An approach is proposed for obtaining estimates of the basic (disaggregated) series, xi, when only an aggregate series, y r , of k period non-overlapping sums of xi's is available. The approach is based on casting the problem in a dynamic linear model form. Then estimates of xi can be obtained by ap
Dynamical systems identification from time-series data: A hankel matrix approach
β Scribed by D. Lai; G. Chen
- Publisher
- Elsevier Science
- Year
- 1996
- Tongue
- English
- Weight
- 761 KB
- Volume
- 24
- Category
- Article
- ISSN
- 0895-7177
No coin nor oath required. For personal study only.
π SIMILAR VOLUMES
A novel procedure is developed for the identi"cation of linear discrete models of dynamical systems from noisy data. Of particular interest is the application of the methodology to time-varying systems. The procedure is based on a representation of the governing di!erential equations with respect to
This paper proposes a new type of time series model to identify the characteristics of non-linear dynamical structures. The model simultaneously accommodates three kinds of output signals, acceleration, velocity and displacement. This model is more sensitive to non-linearity than models utilising on
The program presented computes all the Lyapunov exponents of an unknown dynamical system from a time series. The method used is based on a fitting of the time series with an analytical function through a least square minimizatior, after which the Lyapunov exponents are determined from the stability