ABSTRACT I I The system identification procedure is a powerful andflexible tool for the modeling of dynamic systems. Thispaper implements the theory of parametric identlfidatlon in order to estimate a valid model of a flexible roboticarm. For this purpose experimental data Is used for the,stimation of ARMAX SISO mocjels. A two-stagesIdentification procedure (non-parametric & parametric)provides an Insight about the system underidentification. In the first stage, known signal analysismethods are applied (correlation-spectral analysis) forthe estimation of frequencies and frequency response.and in the second stage, the estimation of ARMAXmodels is performed in order to fit a transfer functionmodel to collected input-output data set. For theestimation of model's coefficients, use of EvolutionaryAlgorithms is implemented. l INTRODUCTIONThe essential concept behind System Identification relies on the simple principle that itis impossible to sit ona desk and figure out how the world works: italso has tobe studied. In an engineering point of view this meansthat. during a modeling process, the use of experimental
[1]
Thomas Bäck,et al.
Evolutionary algorithms
,
1992,
SIGB.
[2]
Michael de la Maza,et al.
Book review: Genetic Algorithms + Data Structures = Evolution Programs by Zbigniew Michalewicz (Springer-Verlag, 1992)
,
1993
.
[3]
Zbigniew Michalewicz,et al.
Genetic Algorithms + Data Structures = Evolution Programs
,
1996,
Springer Berlin Heidelberg.
[4]
Gwilym M. Jenkins,et al.
Time series analysis, forecasting and control
,
1972
.
[5]
Petre Stoica,et al.
Decentralized Control
,
2018,
The Control Systems Handbook.
[6]
Kotaro Hirasawa,et al.
A homotopy approach to improving PEM identification of ARMAX models
,
2001,
Autom..
[7]
Lennart Ljung,et al.
Modeling Of Dynamic Systems
,
1994
.