Conference Agenda

Industry 5.0 re-centres manufacturing around people, yet many shop-floor tasks remain resistant to automation because they demand dexterity, judgement, and adaptability, while imposing simultaneous physical and cognitive strain. Existing exoskeleton adoption approaches under-address this “dual load” reality and rarely treat integration with DMSs as a first-class design and implementation concern through an IPD lens. This study combines a state-of-the-art review and semi-structured interviews with two contrasting case studies (toolroom maintenance and food production), applying IDEF0 modelling, feasibility analysis, and Quality Function Deployment to translate evidence into requirements, integration points, and design direction. This resulted in a novel IPDEXO framework: a phased, three-pillar (business–design–production) prescriptive model, refined through evaluation feedback, and demonstrated through a modular smart exoskeleton concept and proof-of-concept scenarios, such as AR-guided industrial work and ERP-linked traceability.

Society is in the midst of a transformation process that can be attributed to climate change and rapid technological progress. It is anticipated that a new technological leap will be made toward biointelligent value creation. This increasing integration of biological components into technical systems is fundamentally changing development practices and creating new challenges, particularly in product development. Therefore, this paper proposes a theoretical framework for the classification of biointelligent systems based on a maturity model to determine the current state of development.

Automotive development in historically grown organizations faces significant challenges: fragmented processes, component-level optimization, and high early-phase effort. This paper proposes an end-to-end development strategy that leverages automation and AI to improve data generation, transparency, and decision-making. The approach is demonstrated through High-Voltage Wiring Harness development, illustrating its potential to enhance process efficiency and support future data-driven engineering.

This paper introduces an approach for LLM-supported requirements extraction from different data sources within SGE – System Generation Engineering. Developing new mechatronic system generations involves gathering requirements from heterogeneous artifacts, such as specifications, standards, competitor materials. Manual extraction is often time-consuming and error-prone. The proposed approach, developed through industry collaboration and academic projects, incorporates a five-step workflow comprising source identification, preparation, prompting, pre-check, and final check, as well as methodological support, such as a standardized prompt template and INCOSE criteria, to enable requirements extraction. Key features include applicability across different data sources, traceability, domain adaptability, reproducibility, expert validation, and scalability. An initial exploratory evaluation during a semester-long, practice-oriented live-lab indicates the approach’s applicability and potential benefits, such as reduced manual effort, traceability, and the possibility of using it as sparring partner. However, the evaluation also highlights challenges, such as the importance of human involvement to ensure context awareness and requirements quality.