Robust Multimodel Identification of LPV Systems With Missing Observations Based on t-Distribution

Liu, Xin; Yang, Xianqiang; Peng, Zhu; Wang, Yan Bo

doi:10.1109/tsmc.2019.2949087

Cited by 14 publications

(5 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…19 As an alternative, Student's t distribution can resist the influence of outliers on parameter identification, because Student's t distribution has a more enormous tail than Gaussian distribution by changing the degree of freedom (DOF). 20,21 When DOF is smaller, the Student's t distribution curve is smoother and the tail of both sides is higher. On the contrary, when DOF is larger, the Student's t distribution is closer to the standard Gaussian distribution.…”

Section: Introductionmentioning

confidence: 99%

“…However, this may lead to information loss, which is not conducive to parameter estimation 19 . As an alternative, Student's

t

distribution can resist the influence of outliers on parameter identification, because Student's

t

distribution has a more enormous tail than Gaussian distribution by changing the degree of freedom (DOF) 20,21 . When DOF is smaller, the Student's

t

distribution curve is smoother and the tail of both sides is higher.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Expectation‐maximization algorithm for bilinear state‐space models with time‐varying delays under non‐Gaussian noise

Wang

Xiong

2023

Adaptive Control & Signal

View full text Add to dashboard Cite

SummaryIn this paper, the parameter identification of bilinear state‐space model (SSM) in the presence of random outliers and time‐varying delays is investigated. Under the basis of the observable canonical form of the bilinear model, the system output can be written as a regressive form, and a bilinear state observer is applied to estimate the unknown states. To eliminate the influence of outliers and time‐varying delays on parameter estimation, we employ the Student's distribution to deal with the measurement noise and use a first‐order Markov chain to model the delays. In the framework of expectation‐maximization (EM) algorithm, the unknown parameters, delays, noise variance, states and transition probability matrix can be estimated iteratively. A numerical simulation and a continuous stirred tank reactor (CSTR) process demonstrate that the proposed algorithm has good immunity against outliers and time‐varying delays and offers good estimation accuracy for the bilinear SSM.

show abstract

Section: Introductionmentioning

confidence: 99%

“…However, this may lead to information loss, which is not conducive to parameter estimation 19 . As an alternative, Student's

t

distribution can resist the influence of outliers on parameter identification, because Student's

t

distribution has a more enormous tail than Gaussian distribution by changing the degree of freedom (DOF) 20,21 . When DOF is smaller, the Student's

t

distribution curve is smoother and the tail of both sides is higher.…”

Section: Introductionmentioning

confidence: 99%

Expectation‐maximization algorithm for bilinear state‐space models with time‐varying delays under non‐Gaussian noise

Wang

Xiong

2023

Adaptive Control & Signal

View full text Add to dashboard Cite

show abstract

“…While LPV system identification methods have matured over the last 15 years with many competitive approaches, e.g. [3–10] to mention a few, conversion methods of existing NL/TV models of applications has seen only moderate progress. As in practice, often high‐fidelity models of the target application are available due to the development and design process, e.g.…”

Section: Introductionmentioning

confidence: 99%

Affine linear parameter‐varying embedding of non‐linear models with improved accuracy and minimal overbounding

Sadeghzadeh

Sharif

Tóth

2020

IET Control Theory & Appl

View full text Add to dashboard Cite

In this study, automated generation of linear parameter‐varying (LPV) state‐space models to embed the dynamical behaviour of non‐linear systems is considered, focusing on the trade‐off between scheduling complexity and model accuracy and the minimisation of the conservativeness of the resulting embedding. The LPV state‐space model is synthesised with affine scheduling dependency, while the scheduling variables themselves are non‐linear functions of the state and input variables of the original system. The method allows to generate complete or approximative embedding of the non‐linear system model and also it can be used to minimise the complexity of existing LPV embeddings. The capabilities of the method are demonstrated on simulation examples and also in an empirical case study where the first‐principle motion model of a three degrees of freedom (3DOF) control moment gyroscope is converted by the proposed method to an LPV model with low scheduling complexity. Using the resulting model, a gain‐scheduled controller is designed and applied on the gyroscope, demonstrating the efficiency of the developed approach.

show abstract

“…While LPV system identification methods have matured over the last 15 years with many competitive approaches, e.g. ; Goos and Pintelon (2016); Laurain et al (2012); ; Zhao et al (2012); Bachnas et al (2014); Toth (2010); Liu et al (2019) to mention a few, conversion methods of existing NL/TV models of applications has seen only moderate progress. As in practice, often high-fidelity models of the target application are available due to the development and design process, e.g.…”

Section: Introductionmentioning

confidence: 99%

Affine Linear Parameter-Varying Embedding of Nonlinear Models with Improved Accuracy and Minimal Overbounding

Sadeghzadeh¹,

Sharif²,

Tóth³

2020

Preprint

View full text Add to dashboard Cite

In this paper, automated generation of linear parameter-varying (LPV) state-space models to embed the dynamical behavior of nonlinear systems is considered, focusing on the trade-off between scheduling complexity and model accuracy and on the minimization of the conservativeness of the resulting embedding. The LPV state-space model is synthesized with affine scheduling dependency, while the scheduling variables themselves are nonlinear functions of the state and input variables of the original system. The method allows to generate complete or approximative embedding of the nonlinear system model and also it can be used to minimize complexity of existing LPV embeddings. The capabilities of the method are demonstrated on simulation examples and also in an empirical case study where the first-principle motion model of a 3-DOF control moment gyroscope is converted by the proposed method to LPV model with low scheduling complexity. Using the resulting model, a gain-scheduled controller is designed and applied on the gyroscope, demonstrating the efficiency of the developed approach.

show abstract

Robust Multimodel Identification of LPV Systems With Missing Observations Based on t-Distribution

Cited by 14 publications

References 29 publications

Expectation‐maximization algorithm for bilinear state‐space models with time‐varying delays under non‐Gaussian noise

Expectation‐maximization algorithm for bilinear state‐space models with time‐varying delays under non‐Gaussian noise

Affine linear parameter‐varying embedding of non‐linear models with improved accuracy and minimal overbounding

Affine Linear Parameter-Varying Embedding of Nonlinear Models with Improved Accuracy and Minimal Overbounding

Contact Info

Product

Resources

About