Estimation of States of Nonlinear Systems using a Particle Filter

Imtiaz, Syed; Roy, Kallol; Huang, Biao; Shah, Sirish L.; Jampana, Phanindra

doi:10.1109/icit.2006.372687

Cited by 27 publications

(24 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, a prior that spans the support of the likelihood function needs to be chosen for convergence of the particle filter approximations (Doucet et al, 2001). Some of these implementational issues, including suggestions for tuning the state and measurement noise, are discussed in Imtiaz et al (2006).…”

Section: Joint Distribution Of X T Y Tmentioning

confidence: 99%

“…A thorough discussion of the state estimation approaches is beyond the scope of this article, however, a good review of currently popular state estimation procedures is provided in Rawlings and Bakshi (2006) and in Soroush (1998), and the references therein. Practical issues in implementing particle filters are discussed in Imtiaz et al (2006). This article focuses on parameter estimation of models of the form presented above.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A particle filter approach to identification of nonlinear processes under missing observations

Gopaluni

2008

Can J Chem Eng

112

View full text Add to dashboard Cite

A novel maximum likelihood solution to the problem of identifying parameters of a nonlinear model under missing observations is presented. If the observations are missing, then it is difficult to build a partial likelihood function consisting of only the available observations. Hence, an expectation-maximization (EM) algorithm, which uses the expected value of the complete log-likelihood function including the missing observations, is developed. The expected value of the complete log-likelihood (E-step) in the EM algorithm is approximated using particle filters and smoothers. New expressions for particle filters and smoothers under missing observations are derived. In order to reduce the variance on the smoothed states, a point-wise (as opposed to path-based) state estimation procedure is used. The maximization step (M-step) in the EM algorithm is performed using standard optimization routines. The proposed nonlinear identification approach is illustrated through numerical examples.On présente une nouvelle solution de vraisemblance maximum au problème d'identification des paramètres d'un modèle non linéaire avec des observations manquantes. Si des observations manquent, il est alors difficile d'établir une fonction de vraisemblance partielle seulement sur les observations disponibles. En conséquence, on a mis au point un algorithme de maximation des attentes (EM), qui utilise la valeur attendue de la fonction de vraisemblance logarithmique complète incluant les observations manquantes. La valeur attendue de la vraisemblance logarithmique complète (étape E) dans l'algorithme EM est approchéeà l'aide de filtres et d'algorithmes de lissage. De nouvelles expressions pour les filtres et les algorithmes de lissage avec des observations manquantes sont calculées. Afin de réduire la variance desétats lissés, on fait appelà une méthode d'estimation desétats ponctuels (par oppositionà une méthode basée sur les trajectoires). L'étape de maximisation (étape M) dans l'algorithme EM est réalisée au moyen de méthodes d'optimisation standards. La méthode d'identification non linéaire proposée est illustrée par des exemples numériques.

show abstract

Section: Joint Distribution Of X T Y Tmentioning

confidence: 99%

mentioning

confidence: 99%

A particle filter approach to identification of nonlinear processes under missing observations

Gopaluni

2008

Can J Chem Eng

112

View full text Add to dashboard Cite

show abstract

“…After resampling, the weights of the particles are reset to

\frac{1}{N_{s}}

. This is an optional step to avoid the collapsing of particles to one point …”

Section: Methodsmentioning

confidence: 99%

Dynamic Risk Assessment of a Nonlinear Non‐Gaussian System Using a Particle Filter and Detailed Consequence Analysis

2015

View full text Add to dashboard Cite

This paper presents a dynamic risk assessment using a comprehensive economic consequence methodology in combination with a multivariate model‐based fault detection method. The proposed approach aims to calculate process risk dynamically at each sampling instant, and also to identify and screen the faults that are not hazardous. The approach relies on a particle filter combined with a comprehensive economic consequence methodology. The fault detection module uses a state space model of the process plant and a particle filter algorithm that calculates the probability of the fault. The output of this module is then combined with the consequence module, which uses loss functions to relate process deviations to economic losses. The consequence module identifies, quantifies, and integrates losses for a given scenario. Combining the two modules for risk assessment makes this approach more reliable in the analysis of realistic nonlinear process systems, and improves decision‐making for process design and risk management.

show abstract

“…To overcome the limitations of KF and of EKF the Particle Filter (PF) has been proposed [23][24][25]. It has been shown that PFbased state estimation is suitable for industrial systems, subject to non-Gaussian noise, such as the CSTR system (continuously stirred reactor), and the four-tank system [26]. Moreover, PF-based state estimation has been proposed for control and fault diagnosis tasks in mechanical/robotic systems [27][28][29][30][31][32].…”

Section: Introductionmentioning

confidence: 99%

Particle and Kalman filtering for state estimation and control of DC motors

Rigatos¹

2009

ISA Transactions

View full text Add to dashboard Cite

Estimation of States of Nonlinear Systems using a Particle Filter

Cited by 27 publications

References 8 publications

A particle filter approach to identification of nonlinear processes under missing observations

A particle filter approach to identification of nonlinear processes under missing observations

Dynamic Risk Assessment of a Nonlinear Non‐Gaussian System Using a Particle Filter and Detailed Consequence Analysis

Particle and Kalman filtering for state estimation and control of DC motors

Contact Info

Product

Resources

About