A novel intelligent particle filter for process monitoring

Abstract

Particle filter (PF) serves as an effective method applied to the fault diagnosis of nonlinear and non-Gaussian systems. However, the result of state estimation is influenced by the particle impoverishment problem which is common in the typical PF algorithm. Based on the analysis of the PF algorithm, the general particle impoverishment problem is attributed to the deficiency of particle diversity. In this paper a novel intelligent particle filter (NIPF) is designed to deal with the problem of particle impoverishment by means of the genetic and adaptive strategy. The general PF can be regarded as a particular instance of NIPF. The experiment on the vertically falling body model shows that the NIPF can increase the particles diversity and improve the results of state estimation.