Instrumental variable methods for closed-loop system identification (Q1764042)

In many industrial processes, safety and production restrictions are often strong reasons for not allowing identification experiments in open-loop. In such situations experimental data only can be obtained under closed-loop conditions. The main difficulty in closed-loop identification is due to the correlation between the disturbances and the control signal induced by the loop. Several classical alternatives are available to cope with this problem. Some particular versions of these methods have to be developed in the area of control relevant identification. The authors propose several bootstrap methods for approximating the required information from measurement data. Comparison between the different methods is studied on a simulation example.