On the Accuracy Problem in Identification

The estimates obtained from data from an identification experiment depend on a number of items, such as the identification method used, the model structure used and the input signal generation. Effects of these items on the accuracy of the estimates are investigated. Linear, discrete-time systems are treated. Special attention is paid to systems operating in closed loop and to the effects of the feedback on the accuracy. In particular, it is shown for the case of constrained output variance that closed loop experiments can give better accuracy than open loop experiments.