Work

Extracting Information from CAD Assemblies Using Large Language Models and Retrieval-Augmented Generation

Year: 2026

Type: article

Abstract: Digital manufacturing systems require product-specific information retrievable from CAD models. Accessing this information is labor-intensive due to inconsistent property naming and complex assembly structures, often requiring structure-dependent and manually adapted extraction routines. This paper presents an LLM-driven method for automated information extraction from native CAD assemblies, enabling adaptive and structure-independent access to CAD information across systems, and providing results in a predefined schema. The approach employs a three-stage retrieval-augmented generation pipeline, which first plans requests using the CAD system’s API documentation. A request is then drafted based on examples from previous successful executions and refined, if necessary, using error-fix documentation. Experiments demonstrate strong performance on medium-sized assemblies, highlighting the approach’s potential to reduce manual efforts in information extraction, while deeply nested hierarchies remain challenging.

Source: Procedia CIRP

DOI: 10.1016/j.procir.2026.03.195

Authors: Sebastian Kurscheid, Charlotte Reichelt, Paul Geng, Lukas Tanz, Daniel Eder, Ruediger Daub

Institutions: Technical University of Munich, Fraunhofer Institute for Casting, Composite and Processing Technology IGCV

Language: English

Topic: Manufacturing Process and Optimization

Subfield: Industrial and Manufacturing Engineering

Field: Engineering

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: diamond

Funder: Bayerisches Staatsministerium für Wirtschaft, Infrastruktur, Verkehr und Technologie