Simplification techniques for EKF computations in fault diagnosis-suboptional gains

The extended Kalman filter (EKF) is one of the most popular model-based techniques for fault detection and diagnosis. In the present study, the idea of suboptimal EKF is utilized to enhance computation efficiency without sacrificing diagnostic accuracy. In particular, a simple procedure is developed to decompose the filter model according to the precedence order of the state/parameter estimation process. As a result, a large portion of the computations needed for propagating error covariances and updating state estimates can be neglected. Extensive simulation results are also presented to demonstrate the effectiveness of these proposed techniques.