A Decision Support System Based on Support Vector Machine for Hard Landing of Civil Aircraft

Hard landing event affect the flight safety seriously. In this paper, a decision support system that classifiers the hard landing signals of the civil aircraft to two classes (normal and abnormal) is presented to support fault diagnosis. As our previous paper where ANN is used as a classifier for event detection from measured hard landing signals. In this paper, our aim is to develop our previous work by using least-squares support vector machine (LS-SVM) classifier instead of ANN. We compare LS-SVM with backpropagation artificial neural network (BP-ANN) to classify the extracted features. In addition, we use receiver operator characteristic (ROC) curves to compare sensitivities and specificities of these classifiers and compute the area under the curves. Finally, performance of models are analysed, and the aspects of each model are given.