Fault detection and identification for multirotor aircraft by data-driven statistical learning methods

This work compares different data-driven methods for fault detection and identification of rotor failures in multicopters. The fault detection and identification methods employed in this study are based on response-only signals of the aircraft state, as the external excitation due to ambient turbulence is non-observable. Knowledge based methods using the knowledge of aircraft dynamics in the event of rotor failure is studied. A concise overview of the development of statistical time series models using the aircraft attitudes and statistical hypothesis testing to detect and classify rotor failures is presented. These methods are compared with neural networks trained on different parts of the response signals to achieve online fault detection identification of rotor failures in a hexacopter with respect to speed and accuracy of fault classification. It is shown that using a combination of statistical time series model for healthy aircraft and neural networks employed for online monitoring results in fault detection and identification in less than 0.3 s with an accuracy of 99.3%.