Prof. Dr. Jörg Franke
Foto: FAU/David Hartfiel

Prof. Dr.-Ing. Jörg Franke

Institute for Manufacturing Automation and Production Systems

AI in the manufacturing environment

  • Co-author of the position paper ‘KI-unterstützte Produktion’ (AI-supported production) from the German Academic Association for Production Engineering, Wissenschaftliche Gesellschaft Produktionstechnik (WGP).
  • Member of acatech project group ‘AI in production’
  • Competence and analysis project for process and production optimisation using data mining (EFRE E|ASY-OPT)
  • Condition monitoring and process monitoring in production plants on the basis of airborne and structure-borne noise (e.g. for predictive maintenance for wear parts such as ball screws, detection of unwanted process conditions such as rattling or machine collisions, prediction of product quality)
  • Electronics production: intelligent use of operational and inspection data in an SMT line to increase quality and flexibility (VDI|VDE|IT SmartEP, D-LEAP, Sens2IQ)
  • Electric motor production: predicting quality and detecting errors in bonding processes such as ultrasound or laser welding, predicting EOL properties of e-motors based on inline measurement of rotor tolerance
  • Production of inductive charging systems: CNN-based vision system for error pattern classification during the installation process (BMWi E|PROFIL)
  • Manufacturing x-ray units: plant and process monitoring as well as static process optimisation
  • Additive manufacturing: digital twin for process optimisation
  • Assembly process chains: detecting cross-process causes of errors when assembling electro-magnetic actuators
  • Load management in production plants: adjusting machine status and consumption depending on current energy price, load profile and current load in order to minimise energy costs
  • Robotics: Object recognition and pose evaluation for bin-picking applications using synthetic datasets for automated annotation / training (BFS FORobotics)
  • Robotics: Segmentation and determining gripping posture for highly individual objects in the context of autonomous gripping and sorting of waste according to material on the basis of trained characteristics of waste products (rust, broken edges etc.)
  • Robotics: Person and obstacle recognition for autonomous aerial robots in the industrial environment
  • Intralogistics: identification of similar components using applied or inherent characteristics to improve traceability
  • Six-Sigma 4.0 process model for using data mining to support zero-error management
  • Platform for dynamic composition of production-related services (BMBF PRODISYS)
  • IoT solution for production and logistics using intelligently connected multiple sensor systems (VDI|VDE|IT ProLog 4.0)
  • Semantic technologies for supporting production system design
  • Knowledge-based configuration of automation solutions based on robotics applications (BMWi ROBOTOP)
  • Intelligent cost forecast for components and devices for use during negotiations with suppliers

AI in private life

  • 3D camera-based route recognition for blind joggers on the basis of artificial neuronal networks
  • Object recognition for mobile service robots (e.g. for recognising objects)
  • Recognition of falls using structure-bound noise in floors within the context of self-determined living
  • Platform for context-sensitive, intelligent and predictive smart living services (BMWi ForeSight)

Contact: