Support vector machine based aircraft ground icing type classification forecast

Aircraft icing can seriously affect the safety of aircraft, and different types of aircraft icing have an effect on the aircraft safety to various extents. A SVM (Support Vector Machine) model for aircraft icing type prediction is presented to classify aircraft icing types. The input variables of icing type are analyzed, and then based on the analysis, the appropriate forecast methods are chosen and a SVM model for aircraft icing type classification is established. The SVM-based classification model is employed to identify aircraft ground icing type and compare with the classification model based on BP neural network. The experimental results show that the model based on the SVM method supplies high forecast accuracy, strong generalization ability with small samples, and has broad application prospect.