Experiment design

The aim of experiment design

The data, used for the identification of a model, are always corrupted by some disturbances such as noise. The consequence is the existence of a variance error on the identified model. The variance error depends on the number of data and on the choice of the excitation.

Experiment design is the scientific field dedicated to the design a particular excitation signal for the system to be identified so that the experiment run with this signal gives a user-specific model accuracy (i.e., a given variance error magnitude).

Related journal papers

Related conference papers

  • Federico Morelli, Xavier Bombois, Håkan Hjalmarsson, Laurent Bako, Kévin Colin. Optimal Experiment Design for the Identification of One Module in the Interconnection of Locally Controlled Systems. Presented at IEEE 18th European Control Conference (ECC), Napoli, Italy. Published in the proceedings pp 363-368. Open access: https://hal.archives-ouvertes.fr/hal-02063406. 2019

  • Kévin Colin, Fabricio Saggin, Christophe Le Blanc, Xavier Bombois, Anton Korniienko, Gérard Scorletti. Identification Based Approach for Electrical Coupling Compensation in a MEMS Gyroscope. Presented at 2019 IEEE International Symposium on Inertial Sensors and Systems, Naples, USA. Published in the proceedings pp 351-356. Open access: https://hal.archives-ouvertes.fr/hal-02174925. 2019