基于加权LS-SVM的飞行事故率预测模型

Forecast Model of Flight Accident Rate Based on Weighted LS-SVM

飞行事故率是表征飞行安全水平的重要指标,其预测是典型的小样本问题。针对飞行事故率预测建模难的问题,采用加权LS-SVM方法,建立了飞行事故率的时间序列预测模型。仿真实验表明,加权LS-SVM具有很高的建模精度和较强的泛化能力,从而验证了该方法的有效性和先进性。

Flight accident rate is an important index which reflects the aviation safety degree. The prediction of flight accident rate is typically a small sample problem. Aiming at the problem of hard forecast modeling for flight accident rates, the forecast model of flight accident rates is established by using of Weighted LS-SVM method. The simulation results show that Weighted LS-SVM has high modeling precision and strong generalization. Therefore the method mentioned above is valid and advanced.