Abstract
In this chapter, the basic principles of identification of dynamic systems from input–output data are reviewed. The various steps of the system identification procedure are emphasized. Algorithms which were successfully used for identification of active vibration control systems are presented.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Linear feedback regulator design will require also the model of the disturbance. Linear feedforward compensator design will require in addition a model of the primary path. Design of adaptive regulators or of feedforward compensators require only the model of the secondary path.
- 2.
The parameter estimation error induced by the measurement noise is called “bias”.
- 3.
Routines for generating PRBS can be downloaded from the websites: http://www.landau-adaptivecontrol.org and http://www.gipsa-lab.grenoble-inp.fr/~ioandore.landau/identificationandcontrol/.
- 4.
Functions prbs.m and prbs.c available on the websites: http://www.landau-adaptivecontrol.org and http://www.gipsa-lab.grenoble-inp.fr/ ioandore.landau/identificationandcontrol/ allow to generate PRBS of various lengths and magnitudes.
- 5.
Routines corresponding to this method in MATLAB (estorderiv.m) and Scilab (estorderiv.sci) can be downloaded from the websites: http://www.landau-adaptivecontrol.org and http://www.gipsa-lab.grenoble-inp.fr/ ioandore.landau/identificationandcontrol/.
- 6.
Routines for these algorithms can be downloaded from the websites: http://www.landau-adaptivecontrol.org and http://www.gipsa-lab.grenoble-inp.fr/~ioandore.landau/identificationandcontrol/.
- 7.
The interactive stand alone software iReg (http://tudor-bogdan.airimitoaie.name/ireg.html) provides parameter estimations algorithms for all the mentioned “plant \(+\) noise” structures as well as an automated identification procedure covering all the stages of system identification. It has been extensively used for identification of active vibration control systems.
- 8.
Routines corresponding to this validation method in MATLAB and Scilab can be downloaded from the websites: http://www.landau-adaptivecontrol.org and http://www.gipsa-lab.grenoble-inp.fr/ ioandore.landau/identificationandcontrol/.
- 9.
Conversely, for Gaussian data, uncorrelation implies independence. In this case, \(RN(i)=0, i \ge 1\) implies independence between \(\varepsilon (t), \varepsilon (t-1) \ldots ,\) i.e., the sequence of residuals \(\{ \varepsilon (t) \}\) is a Gaussian white noise.
References
Landau I, Zito G (2005) Digital control systems - design, identification and implementation. Springer, London
Ljung L, Söderström T (1983) Theory and practice of recursive identification. The MIT Press, Cambridge
Ljung L (1999) System identification - theory for the user, 2nd edn. Prentice Hall, Englewood Cliffs
Soderstrom, T., Stoica, P.: System Identification. Prentice Hall (1989)
Duong HN, Landau ID (1996) An IV based criterion for model order selection. Automatica 32(6):909–914
Duong HN, Landau I (1994) On statistical properties of a test for model structure selection using the extended instrumental variable approach. IEEE Trans Autom Control 39(1):211–215. doi:10.1109/9.273371
Landau ID, Lozano R, M’Saad M, Karimi A (2011) Adaptive control, 2nd edn. Springer, London
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2017 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Landau, I.D., Airimitoaie, TB., Castellanos-Silva, A., Constantinescu, A. (2017). Identification of the Active Vibration Control Systems—The Bases. In: Adaptive and Robust Active Vibration Control. Advances in Industrial Control. Springer, Cham. https://doi.org/10.1007/978-3-319-41450-8_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-41450-8_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-41449-2
Online ISBN: 978-3-319-41450-8
eBook Packages: EngineeringEngineering (R0)