Test statistics for low complexity change detection in dynamic systems based on averaged filter models
1996 (English)In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Atlanta, GA, USA, 1996, Vol. 5, no Piscataway, NJ, United States, 2845-2848 p.Conference paper (Refereed)
This paper presents a new method to detect and discriminate between abrupt changes in dynamics and sudden changes in disturbance levels in dynamic systems. It is assumed that a normalized least mean square (NLMS) adaptive filter estimates the system. The detection method is based on the observation that the estimated taps behave differently in the two studied events. The convergence behavior of the taps is modeled using averaging theory, giving an exponential convergence behavior for each tap. Kalman filtering techniques, based on this model, are then used in order to design a new detection scheme.
Place, publisher, year, edition, pages
Atlanta, GA, USA, 1996. Vol. 5, no Piscataway, NJ, United States, 2845-2848 p.
, Proceedings of the 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 6)
Adaptive filtering, Algorithms, Convergence of numerical methods, Kalman filtering, Least squares approximations, Mathematical models, Parameter estimation, Signal detection, Statistical tests, Averaging theory, Normalized least mean square (NLMS), Signal processing
IdentifiersURN: urn:nbn:se:kth:diva-55420OAI: oai:DiVA.org:kth-55420DiVA: diva2:471610
Sponsors: IEEE NR 201408052012-01-022012-01-022013-09-05Bibliographically approved