基于BP神经网络的民航安全预测方法研究

Study on Civil Aviation Safety Forecasting Method Based on BP Neural Network

为了对民航系统安全运行状态进行科学的分析和预测,针对反映民航系统安全运行状态的重要指标之一——飞行事故万时率,采用BP神经网络的时间序列非线性预测模型及方法,对其进行了分析研究和仿真验证,计算结果表明,该预测方法是可行的,并与实际具有较好的一致性。

In order to analyze and forecast the civil aviation system safety operation state scientifically,nonlinear forecasting model and method based on BP neural network are used to study and simulate the indicator of 10 000-hour-flight accident-rate which is one of the important indicators of civil aviation system safety operation state. The result shows that the forecasting method is feasible and has good consistency with reality.