Stefano De Blasi
Stefano De Blasi has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
Elmar Engels
University of Applied Sciences Fulda, Fulda, Germany
2 shared publications- Alexander Gepperth
Fulda University of Applied Sciences
1 shared publication Andreas Bahmer
University ENT-Clinic Würzburg, Theoretical and Experimental Neurophysiology, 97080 Würzburg, Germany
1 shared publicationArne Müller
DXC Technology, Böblingen, Germany
1 shared publication- Christiane Thielemann
BioMEMS lab, University of Applied Sciences Aschaffenburg, Aschaffenburg, Germany
1 shared publication Fabian Sturm
Bosch Rexroth AG, Lohr am Main, Germany
1 shared publication
Latest Publications
- Open Access
- 13 February 2023
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 35 (2) , 885-903
Safe contextual Bayesian optimization integrated in industrial control for self-learning machines
Intelligent manufacturing applications and agent-based implementations are scientifically investigated due to the enormous potential of industrial process optimization. The most widespread data-driven approach is the use of experimental history under test conditions for training, followed by execution of the trained model. Since factors, such as tool wear, affect the process, the experimental history has to be compiled extensively. In addition, individual machine noise implies that the models are not easily transferable to other (theoretically identical) machines. In contrast, a continual learning system should have the capacity to adapt (slightly) to a changing environment, e.g., another machine under different working conditions. Since this adaptation can potentially have a negative impact on process quality, especially in industry, safe optimization methods are required. In this article, we present a significant step towards self-optimizing machines in industry, by introducing a novel method for efficient safe contextual optimization and continuously trading-off between exploration and exploitation. Furthermore, an appropriate data discard strategy and local approximation techniques enable continual optimization. The approach is implemented as generic software module for an industrial edge control device. We apply this module to a steel straightening machine as an example, enabling it to adapt safely to changing environments.
- 13 February 2023
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 35 (2) , 885-903
Open AccessSafe contextual Bayesian optimization integrated in industrial control for self-learning machines
Intelligent manufacturing applications and agent-based implementations are scientifically investigated due to the enormous potential of industrial process optimization. The most widespread data-driven approach is the use of experimental history under test conditions for training, followed by execution of the trained model. Since factors, such as tool wear, affect the process, the experimental history has to be compiled extensively. In addition, individual machine noise implies that the models are not easily transferable to other (theoretically identical) machines. In contrast, a continual learning system should have the capacity to adapt (slightly) to a changing environment, e.g., another machine under different working conditions. Since this adaptation can potentially have a negative impact on process quality, especially in industry, safe optimization methods are required. In this article, we present a significant step towards self-optimizing machines in industry, by introducing a novel method for efficient safe contextual optimization and continuously trading-off between exploration and exploitation. Furthermore, an appropriate data discard strategy and local approximation techniques enable continual optimization. The approach is implemented as generic software module for an industrial edge control device. We apply this module to a steel straightening machine as an example, enabling it to adapt safely to changing environments.
- 24 April 2021
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 102 (1) , 1-18
KIcker: An Industrial Drive and Control Foosball System automated with Deep Reinforcement Learning
- 24 April 2021
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 102 (1) , 1-18
KIcker: An Industrial Drive and Control Foosball System automated with Deep Reinforcement Learning
- 1 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 468-473
Next generation control units simplifying industrial machine learning
The increasing amount of sensor data creates new possibilities through data-driven projects in industry. The demands on the final solution architecture are different and typically include at least one controller (e.g. PLC). In this paper, we focus on these industrial controllers and identify their possible roles in smart factories: Collection, distribution and preprocessing of field data, execution of intelligence and functionalities to ease rapid prototyping approaches. Furthermore, we specify the capabilities leading to the fulfillment of these roles and present an application example of drive anomaly detection to demonstrate how to setup an industrial controller for machine learning projects.
- 1 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 468-473
Next generation control units simplifying industrial machine learning
The increasing amount of sensor data creates new possibilities through data-driven projects in industry. The demands on the final solution architecture are different and typically include at least one controller (e.g. PLC). In this paper, we focus on these industrial controllers and identify their possible roles in smart factories: Collection, distribution and preprocessing of field data, execution of intelligence and functionalities to ease rapid prototyping approaches. Furthermore, we specify the capabilities leading to the fulfillment of these roles and present an application example of drive anomaly detection to demonstrate how to setup an industrial controller for machine learning projects.
- 1 January 2019
- Published by Springer Nature
- p. 689-699
Active Learning Approach for Safe Process Parameter Tuning
- 1 January 2019
- Published by Springer Nature
- p. 689-699
Active Learning Approach for Safe Process Parameter Tuning
- 1 January 2019
- Published by Elsevier in Journal of Neuroscience Methods
- Vol. 312, 169-181
Total spiking probability edges: A cross-correlation based method for effective connectivity estimation of cortical spiking neurons
- 1 January 2019
- Published by Elsevier in Journal of Neuroscience Methods
- Vol. 312, 169-181
Total spiking probability edges: A cross-correlation based method for effective connectivity estimation of cortical spiking neurons