State estimation of nonlinear system through Particle Filter based Recurrent Neural Networks

Author

Yadaiah, N. ; Kumar, A. Suresh ; Bapi, Raju S. ; Roopchandan, M.

Author_Institution

Dept. of Electr. & Electron. Eng., JNTUH Coll. of Eng., Hyderabad, India

fYear

2011

fDate

22-24 Sept. 2011

Firstpage

307

Lastpage

310

Abstract

This paper presents a Hybrid Particle Filter based RNN method for state estimation of non-linear dynamical system with knowledge of its input and output measurements. Particle filters are sequential Monte Carlo methods based on point mass (or particle) representations of probability densities, which is used to train Recurrent Neural Networks for estimation problems. The performance this method is compared with EKF based estimation and RNN based estimation. An Induction motor is considered as typical non-linear system and is implemented in MATLAB environment.

Keywords

Kalman filters; Monte Carlo methods; induction motors; machine control; nonlinear dynamical systems; particle filtering (numerical methods); recurrent neural nets; state estimation; EKF based estimation; MATLAB; hybrid particle filter based RNN method; induction motor; input measurements; nonlinear dynamical system; output measurements; particle filter based recurrent neural networks; point mass; probability densities; sequential Monte Carlo methods; state estimation; Algorithm design and analysis; Particle filters; Recurrent neural networks; State estimation; Torque; Vectors; Hybrid Particle filter; Nonlinear system; Recurrent Neural Networks; State Estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Recent Advances in Intelligent Computational Systems (RAICS), 2011 IEEE

Conference_Location

Trivandrum

Print_ISBN

978-1-4244-9478-1

Type

conf

DOI

10.1109/RAICS.2011.6069324

Filename

6069324