Fault detection of Aircraft Landing Gear System using Machine Learning

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