System identification using measurements subject to stochastic time jitter [Elektronisk resurs] / Frida Eng, Fredrik Gustafsson

• When the sensors readings are perturbed by an unknown stochastic time jitter, classical system identification algorithms based on additive amplitude perturbations will give biased estimates. We here outline the maximum likelihood procedure, for the case of both time and amplitude noise, in the frequency domain, based on the measurement DFT. The method directly applies to output error continuous time models, while a simple sinusoid in noise example is used to illustrate the bias removal of the proposed method. 

Indexterm och SAB-rubrik

System identification Nonuniform jitter sampling Frequency domain