System state estimation by particle filtering for fault diagnosis and prognosis

Efficient diagnosis and prognosis of system faults depend on the ability to estimate the system state. In many real applications, the system dynamics is typically characterized by transitions among discrete modes of operation, each one giving rise to a specific continuous dynamics of evolution. The estimation of the state of these hybrid dynamic systems is a particularly challenging task because it requires tracking the system dynamics corresponding to the different modes of operation. In the present paper a Monte Carlo-based estimation method, called particle filtering, is illustrated with reference to a case study of a hybrid system from the literature.

[1]  G. Kitagawa.  Non-Gaussian State—Space Modeling of Nonstationary Time Series , 1987 .

[2]  Enrico Zio,et al.  Model-based Monte Carlo state estimation for condition-based component replacement , 2009, Reliab. Eng. Syst. Saf..

[3]  Simon J. Godsill,et al.  On sequential simulation-based methods for Bayesian filtering , 1998 .

[4]  Jeffrey K. Uhlmann,et al.  Unscented filtering and nonlinear estimation , 2004, Proceedings of the IEEE.

[5]  Alfredo Germani,et al.  Filtering of Stochastic Nonlinear Differential Systems via a Carleman Approximation Approach , 2007, IEEE Transactions on Automatic Control.

[6]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[7]  Peng Wang,et al.  DSD: a generic software package for model-based fault diagnosis in dynamic systems , 2002, Reliab. Eng. Syst. Saf..

[8]  Hisashi Tanizaki,et al.  Nonlinear and nonnormal filters using Monte Carlo methods , 1997 .

[9]  Enrico Zio,et al.  Monte Carlo-based filtering for fatigue crack growth estimation , 2009 .

[10]  Nicholas G. Polson,et al.  Particle Filtering , 2006 .

[11]  Enrico Zio,et al.  The cell-to-boundary method in the frame of memorization-based Monte Carlo algorithms. A new computational improvement in dynamic reliability , 1998 .

[12]  Un-Chul Lee,et al.  Development of Fast-Running Simulation Methodology Using Neural Networks for Load Follow Operation , 2002 .

[13]  Enrico Zio,et al.  Monte Carlo approach to PSA for dynamic process systems , 1996 .

[14]  Robert Tibshirani,et al.  An Introduction to the Bootstrap , 1994 .

[15]  A. Germani,et al.  Filtering of Differential Nonlinear Systems via a Carleman Approximation Approach; 44th IEEE Conf. on Decision and Control & European Control Conference (CDC-ECC 2005) , 2005, Proceedings of the 44th IEEE Conference on Decision and Control.

[16]  Simon J. Godsill,et al.  On sequential Monte Carlo sampling methods for Bayesian filtering , 2000, Stat. Comput..

[17]  Sachin C. Patwardhan,et al.  State Estimation and Fault Tolerant Nonlinear Predictive Control of an Autonomous Hybrid System Using Unscented Kalman Filter , 2009 .

[18]  Feng Zhao,et al.  Monitoring and Diagnosis of Hybrid Systems Using Particle Filtering Methods , 2002 .

[19]  Hisashi Tanizaki,et al.  Nonlinear and non-Gaussian state-space modeling with Monte Carlo simulations , 1998 .

[20]  Nando de Freitas,et al.  An Introduction to Sequential Monte Carlo Methods , 2001, Sequential Monte Carlo Methods in Practice.