Activities per year
Project Details
Description
In the smart factory, all machines, robots and systems are connected and can talk and interact with each other. The digital technologies tie all business processes together in the organization and create a production that is constantly adapting to new demands from customers, suppliers and the outside world.
In MADE Digital work package 5, Smart Factories, we work on how digital technologies can be applied in Danish companies to create smarter production.
Specifically, in WP5.3, the research work is concerned with developing adaptive learning algorithms enabling robots to adapt to variations in input, continuously perform corrections during processing and adjust processes based on the quality of the produced output.
In MADE Digital work package 5, Smart Factories, we work on how digital technologies can be applied in Danish companies to create smarter production.
Specifically, in WP5.3, the research work is concerned with developing adaptive learning algorithms enabling robots to adapt to variations in input, continuously perform corrections during processing and adjust processes based on the quality of the produced output.
Layman's description
Our research is focus on introducing self-learning capabilities in smart factories to optimize industrial processes in food manufacturing.
Short title | MADE Digital WP5.3 |
---|---|
Status | Finished |
Effective start/end date | 01/03/2017 → 31/12/2019 |
Collaborative partners
- Danish Meat Research Institute (DMRI) (Project partner)
- danish crown (Project partner)
Keywords
- made digital
- self-learning factories
- Reinforcement Learning
- smart factories
Fingerprint
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.
Activities
- 1 Organisation or participation in workshops, courses, seminars, exhibitions or similar
-
Special Session on Deep Learning As a Mean for Enabling Self-Learning and Self-Optimizing Capabilities in Real-World Industrial Applications
Simon Bøgh (Organizer), Nestor Arana-Arexolaleiba (Organizer) & Dimitrios Chrysostomou (Organizer)
14 Jan 2020Activity: Attending an event › Organisation or participation in workshops, courses, seminars, exhibitions or similar
Research output
- 3 Article in proceeding
-
Transferring Human Manipulation Knowledge to Robots with Inverse Reinforcement Learning
Hansen, E. B., Andersen, R. E., Madsen, S. & Bøgh, S., 2020, Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020. IEEE, p. 933-937 5 p. 9025873. (Proceedings of the 2020 IEEE/SICE International Symposium on System Integration).Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review
File6 Citations (Scopus)177 Downloads (Pure) -
Self-learning Processes in Smart Factories: Deep Reinforcement Learning for Process Control of Robot Brine Injection
Andersen, R. E., Madsen, S., Barlo, A. B. K., Blegebrønd Johansen, S., Nør, M., Andersen, R. S. & Bøgh, S., 2019, 29th International Conference on Flexible Automation and Intelligent Manufacturing: FAIM 2019. Elsevier, Vol. 38. p. 171-177 7 p. (Procedia Manufacturing).Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review
Open AccessFile16 Citations (Scopus)168 Downloads (Pure) -
Transferring Human Manipulation Knowledge to Industrial Robots Using Reinforcement Learning
Arexolaleiba, N. A., Anguiozar, N. U., Chrysostomou, D. & Bøgh, S., 2019, 29th International Conference on Flexible Automation and Intelligent Manufacturing: FAIM 2019. Elsevier, Vol. 38. p. 1508 - 1515 8 p. (Procedia Manufacturing, Vol. 38).Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review
Open AccessFile11 Citations (Scopus)156 Downloads (Pure)