Fault Detection and Diagnosis of Dynamic Systems with Colored Measurement Noise

B.S. Kim, I.S. Lee, D.Y. Lee, J.T. Kim, J.C. Park, J.W. Lee, Y.J. Lee, and K.Y. Kim (Korea)


Interacting Multiple Model, Fault Detection and Diagnosis, Colored Measurement Noise


An effective scheme to detect and diagnose multiple failures in a dynamic system is described for the case where the measurement noise is correlated sequentially in time. It is based on the modified interacting multiple model (MIMM) estimation algorithm in which a generalized decorrelation process is developed by employing the autoregressive (AR) model for the colored noise and applying measurement difference method.

Important Links:

Go Back