WSEAS Transactions on Systems
Print ISSN: 1109-2777, E-ISSN: 2224-2678
Volume 13, 2014
Analytic Local Linearization Particle Filter for Bayesian State Estimation in Nonlinear Continuous Process
Authors: ,
Abstract: State estimation is a prerequisite for monitoring, control and fault diagnosis of many processes. Dynamic model based state estimation techniques are used for monitoring the state variables. Particle filter have been widely used to estimate the state of nonlinear and non-Gaussian system. Particle filters require a proposal distribution but the choice of proposal distribution is the key design issue. In this paper, the extended Kalman filter (EKF) which is based on analytic local linearization is used to generate a proposal distribution for the particle filter. The efficacy of this local linearization particle filter (LLPF) is demonstrated via application to a simulated nonlinear continuous stirred tank reactor (CSTR) and the results are compared with the sampling importance resampling (SIR) particle filter.
Search Articles
Keywords: State estimation, Particle filter, Non-Gaussian, Proposal distribution, Local linearization particle filter, Sampling importance resampling
Pages: 154-163
WSEAS Transactions on Systems, ISSN / E-ISSN: 1109-2777 / 2224-2678, Volume 13, 2014, Art. #14