Data-driven Model Learning in Interconnected Systems
Seminar with Paul Van den Hof (TU Eindhoven).
Practical information:
Want to register?
- Register until: 05 May 2022
- Price: Free
Registration is not necessary, you can simply join the seminar.
Would you like to receive a reminder of our monthly seminars in this series on time series? Subscribe!
Georganiseerd door:
Leertraject
Many of our current technological systems are composed of subsystems that have local dynamic behaviour and that interact with each other in a network structure. Typical examples are found in e.g., power systems (smart grids), biological systems, flexible mechanical structures, robotic networks, transportation systems and distribution networks.
For control, optimization and diagnostics of those systems, the interconnected nature leads to distributed and/or multi-agent type of approaches, while data is playing a paramount role in modelling, monitoring and controlling the dynamic behaviour of the system.
In this seminar we will present the emerging challenge of developing effective and scalable tools for data-driven dynamic model learning in large-scale interconnected systems, also referred to as dynamic networks. Focusing on linear dynamic networks, the problems of conceptual network modelling and local module learning will be presented, while graph-based tools are shown to be able to address problems like sensor and excitation/actuator allocation for accurately learning either a single module or a full network.
Teacher / speaker
Paul Van den Hof
Paul Van den Hof is Full Professor of the Control Systems (CS) Group at the Department of Electrical Engineering of Eindhoven University of Technology. He is interested in data-driven modeling, control and optimization of dynamic systems in several technological fields: industrial process control, oil reservoir engineering, high-tech mechatronic and cyber-physical systems, etc. His focus is the development of fundamental techniques, such as data-driven modeling, closed-loop and control-oriented identification and data analytics, experimental design and performance monitoring, and model-based control, monitoring and optimization. Van den Hof often collaborates closely with international academic and industrial partners. Van den Hof was General Chair of the 13th IFAC Symposium on System Identification in 2003. He has served as member of the IFAC Council (1999-2005, 2017-2020), Associate Editor and Editor of Automatica (1992-2005), and Vice-President of IFAC (2017-2020). He is a Fellow of IFAC and of IEEE, and Honorary Member of the Hungarian Academy of Sciences. He holds an ERC Advanced Research Grant on Dynamic Network Identification.
AI for Time Series
Several research groups in the Flanders AI Research Program conduct world-class research on time series, both in the development of algorithms and tools, as in a wide area of application fields. In a recent poll in the Flanders AI community, ‘time series’ came up as the most wanted topic for future workshops or courses. With this seminar series, we bring together researchers that are interested in, or are conducting research related to, time series. We offer a varied program of national and international speakers.
Klik on the separate webinars below to (re)watch the recordings.
Related courses
Summer School on Security and Privacy in the Age of AI
Summerschool - Heverlee - KU Leuven, UGent, VUB, Imec