飞行器健康度神经网络预测方法

A Neural Network Predicion Method for Aircraft Health

提出了一种飞行器健康状态的智能预测方法,用于飞行器实时控制健康预测,是一种实时在线健康预测算法。该方法改变了传统飞行器事后补救的健康处置方案,采用实时输出飞行器的健康预测值。包括5个模型:飞行器数据模拟模型、基于RNN和LSTM的数据集正样本训练预测模型、基于灰色模型的预测模型、组合预测模型,以及健康度计算模型。

An intelligent prediction method for aircraft health are presented,which are used for aircraft real-time control for the purpose of online health prediction.The traditional health disposal scheme of the aircraft is taken by a second thought and the predicted health value output of aircraft is changed due to generation on real-time in this mehtod that includes five models:aircraft data simulation model,positive sample training prediction model based on RNN and LSTM,prediction model based on gray model,combined prediction model and health calculation model.