Parity space‐based intermittent fault detection for T‐S fuzzy systems with unknown disturbances

Abstract This paper investigates the problem of intermittent fault (IF) detection for T‐S fuzzy systems with unknown disturbances. Firstly, a robust residual for IF detection is designed by utilizing the parity space method. Subsequently, the optimal performance index and the optimal residual generation vector are designed by considering the influence of stochastic noises. Furthermore, the thresholds for detecting the appearing time (AT) and disappearing time (DT) of the IF are set based on the hypothesis testing method. In addition, the detectability, false alarm rates and missing alarm rates are discussed under the framework of stochastic analysis. Finally, the simulation results verify the effectiveness of the proposed method.