62459 2024 eng 101 110 3760 conferenceobject RWTH Aachen Aachen 0 -- -- -- This paper presents an innovative approach for the automatic generation of Knowledge Graphs (KGs) from heterogeneous scientific articles in the domain of Non-Destructive Testing (NDT) applied to building materials. Our methodology leverages large language models (LLMs) to extract and semantically relate concepts from diverse sources. We developed material-specific agents for concrete, wood, steel, and bricks, each equipped with a curated glossary of terms to ensure domain accuracy. These agents process PDF documents, extracting relevant information on deterioration mechanisms, physical changes, and applicable NDT methods. The extracted data is then normalized, validated, and structured into a Neo4j graph database, forming a comprehensive KG. Our results demonstrate the system’s ability to automatically discover and represent intricate relationships between materials, deterioration mechanisms, physical changes, and NDT techniques. The generated KG successfully captures complex interactions, such as the applicability of specific NDT methods to various materials under different deterioration conditions. This work not only highlights the potential of KGs in enhancing knowledge discovery and representation in NDT research but also provides a scalable framework for extending this approach to other scientific domains. SeMatS 2024 - Proceedings of the first international workshop on semantic materials science: Harnessing the power of semantic web technologies in materials science 1613-0073 10.5281/zenodo.13834164 urn:nbn:de:kobv:b43-624597 Serientitel: CEUR workshop proceedings – Series title: CEUR workshop proceedings SeMatS 2024 - The 1st International Workshop on Semantic Materials Science Amsterdam, The Netherlands 17.09.2024 publish https://opus4.kobv.de/opus4-bam/frontdoor/index/index/docId/62497 false true Creative Commons - CC BY - Namensnennung 4.0 International Ghezal Ahmad Jan Zia Andre Valdestilhas Benjami Moreno Torres Sabine Kruschwitz eng uncontrolled Materials science and engineering eng uncontrolled Large language model eng uncontrolled Linked open data eng uncontrolled Data interoperability eng uncontrolled RDF eng uncontrolled Semantic web Ingenieurwissenschaften und zugeordnete Tätigkeiten 8 Zerstörungsfreie Prüfung Material Datei für die Öffentlichkeit verfügbar ("Open Access") Graue Literatur Wissenschaftliche Artikel der BAM 8.0 Abteilungsleitung und andere Materialdesign Bundesanstalt für Materialforschung und -prüfung (BAM) https://opus4.kobv.de/opus4-bam/files/62459/ZiaKG_NDT (1).pdf