» Download Article

Authors
Frida Eng; Fredrik Gustafsson

Identifier
10.3182/20060329-3-AU-2901.00094

Index Terms
system identification,stochastic systems,least-squares estimation,maximum likelihood,frequency domain

Abstract
This work investigates how stochastic unmeasureable sampling jitter noise affects the result of system identification, and proposes a modification of known approaches to mitigate the effects of sampling jitter. By just assuming conventional additive measurement noise, the analysis shows that the identified model will get a bias in the transfer function amplitude that increases for higher frequencies. A frequency domain approach with a continuous time system model allows an analysis framework for sampling jitter noise. This leads to a bias compensated (weighted) least squares algorithm. A continuous time output error model is used for numerical illustration.

References

[1] Bilinskis, I. and A. Mikelsons (1992). Randomized
    Signal Processing. Prentice Hall.
[2] Eng, F. and F. Gustafsson (2005). System identification
     using measurements subject to
    stochastic time jitter. In: International Federation
     of Automatic Control (IFAC) World
    Congress. IFAC. Prague.
[3] Eng, F., F. Gustafsson and F. Gunnarsson (2005).
    Frequency domain analysis in the case of
    stochastic sampling times. Submitted to IEEE
    Transactions on Signal Processing.
[4] Gillberg, J. and F. Gustafsson (2005). Frequency-domain
     continuous time AR modeling using
     non-uniformly sampled measurments. In:
    IEEE Conference on Acoustics, Speech and
    Signal Processing (ICASSP). IEEE. Philadelphia.
    
[5] Gillberg, J. and L. Ljung (2005). Frequency-domain
     identification of continuous-time output
     error models from sampled data. In: IFAC
    World Congress.
[6] Ljung, L. (1999). System identification, Theory
    for the user. second ed., Prentice Hall. Englewood
     Cliffs, NJ.
[7] Marvasti, Farokh, Ed. (2001). Nonuniform Sampling:
     Theory and Practice. Kluwer.
[8] Pintelon, R. and J. Schoukens (2001). System
     Identification: A Frequency Domain Approach
    .
[9] Pintelon, R. and J. Schoukens (2005). ML identification
     of closed-loop systems in a specified
    frequency band. In: IFAC World Congress.
[10] Schoukens, J., Y. Rolain and R. Pintelon (2005).
     Analysis of windowing/leakage effects in frequency
      response function measurements. In:
     IFAC World Congress.
[11] Souders, T. M., D. R. Flach, C. Hagwood and G. L.
     Yang (1990). The effects of timing jitter in
     sampling systems. IEEE Transactions on Instrumentation
      and Measurements.