Recursive identification for Wiener non‐linear systems with non‐stationary disturbances

Dong, Shijian; Zhang, Wen-An; Chen, Bo

doi:10.1049/iet-cta.2018.6413

Cited by 11 publications

(6 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Dong et al developed the recursive least squares algorithm for the Wiener nonlinear systems based on the auxiliary model idea. 28 Du et al investigated the online recursive identification approach to identifying the continuous-time switched nonlinear state-space models and proposed the subspace-based method to estimate the switching signal. 29 Zhang et al derived the recursive projection algorithm to identify the finite impulse response systems with binary-valued observations.…”

Section: Introductionmentioning

confidence: 99%

Overall recursive least squares and overall stochastic gradient algorithms and their convergence for feedback nonlinear controlled autoregressive systems

Wei

Xiao

et al. 2022

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

This article deals with the problems of the parameter estimation for feedback nonlinear controlled autoregressive systems (i.e., feedback nonlinear equation‐error systems). The bilinear‐in‐parameter identification model is formulated to describe the feedback nonlinear system. An overall recursive least squares algorithm is developed to handle the difficulty of the bilinear‐in‐parameter. For the purpose of avoiding the heavy computational burden, an overall stochastic gradient algorithm is deduced and the forgetting factor is introduced to improve the convergence rate. Furthermore, the convergence analysis of the proposed algorithms are established by means of the stochastic process theory. The effectiveness of the proposed algorithms are illustrated by the simulation example.

show abstract

Section: Introductionmentioning

confidence: 99%

Overall recursive least squares and overall stochastic gradient algorithms and their convergence for feedback nonlinear controlled autoregressive systems

Wei

Xiao

et al. 2022

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

show abstract

“…System identification and model parameter estimation are basic in controller design, dynamic systems modeling, and signal processing 1,2 . Different identification methods have been proposed for linear systems and nonlinear systems, such as the least squares methods, 3‐5 the maximum likelihood methods, 6‐8 the gradient methods, 9 the orthogonal matching pursuit methods, 10 and the robust identification methods 11,12 . However, most of these methods assumed that the input–output data are available at every sampling instant.…”

Section: Introductionmentioning

confidence: 99%

“…1,2 Different identification methods have been proposed for linear systems and nonlinear systems, such as the least squares methods, [3][4][5] the maximum likelihood methods, [6][7][8] the gradient methods, 9 the orthogonal matching pursuit methods, 10 and the robust identification methods. 11,12 However, most of these methods assumed that the input-output data are available at every sampling instant. In other words, the outputs and the inputs have the same sampling rates.…”

Section: Introductionmentioning

confidence: 99%

Maximum likelihood hierarchical least squares‐based iterative identification for dual‐rate stochastic systems

2020

Adaptive Control & Signal

166

104

View full text Add to dashboard Cite

For a dual-rate sampled-data stochastic system with additive colored noise, a dual-rate identification model is obtained by using the polynomial transformation technique, which is suitable for the available dual-rate measurement data. Based on the obtained model, a maximum likelihood least squares-based iterative (ML-LSI) algorithm is presented for identifying the parameters of the dual-rate sampled-data stochastic system. In order to improve the computation efficiency of the algorithm, the identification model of a dual-rate sampled-data stochastic system is divided into two subidentification models with smaller dimensions and fewer parameters, and a maximum likelihood hierarchical least squares-based iterative (H-ML-LSI) algorithm is proposed for these subidentification models by using the hierarchical identification principle. The simulation results indicate that the proposed algorithms are effective for identifying dual-rate sampled-data stochastic systems and the H-ML-LSI algorithm has a higher computation efficiency than the ML-LSI algorithm.

show abstract

“…To deal with time-varying disturbance, forgetting factors were suggested to establish recursive identification algorithms [29][30][31] which could result in the asymptotic convergence of model parameter estimation under such disturbance. Nonetheless, a constant forgetting factor may fail to yield good accuracy in estimating the system model parameters, and therefore, variable forgetting factors were proposed to tackle different types of time-varying load disturbances [32][33][34][35]. However, these recursive identification methods based on forgetting factors could not be used to identify the delay parameter for a time-delay system.…”

Section: Introductionmentioning

confidence: 99%

Parametric identification of output error model for sampled systems with integer‐type time delay subject to load disturbance with unknown dynamics

Pandey

Liu

Wang

2021

IET Control Theory & Appl

View full text Add to dashboard Cite

In this paper, a bias-eliminated output error (OE) model identification method is proposed for single-input-single-output sampled systems with integer-type time delay subject to load disturbance with unknown dynamics. By viewing the load disturbance response as a time-variant parameter, an iterative least-squares identification algorithm is established to estimate the rational model parameters together with an integer-type delay parameter, while the disturbance response could be simultaneously estimated. To overcome the adverse effect of stochastic noise involved with output measurement, an auxiliary model is constructed to predict the noise-free system response. Moreover, a set of adaptive forgetting factors is introduced to expedite the convergence rate of model parameter estimation and the tracking performance of load disturbance response, respectively. In addition, a monotonically rising profile for evaluating the delay parameter is proposed for implementing the above iterative least-squares algorithm, in order to avoid the occurrence of multiple local minima of the loss function for model fitting. The asymptotic convergence on estimating the rational model parameters together with the delay parameter is analysed with a proof. An illustrative example is given to demonstrate the effectiveness and advantage of the proposed method.

show abstract

Recursive identification for Wiener non‐linear systems with non‐stationary disturbances

Cited by 11 publications

References 44 publications

Overall recursive least squares and overall stochastic gradient algorithms and their convergence for feedback nonlinear controlled autoregressive systems

Overall recursive least squares and overall stochastic gradient algorithms and their convergence for feedback nonlinear controlled autoregressive systems

Maximum likelihood hierarchical least squares‐based iterative identification for dual‐rate stochastic systems

Parametric identification of output error model for sampled systems with integer‐type time delay subject to load disturbance with unknown dynamics

Contact Info

Product

Resources

About