Particle filtering for state and parameter estimation in gas turbine engine fault diagnostics

In this paper, a novel method for a time-varying parameter estimation technique using particle filters is proposed based on the concept of Recursive Prediction Error (RPE). According to the proposed method, a parallel structure for both state and parameter estimation in a nonlinear non-Gaussian system is developed. The performance of the developed framework is evaluated in an application to the gas turbine engine state and health parameters estimation by using different scenarios. The developed method is identified to be applicable for fault diagnosis of an engine system while it is subjected to concurrent and simultaneous loss of effectiveness faults in the system components.