From Dialogue to Design : GenAI-Based Automation of Parametric Modeling and Sizing Tasks in CAD Workflows

DOI zum Zitieren der Version auf EPub Bayreuth: https://doi.org/10.15495/EPub_UBT_00009435
URN to cite this document: urn:nbn:de:bvb:703-epub-9435-1

Title data

Rosnitschek, Tobias ; Walschewski, Jan ; Grohmann, Peter ; Eckardt, Sascha ; Stonis, Malte ; Alber-Laukant, Bettina ; Tremmel, Stephan:
From Dialogue to Design : GenAI-Based Automation of Parametric Modeling and Sizing Tasks in CAD Workflows.
In: Computer-Aided Design. Vol. 196 (2026) . - 104065.
ISSN 0010-4485
DOI der Verlagsversion: https://doi.org/10.1016/j.cad.2026.104065

	Format: PDF Name: 1-s2.0-S0010448526000357-main.pdf Version: Published Version Available under License Creative Commons BY 4.0: Attribution
	Download (3MB)

Project information

Project title:	Project's official title Project's id Open Access Publizieren No information
Project financing:	Bayerische Forschungsstiftung

Abstract

This study explores the automation of engineering design tasks using Generative Artificial Intelligence, focusing on the dimensioning machine elements and generation of their respective CAD models, specifically bolted connections, in the open-source software FreeCAD. Three system architectures were developed and evaluated: All-in-One, Chatbot-Designbot, and Chatbot-Calculator-Code Generator. These frameworks integrate Large Language Models, such as GPT-2 and CodeGen, which were fine-tuned using Parameter-Efficient Fine-Tuning and Low-Rank Adaptation. While the All-in-One architecture consolidates all tasks into a single model, the Chatbot-Designbot and Chatbot-Calculator-Code Generator architectures decompose the process into specialized modules for dialogue interaction, parameter extraction, part dimensioning, and CAD code generation. The evaluation results show that the Chatbot-Calculator-Code Generator configuration achieves the lowest overall error rate for the four steps combined (2) with a total training time of 63.4 minutes. This configuration outperforms the Chatbot-Designbot (3.96, 117.7 minutes) and All-in-One (53, 24.2 minutes) architectures. These findings demonstrate that compact, fine-tuned Large Language Models can enable accurate and efficient design automation, even with limited data. This work establishes a methodological foundation for scalable, Generative Artificial Intelligence -driven CAD systems and interactive engineering design workflows.

Further data

Item Type:	Article in a journal
Keywords:	Artificial Intelligence applications; Computer-Aided Design; Design automation; Natural Language Processing; Engineering computation
DDC Subjects:	600 Technology, medicine, applied sciences > 620 Engineering
Institutions of the University:	Faculties > Faculty of Engineering Science > Former Professors > Chair Engineering Design and CAD - Univ.-Prof. Dr.-Ing. Frank Rieg Faculties > Faculty of Engineering Science > Chair Engineering Design and CAD > Chair Engineering Design and CAD - Univ.-Prof. Dr.-Ing Stephan Tremmel Faculties Faculties > Faculty of Engineering Science Faculties > Faculty of Engineering Science > Former Professors Faculties > Faculty of Engineering Science > Chair Engineering Design and CAD
Language:	English
Originates at UBT:	Yes
URN:	urn:nbn:de:bvb:703-epub-9435-1
Date Deposited:	16 Jun 2026 14:29
Last Modified:	16 Jun 2026 14:29
URI:	https://epub.uni-bayreuth.de/id/eprint/9435

Download Statistics

Download Statistics

Download Statistics

Downloads

Downloads per month over past year