基于最小二乘支持向量机的飞行事故预测

Flight accident Prediction Based on Least Squares Support Vector Machines

为了对空军飞行安全形势进行科学的分析和预测,针对反映空军飞行安全形势的重要指标之一——飞行事故万时率,采用了最小二乘支持向量机(LS-SVM)的时间序列非线性预测模型,并对其建模过程和参数选择问题进行了分析和研究。文中利用美国空军A类飞行事故的历史数据对该方法进行了验证,预测精度较高,方法可行。

In order to analyze and forecast the air force flight safety situation scientifically, nonlinear forecasting model and method based on least squares support vector machines （LS-SVM） are used to study the indicator of 10000 - hour - flight accident - rate which is one of the important indicators of air force flight safety situation, and analysis the parameter choosing. The simulation result shows that the forecasting method is feasible and has good consistency with reality.