Fault Detection in Aircraft Flight Control Actuators Using Support Vector Machines

Future generations of flight control systems, such as those for unmanned autonomous vehicles (UAVs), are likely to be more adaptive and intelligent cope with the extra safety reliability requirements due pilotless operations. An efficient fault detection isolation (FDI) system is paramount should capable monitoring health status an aircraft. Historically, hardware redundancy techniques have been used detect faults. However, duplicating actuators in UAV not ideal high cost large mass additional components. Fortunately, aircraft actuator faults can also detected using analytical techniques. In this study, a data-driven algorithm Support Vector Machine (SVM) designed. The investigated loss-of-effectiveness (LOE) fault. aim classify feature vector data into nominal or faulty class based on actuator. results show that SVM detects LOE almost instantly, average accuracy 99%.