飞行器健康度神经网络预测方法  

A Neural Network Predicion Method for Aircraft Health

作　　者：张英 韦闽峰[2,3,4] 高晓颖[2,3] 王世会[2,3] 曹健 张兴[1] Zhang Ying;Wei Minfeng;Gao Xiaoying;Wang Shihui;Cao Jian;Zhang Xing(School of Software&Microelectronics,Peking University,Beijing 100871,China;Beijing Aerospace Automatic Control Institute,Beijing 100854,China;National Key Laboratory of Science and Technology on Aerospace Intelligent Control,Beijing 100854,China;School of Automation,Beijing Institute of Technology,Beijing 100081,China)

机构地区：[1]北京大学软件与微电子学院,北京100871 [2]北京航天自动控制研究所,北京100854 [3]宇航智能控制技术国家级重点实验室,北京100854 [4]北京理工大学自动化学院,北京100081

出　　处：《航天控制》2019年第6期24-28,65,共6页Aerospace Control

摘　　要：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.

关 键 词：AI 神经网络 健康预测 飞行器 

分 类 号：TN911.22[电子电信—通信与信息系统]