Prof. Dr.-Ing. Daniel Böhnke
Engineering Computer Science
24149 Kiel
Room: C05-0.37
Prof. Dr.-Ing. Böhnke holds the professorship for Engineering Informatics in the Department of Mechanical Engineering. The focus of his work is the interface between engineering sciences and computer science. In both teaching and research, he is engaged with the digitalization of mechanical engineering. His teaching portfolio includes the fundamental principles of computer science for engineers, as well as specialized courses in machine learning and the programming of numerical methods.
In the field of research, the focus is on the application of machine learning methods in an engineering context, particularly in production. Some of the topics covered include condition monitoring, predictive maintenance, numerical optimization, and the processing of CAD data with AI.
Prof. Böhnke is also the head of the Practice-Oriented Studies (PBS) program at the university of applied sciences.
Information about the individual courses can be found in the module database.
- Professor of engineering computer science at the Kiel University of Applied Sciences
- Product Owner Data Science at Lufthansa Industry Solutions
- Project manager and deputy department head at DLR, Institute for Air Transport Systems
- Doctorate Dr.-Ing. at the Technical University of Hamburg
- Dipl.-Ing. Aerospace Engineering University of Stuttgart & Southampton
Focus: CAD and AI
A large portion of a product’s information is linked to its geometry. The processing of this information—usually CAD data—with the help of AI remains a current research topic. Prof. Böhnke’s research group is intensively engaged in this area. Possible applications include:
• Deriving information for manufacturing (work plan, tool, program) from CAD data
• Assessing the similarity of CAD geometries, e.g., for simplified costing or programming
• Generating CAD parts with AI support
Focus: Predictive Maintenance
Predictive maintenance deals with the question of how failures can be detected in time using individualized data and models to prevent breakdowns. Finding the right use case and its operational implementation are key challenges. This topic is addressed by the research group in various projects and also in teaching. Possible applications include:
• Detecting anomalies and determining the likelihood of failures
• Using digital twins to monitor the efficiency of a facility or machine
• Interpreting AI models for rapid identification of error causes
Projects
• KI-Transfer-Hub SH (2020-2023)
• Argus-KI (2023-2025)
• Offer-AI (2023-2026)
• KI Application Center SH (2023-2028)
• Audio Anomaly Detector
ORCID ID: 0000-0003-2781-2685