Data-driven fault detection, isolation and estimation of aircraft gas turbine engine actuator and sensors

In this work, a data-driven fault diagnosis and estimation scheme is proposed and developed specifically for aircraft gas turbine engine actuator and sensors. The proposed fault detection, isolation and estimations filters are directly constructed by using only the system I/O data at each operating point of the engine. The associated system Markov parameters are estimated by using the frequency response data that are then used for the direct construction of the fault detection, isolation and estimation filters. Our proposed scheme therefore does not require a priori knowledge of the system linear model or its number of poles and zeros at each operating point. We have shown through simulations that desirable fault detection, isolation and estimation performance metrics can be achieved.