Conference Agenda
Overview and details of the sessions of this conference. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
Please note that all times are shown in the time zone of the conference. The current conference time is: 18th Apr 2026, 03:59:52pm CEST
|
Agenda Overview |
| Session | ||
D422: GENERATIVE AI FOR DESIGN SYNTHESIS AND ENGINEERING APPLICATIONS
| ||
    | ||
From geometry to function: towards context-aware generative AI for engineering design 1Dresden University of Technology, Germany; 2MAN Truck & Bus SE, Germany; 3Leibniz University Hannover, Germany Current generative artificial intelligence for Computer-Aided Design (CAD) optimizes for geometric similarity, neglecting engineering criteria like functionality, manufacturability, and sustainability. This paper addresses this gap and proposes a conceptual framework to reorient generative CAD from replicating shapes to achieving function. We introduce two hybrid training strategies: a pre-learning approach using synthetically labeled datasets (evaluated via FEA, CAM, LCA) and a self-learning approach where GenAI uses these knowledge-based tools as a reinforcement feedback loop. Achievable mechanical performance of generatively designed PA6-CF and PLA components fabricated by desktop material extrusion Norwegian University of Science and Technology, Norway This study investigates the mechanical performance of PA6-CF and PLA components fabricated with desktop material extrusion additive manufacturing. To define the geometry, low-cost 3D scanning was used in combination with Generative Design in Autodesk Fusion 360. PA6-CF outperformed PLA by 25% in pre-failure peak load (1.85 kN vs. 1.47 kN), despite the datasheet values suggesting a 450% advantage in interlayer strength. Poor interlayer bonding of PA6-CF is attributed to low layer temperatures (87–136 °C) during the printing process, indicating that a chamber temperature of 60 °C is inadequate. Structured prompting for design for multi-X: evaluating LLM support in early prosthetic device design University of Malta, Malta This paper investigates how prompt structure influences the use of Large Language Models in early engineering design. A structured prompting framework aligned with the engineering design cycle is proposed to support Design for Multi X reasoning and more coherent problem exploration. Using a prosthetic knee-cover case study, six engineering designers engaged with both generic and structured prompting workflows. A mixed methods study examines how prompt organisation shapes LLM assisted reasoning, problem framing and the articulation of design constraints and considerations. In search for working principles using large language models: an experimental study 1Swinburne University of Technology, Australia; 2University of Rostock, Germany; 3Hochschule für Technik und Wirtschaft Berlin, Germany The use of artificial intelligence, especially large language models (LLMs), is increasingly explored to support early system development. This paper evaluates low-threshold LLM-based tools for supporting conceptual design. Through an experiment, two LLM-based tools were compared generating alternative solutions using an existing function model of an electro-mechanical system as input. Functions were provided in natural language and using the Functional Basis. Results show limitations and significant potentials for effective and efficient conceptual design support. | ||
