Navigationsweiche Anfang

Navigationsweiche Ende

Select language

Chair for Technologies and Management of Digital Transformation


Univ. Prof. Dr. Ing. Tobias Meisen

Industrial Deep Learning

In our research, we address the development and verification of deep learning methods for the use in industrial processes and services. On the one hand, our research aims at establishing deep learning as an enabler of new services such as predictive quality and predictive maintenance. On the other hand, we investigate reinforcement learning methods for training intelligent, self-learning agents to solve planning tasks. Central reserach topics are the formalization of industrial use cases as learning problems and their solution under consideration of criteria such as reliability, robustness and accuracy. Furthermore, we address the issue of developing data-efficient and sustainable deep learning models for the manufacturing industry. Our main research areas here cover bridging the reality gap of simulations by means of transfer learning methods and the continual training of deep learning models across process and system changes.

Main Topics

  • Deep Reinforcement Learning
  • Supervised Learning and Anomaly Detection
  • Sim2Real Transfer Learning
  • Continual Learning

Application Areas

  • Predictive Quality and Predictive Maintenance
  • Planning and control of industrial robots
  • Job shop scheduling and intelligent production planning
  • Usage anlalytics of digital products and services

Contact

Hasan Tercan, M.Sc.

Selected relevant publications

References
Ira Assent; Marc Wichterich; Tobias Meisen; Thomas Seidl
Efficient Similarity Search using the Earth Mover's Distance for Large Multimedia Databases
2008 IEEE 24th International Conference on Data Engineering, :307--316
2008

Keywords: research-industrial-deep-learning

Page:  
Previous | 1, 2, 3 | Next
Total:
25
Export as:
BibTeX, XML