Hierarchical Least Squares Identification for Linear SISO Systems With Dual-Rate Sampled-Data

Least-squares-based iterative identification algorithm for Hammerstein nonlinear systems with non-uniform sampling

“…The simulation results verified the effectiveness of the proposed algorithm. It is worth to point out that the methods in this paper can combine the multi-innovation identification theory [6,13,20,27,33] to study identification problems of other linear or nonlinear systems with coloured noises [7,8,15,25,30].…”

Partially coupled estimation algorithm for discrete-time multiple-input multiple-output systems

“…Remark 6: To distinguish from the coupled least squares algorithm, we term the algorithm in (14)- (19) as the partially coupled recursive least squares (PC-RLS) algorithm because α is a part of the parameters and only the part of parameters are coupled in the algorithm. Remark 7: we can clearly see from the PC-RLS algorithm (14)- (19) that the estimatesθ i (t) and the covariance matrices P i (t) for i = 1, 2, · · · m are updated recursively in there corresponding subsystem i as the increase of time t, while the estimate for α is updated from subsystem 1 to subsystem m at every time instant t.…”

“…In [16], Ding et al presented a hierarchical identification algorithm to estimate the unknown parameters of the lifted state space models for general dual-rate multivariable systems. The hierarchical identification principle also has been used to identify multivariable systems described by the input-output representations, the hierarchical least squares identification methods and the hierarchical gradient-based methods for multivariable systems and their performances were discussed in [17][18][19]. Beside these contributions, there are many other effective methods developed for multivariable system identification, for example, the expectation maximization algorithm and the maximum likelihood approach [20,21], the multi-innovation based algorithms [22][23][24][25][26][27][28], the asymptotic methods [29], the iterative methods [30][31][32][33][34], the correlation technique based methods [35] and the stochastic approximation algorithm [36].…”

Identification of Dual-Rate Sampled Hammerstein Systems with a Piecewise-Linear Nonlinearity Using the Key Variable Separation Technique

“…In the area of dual-rate/multirate sampled system identification, Chen proposed three gradient parameter estimation methods for dual-rate sampled systems [4]; Ding et al explored a hierarchical least squares method for dual-rate sampled systems [6]; Liu et al studied a hierarchical identification method for general dual-rate sampled systems [7]. By using T-S (Takagi and Sugeno) fuzzy models, Huang et al proposed a filtering method for multirate nonlinear sampled-data systems [8].…”