Scientific Publication

Mining data on material fatigue from scientific publications using AI – combining reasoning language models and formalized domain knowledge

News /

The scarcity and expense of fatigue data limits optimal design of components and constrains companies to a few well qualified materials when safety-critical applications are concerned. Scientists of Fraunhofer IWM together with colleagues at the University of California, Santa Barbara, have developed strategies for significantly improving the extraction of structured information from unstructured scientific literature—the largest corpus of fatigue data to date. They have published their findings on the ChemRxiv platform.