liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Exploring an Agent-Based Generative AI CAD Framework: Enhancing CAD Design Automation with AI-Driven Parametric Modelling and Adaptive Query Generation
Linköping University, Department of Management and Engineering. (Product Realization)
Linköping University, Department of Management and Engineering. (Product Realization)
2025 (English)Independent thesis Advanced level (degree of Master (Two Years)), 80 credits / 120 HE creditsStudent thesis
Abstract [en]

This thesis presents the development of an AI-driven, agent-based framework designed to make Computer Aided Design (CAD) more accessible, intuitive, and efficient for the CAD users. Traditional CAD workflows require technical expertise and manual operations, creating barriers for those unfamiliar with complex software tools. Our goal was to create a system where users can simply describe their design intent using plain language, sketches, or both, and have those ideas automatically converted into accurate CAD models.To achieve this, we developed a modular framework that integrates advanced AI components capable of understanding user input, inferring missing details, and executing design operations inside a professional CAD environment (CATIA V5). The system uses language and vision models to interpret input, a structured database to manage commands, and a graph-based workflow engine to ensure correct execution order. Following an iterative development method (Rapid Application Development), we implemented and tested the framework in stages, gradually improving its capabilities. The result is a working prototype that successfully performs CAD functions based on natural input, demonstrating the feasibility of more intelligent and user-friendly CAD automation

Place, publisher, year, edition, pages
2025. , p. 68
Keywords [en]
CAD, AI, Large Language Models, Natural Language Processing, Agentic, CATIA, P
National Category
Other Mechanical Engineering
Identifiers
URN: urn:nbn:se:liu:diva-218259ISRN: LIU-IEI-TEK-A--25/05160—SEOAI: oai:DiVA.org:liu-218259DiVA, id: diva2:2002963
Presentation
2025-06-04, Linkoping University, Linkoping, 13:10 (English)
Supervisors
Examiners
Available from: 2025-10-02 Created: 2025-10-02 Last updated: 2025-10-02Bibliographically approved

Open Access in DiVA

fulltext(2121 kB)840 downloads
File information
File name FULLTEXT01.pdfFile size 2121 kBChecksum SHA-512
3fdfc9fe9fcc5685f35ead3ed2f6c5d17fa95e4a958d915ff2ac943fab95ec3075fe46270c23c49af0c21a8e8f1fca01bb6e10f93312084ba2a0dd45b1cdb83f
Type fulltextMimetype application/pdf

By organisation
Department of Management and Engineering
Other Mechanical Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 842 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 1808 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf