Experiment design in identification for control
FP4 — Training and Mobility of Researchers
- Duration
- 1996-10-07 → 1997-10-06
- EU contribution
- —
- Participants
- 2
- Scheme
- RGI
Lines connect the coordinator with its partners. CORDIS does not always give exact coordinates for projects before 2014. These points are placed at city or country level.
Project objective
System identification deals with the estimation of models of dynamical systems from data measured on these systems. When a nodel-based controller is used, it has recently been observed that significant improvements in performance can be achieved by letting the design of the identification experiment be guided by the control objective. This has given rise to an intense new research activity in identification for control" at CESAME/UCL, one of the world leaders in this field The purpose of this project is to propose a sequential design of experiments approach, building on the concepts of dual control, a methodology which leads to an optimal compromise between the antagonistic objectives of regulation and identifi- cation. The main difficulty is the huge computational complexity of the solution. The thesis of C. Kulcsar (1) has led to suboptimal but significantly simpler solu- tions to the dual control problem, and the project aims at linking these solution techniques to identification for control. (1) C. Kulcsar, "Planification d'expirience et commande duale", Thhse de Doctorat en Sciences, Universiti de Paris-Sud Orsay, Laboratoire des Signaux et Systhmes, 1995. "
Original text from CORDIS.
Participants
Links
Data: CORDIS, © European Union