papers, process logs, and experimental datasets to optimize build parameters, reduce defects, and enhance reliability. Case studies highlight the additive manufacturing of aerospace-grade alloys such as Ti-6Al-4V and Al-Mg systems, both of which offer excellent strength-to-weight ratios but present challenges such as residual stress, hot cracking, and surface oxidation. These results underscore the potential of LLMs to revolutionize the design and fabrication of lightweight aerospace materials by enabling faster, data-driven decision-making and accelerating innovation pipelines. |