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.

Using structural optimization is ideal for the development of complex aluminum cast parts, due to the high degree of design freedom. Various casting processes exist for production, and these differ in their boundary conditions and process restrictions. The resulting geometric restrictions have so far only been taken into account to a limited extent in structural optimization. Hence, there is a desire to determine simple process restrictions that can be taken into account to generate component geometries that are as light as possible but can still be produced by casting. This paper addresses the automated validation and optimization of directional solidification for topology-optimized geometries for castings. For the parametric description of the component volume, the medial axis transform (MAT) method is chosen. This approach allows a subsequent evaluation and optimization by methods of graph theory and feedback into an adapted surface file. The optimization results are finally evaluated by a process simulation using the finite volume method.