An active generalized likelihood ratio test in a reconfigurable fault-tolerant control system

For sequential jumps detection, isolation and estimation in discrete-time stochastic linear systems, (A.S. Wilsky et al., 1976) have developed the generalized likelihood ratio (GLR) test. After each detection and isolation of one jump, the treatment of another possible jump is obtained by a direct state estimate and covariance incrementation of the Kalman filter originally designed on the jump-free system. With this updating strategy, the rate of good decisions is not guaranted to be maximized. To solve this problem, the proposed active GLR test will be based on a reference model updated on line after each detection and isolation of one jump. We will show that the active GLR tests can be easily integrated in a reconfigurable fault-tolerant control system (FTCS) to asymptotically recover the nominal system performances of the jump-free system.