Automated Extraction of Mechanical Constitutive Models from Scientific Literature using Large Language Models: Applications in Cultural Heritage Conservation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908839879639040 |
|---|---|
| author | Hu, Rui Wu, Yue Su, Tianhao Wang, Yin Hu, Shunbo Huang, Jizhong |
| author_facet | Hu, Rui Wu, Yue Su, Tianhao Wang, Yin Hu, Shunbo Huang, Jizhong |
| contents | The preservation of cultural heritage is increasingly transitioning towards data-driven predictive maintenance and "Digital Twin" construction. However, the mechanical constitutive models required for high-fidelity simulations remain fragmented across decades of unstructured scientific literature, creating a "Data Silo" that hinders conservation engineering. To address this, we present an automated, two-stage agentic framework leveraging Large Language Models (LLMs) to extract mechanical constitutive equations, calibrated parameters, and metadata from PDF documents. The workflow employs a resource-efficient "Gatekeeper" agent for relevance filtering and a high-capability "Analyst" agent for fine-grained extraction, featuring a novel Context-Aware Symbolic Grounding mechanism to resolve mathematical ambiguities. Applied to a corpus of over 2,000 research papers, the system successfully isolated 113 core documents and constructed a structured database containing 185 constitutive model instances and over 450 calibrated parameters. The extraction precision reached 80.4\%, establishing a highly efficient "Human-in-the-loop" workflow that reduces manual data curation time by approximately 90\%. We demonstrate the system's utility through a web-based Knowledge Retrieval Platform, which enables rapid parameter discovery for computational modeling. This work transforms scattered literature into a queryable digital asset, laying the data foundation for the "Digital Material Twin" of built heritage. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16551 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Automated Extraction of Mechanical Constitutive Models from Scientific Literature using Large Language Models: Applications in Cultural Heritage Conservation Hu, Rui Wu, Yue Su, Tianhao Wang, Yin Hu, Shunbo Huang, Jizhong Databases The preservation of cultural heritage is increasingly transitioning towards data-driven predictive maintenance and "Digital Twin" construction. However, the mechanical constitutive models required for high-fidelity simulations remain fragmented across decades of unstructured scientific literature, creating a "Data Silo" that hinders conservation engineering. To address this, we present an automated, two-stage agentic framework leveraging Large Language Models (LLMs) to extract mechanical constitutive equations, calibrated parameters, and metadata from PDF documents. The workflow employs a resource-efficient "Gatekeeper" agent for relevance filtering and a high-capability "Analyst" agent for fine-grained extraction, featuring a novel Context-Aware Symbolic Grounding mechanism to resolve mathematical ambiguities. Applied to a corpus of over 2,000 research papers, the system successfully isolated 113 core documents and constructed a structured database containing 185 constitutive model instances and over 450 calibrated parameters. The extraction precision reached 80.4\%, establishing a highly efficient "Human-in-the-loop" workflow that reduces manual data curation time by approximately 90\%. We demonstrate the system's utility through a web-based Knowledge Retrieval Platform, which enables rapid parameter discovery for computational modeling. This work transforms scattered literature into a queryable digital asset, laying the data foundation for the "Digital Material Twin" of built heritage. |
| title | Automated Extraction of Mechanical Constitutive Models from Scientific Literature using Large Language Models: Applications in Cultural Heritage Conservation |
| topic | Databases |
| url | https://arxiv.org/abs/2602.16551 |