ROBUST SYSTEM-IDENTIFICATION WITH NOISY EXPERIMENTAL-DATA - PROJECTION OPERATOR AND LINEAR ALGORITHMS

In this paper we consider the problem of robust system identification with noisy time or frequency response measurement data. It is shown here that any linear identification algorithm which is convergent in the noise free case can be made robustly convergent in the presence of noise by incorporating a simple projection operator into the algorithm. The computational simplicity and faster rate of convergence distinguish this approach from other existing robustly convergent nonlinear identification techniques.