No abstract

A robust framework for fault detection and identification of rotor faults in multicopters is validated with data from experiments with a quadcopter and a hexacopter. The rotor fault detection and identification methods employed in this study are based on excitation-response signals of the aircraft under atmospheric disturbances. A concise overview of the development of the statistical time series model for healthy aircraft using the aircraft attitudes as the output and controller commands as the input is presented. This model is utilized to extract quality features for training a simple neural network to perform effective online rotor fault detection and identification. A proper justification of choosing the method of time-series assisted neural network has been given. It is shown a statistical time-series assisted neural network employed for online monitoring in the quadcopter and hexacopter achieves accuracy over 96% and 95%, respectively. It is effective under gusts and experimental variability encountered during outdoor flight and is sensitive to even partial loss of rotor thrust.

No abstract

An innovative machine-learning-based probabilistic framework for online rotor fault diagnosis in multicopters is presented. The proposed scheme employs in-flight out-of-plane strain measurements at each of the multicopter booms to detect, identify, and quantify rotor faults while distinguishing them from the aircraft response to random gusts. Its robust performance is demonstrated with application to a 2-foot-diam hexacopter flying under varying forward velocity and gross weight configurations, as well as atmospheric disturbances and uncertainty. The rotor fault diagnosis takes place in two steps. First, a simple perceptron classifies the aircraft’s health condition. If a rotor fault is detected it is simultaneously identified and the fault magnitude estimation step initiates. Here, linear regression models are used to predict the respective rotor degradation values with their 95% confidence intervals. The generalization capability of the method is established with several test data under unmodeled operating conditions (not used in the training phase). The proposed framework can accurately diagnose even minor rotor faults of 8% degradation while distinguishing them from aggressive gusts of up to [Formula: see text] magnitude. The maximum fault detection time is less than 0.3 s. The health state classification and the rotor fault magnitude quantification accuracy are over 99%.

No abstract