Support Vector Machine based Fault Diagnosis for an Unmanned Tandem Helicopter

Fault diagnosis of actuators in flight control system of an unmanned tandem helicopter has been studied in this paper. A support vector machine (SVM) observer is designed to parameter estimation and model compensation for its uncertainty, and then to fault detection. Further more, a fuzzy sample SVM (FS-SVM) based diagnostic tool is used to fault diagnosis for the actuators of the small tandem helicopter, and fuzzy grades of membership functions are chosen by cost value of fault decision logic and the actuator damage degree. The proposed diagnosis method is applied into the structure fault diagnosis of a small unmanned tandem helicopter. The simulation results show the effectiveness of the proposed way.