Identification of Hammerstein Systems Using Separable Random Multisines

摘要

The choice of input signal is very important in identification of nonlinear systems. In this paper, it is shown that random multisines with a flat amplitude spectrum are separable. The separability property means that certain conditional expectations are linear and it implies that random multisines easily can be used to obtain accurate estimates of the linear time-invariant part of a Hammerstein system. This is illustrated in a numerical example.