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, 05:29:05pm CEST
|
Agenda Overview |
| Session | ||
D412: LLM-ENABLED DESIGN METHODS AND ENGINEERING PROCESSES
| ||
    | ||
ISOprep: an LLM-driven pipeline for semantics-preserving processing of neutralized requirements according to ISO 29148 Leuphana University Lüneburg, Germany AI in Requirements Engineering (RE) relies on industrial data, yet safety and privacy risks limit its use. While the GDPR distinguishes only between anonymization and pseudonymization, we use neutralization as a semantics-preserving technique. In AI-supported RE, data heterogeneity and cross-domain variability impede model training. We propose guidelines for semantics-preserving preprocessing for RE datasets based on ISO 29148 criteria, showing that neutralization does not compromise semantics. The approach enables industry–academia collaboration through AI-assisted RE in product development. Evaluating TRIZ with and without LLM support: an experimental study on engineering problem-solving 1Faculty of Mechanical Engineering, University of Ljubljana, Slovenia; 2Department of Design Sciences, Lund University, Sweden; 3ENSAM, University of Moulay Ismail, Morocco; 4Mathematics, Computer Science and Engineering Department, University of Quebec at Rimouski, Canada This paper examines integrating Large Language Models (LLMs) into the TRIZ contradiction matrix (TRIZ-C+LLM) to support engineering students in creative problem-solving. Experiments with three problems show that LLMs did not always improve design quality for complex tasks but reduced cognitive workload, improved understanding of contradictions, and increased perceived usefulness. Prompting experience strongly influenced outcomes, highlighting both the promise and limits of combining TRIZ with generative AI. Discover the use of multimodal language models for idea detailing in human-AI collaborative design University of Exeter, United Kingdom In this work, we propose a multimodal, language-model–based design assistance framework for the design ideation stage. The framework leverages large language models (LLMs) to interpret user intentions with mood boards, enrich initial ideas with essential contextual details, and produce structured instructions for visual language models (VLMs) to enhance the accuracy and consistency of visual feedback. Structure-based similarity searches to improve the reuse of assemblies and functional units in plant engineering – use cases and implementation verification with a large language model as a search tool 1VON ARDENNE GmbH, Germany; 2Dresden University of Technology, Germany In plant engineering and industrial solution business, the focus is on developing customer-specific products. At the same time, finding suitable templates from previous projects (adaptation design) is essential for efficient product development. Conventional search tools in PDM/ERP systems are not suitable for this purpose, which is why structure-based similarity search was proposed in an earlier article. In this article, a feasibility study is conducted to determine what typical use cases exist and whether these can be easily SME-implemented with a large language model (LLM) as a search tool. | ||
