AI Systems Engineering - Challenges of a new professional discipline
summary
Competence Center CC-KING develops predictive quality models for 300 m wood‑panel lines that cut energy and material costs by millions of euros; prototypes appear within weeks but full production deployment takes years. Key engineering problems are performance prediction, scarce operational data and heterogeneous deployments across non‑identical machines, plus lost domain knowledge when pure neural models replace physics. Research focuses on hybrid models, online experiment design to pick informative samples, automated drift detection and adaptation, and methods aimed at meeting safety certification for high‑critical systems.
AI-written summary · about
chapters (10)
- 0:00Intro
- 1:16Al in Industrial Systems
- 3:00Most Al initiatives in industry die after the prototype...
- 4:47Agenda of the talk
- 5:36Application Dimensions of Al Systems Engineering
- 8:57Technical Dev Challenges
- 11:442. Organizational Dev Challenges
- 13:42Operational Challenges
- 17:00Research Questions
- 20:12CC-KING: Competence Center for KI-Engineering What are we doing today and how can you help?
related talks
22mEngineering Predictive Platforms
44mAI Engineering Anti-patterns
15mIndustrial AI at Thyssenkrupp Steel: From idea to scalable solution – what really works
55mWhat Skills Do Predictive Modelers Need?
10mAI-Powered Digital Twins: Patterns for Smart Manufacturing
31mHow to successfully implement AI in manufacturing
22mUnique Challenges of AI in Materials Design
34mData-Driven Solutions in Engineering