Bayesian Filters for Parameter Identification of Duffing Oscillator

Vikas Kumar Mishra; Rahul Radhakrishnan; Abhinoy Kumar Singh; Shovan Bhaumik

doi:10.1016/j.ifacol.2018.05.068

Bayesian Filters for Parameter Identification of Duffing Oscillator

Vikas Kumar Mishra, Rahul Radhakrishnan, Abhinoy Kumar Singh, Shovan Bhaumik

Research output: Contribution to journal › Article › peer-review

7 Scopus citations

Abstract

In this paper, a joint state and parameter estimation problem of Duffing oscillator is explored using Bayesian filters, where the parameter to be identified is considered as an additional state variable. From a variety of Bayesian filters, the unscented Kalman filter (UKF), cubature Kalman filter (CKF) and Gauss-Hermite filter (GHF) are chosen for solving this problem. The performance of these filters are compared in terms of the root mean square error (RMSE) calculated over a specified number of Monte-Carlo runs. From simulation results, it is found that the accuracy of CKF and GHF are almost same while the computational time for GHF is almost three times higher.

Original language	English
Pages (from-to)	425-430
Number of pages	6
Journal	5th IFAC Conference on Advances in Control and Optimization of Dynamical Systems ACODS 2018
Volume	51
Issue number	1
DOIs	https://doi.org/10.1016/j.ifacol.2018.05.068
State	Published - 1 Jan 2018
Externally published	Yes

Keywords

Duffing oscillator
Higher order Gauss-Laguerre quadrature rule
Nonlinear filtering
Third-degree spherical cubature rule
multidimensional Gauss-Hermite quadrature rule

ASJC Scopus subject areas

Control and Systems Engineering

Access to Document

10.1016/j.ifacol.2018.05.068

Cite this

@article{3082c128189e4f17ab0177a7604a9c52,

title = "Bayesian Filters for Parameter Identification of Duffing Oscillator",

abstract = "In this paper, a joint state and parameter estimation problem of Duffing oscillator is explored using Bayesian filters, where the parameter to be identified is considered as an additional state variable. From a variety of Bayesian filters, the unscented Kalman filter (UKF), cubature Kalman filter (CKF) and Gauss-Hermite filter (GHF) are chosen for solving this problem. The performance of these filters are compared in terms of the root mean square error (RMSE) calculated over a specified number of Monte-Carlo runs. From simulation results, it is found that the accuracy of CKF and GHF are almost same while the computational time for GHF is almost three times higher.",

keywords = "Duffing oscillator, Higher order Gauss-Laguerre quadrature rule, Nonlinear filtering, Third-degree spherical cubature rule, multidimensional Gauss-Hermite quadrature rule",

author = "Mishra, {Vikas Kumar} and Rahul Radhakrishnan and Singh, {Abhinoy Kumar} and Shovan Bhaumik",

note = "Publisher Copyright: {\textcopyright} 2018",

year = "2018",

month = jan,

day = "1",

doi = "10.1016/j.ifacol.2018.05.068",

language = "English",

volume = "51",

pages = "425--430",

journal = "5th IFAC Conference on Advances in Control and Optimization of Dynamical Systems ACODS 2018",

issn = "2405-8963",

publisher = "IFAC Secretariat",

number = "1",

}

TY - JOUR

T1 - Bayesian Filters for Parameter Identification of Duffing Oscillator

AU - Mishra, Vikas Kumar

AU - Radhakrishnan, Rahul

AU - Singh, Abhinoy Kumar

AU - Bhaumik, Shovan

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In this paper, a joint state and parameter estimation problem of Duffing oscillator is explored using Bayesian filters, where the parameter to be identified is considered as an additional state variable. From a variety of Bayesian filters, the unscented Kalman filter (UKF), cubature Kalman filter (CKF) and Gauss-Hermite filter (GHF) are chosen for solving this problem. The performance of these filters are compared in terms of the root mean square error (RMSE) calculated over a specified number of Monte-Carlo runs. From simulation results, it is found that the accuracy of CKF and GHF are almost same while the computational time for GHF is almost three times higher.

AB - In this paper, a joint state and parameter estimation problem of Duffing oscillator is explored using Bayesian filters, where the parameter to be identified is considered as an additional state variable. From a variety of Bayesian filters, the unscented Kalman filter (UKF), cubature Kalman filter (CKF) and Gauss-Hermite filter (GHF) are chosen for solving this problem. The performance of these filters are compared in terms of the root mean square error (RMSE) calculated over a specified number of Monte-Carlo runs. From simulation results, it is found that the accuracy of CKF and GHF are almost same while the computational time for GHF is almost three times higher.

KW - Duffing oscillator

KW - Higher order Gauss-Laguerre quadrature rule

KW - Nonlinear filtering

KW - Third-degree spherical cubature rule

KW - multidimensional Gauss-Hermite quadrature rule

UR - http://www.scopus.com/inward/record.url?scp=85048705921&partnerID=8YFLogxK

U2 - 10.1016/j.ifacol.2018.05.068

DO - 10.1016/j.ifacol.2018.05.068

M3 - Article

AN - SCOPUS:85048705921

SN - 2405-8963

VL - 51

SP - 425

EP - 430

JO - 5th IFAC Conference on Advances in Control and Optimization of Dynamical Systems ACODS 2018

JF - 5th IFAC Conference on Advances in Control and Optimization of Dynamical Systems ACODS 2018

IS - 1

ER -

Bayesian Filters for Parameter Identification of Duffing Oscillator

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this