中国民航大学学报

• 民用航空 • 上一篇    下一篇

基于SOM 神经网络的航空发动机滑油系统健康评估

曹惠玲,黄乐腾,李志伟,庞思凯   

  1. (中国民航大学航空工程学院,天津300300)
  • 收稿日期:2013-06-26 修回日期:2013-10-23 出版日期:2014-12-25 发布日期:2014-12-05
  • 作者简介:曹惠玲(1962—),女,河北唐山人,教授,工学博士,研究方向为航空发动机性能分析与故障诊断.
  • 基金资助:

    中国民航大学博士启动基金项目(QD02s04)

Health assessment study of aero-engine oil system based on SOM neural network

CAO Hui-ling,HUANG Le-teng,LI Zhi-wei,PANG Si-kai   

  1. (College of Aeronautical Engineering,CAUC,Tianjin 300300,China)
  • Received:2013-06-26 Revised:2013-10-23 Online:2014-12-25 Published:2014-12-05

摘要:

研究了基于SOM神经网络的滑油系统健康评估方法。利用SOM 神经网络确定了系统不同状态下的健康参数,并与故障状态下的健康指数进行比较,划分了系统的健康等级,为及时评判滑油系统的健康情况提供了依据。利用正常样本及故障样本分别对SOM神经网络进行验证,结果证明了模型的有效性。SOM神经网络应于健康评估时具有泛化能力好、学习速率快、输出层结果比较直观等优点,为滑油系统的健康评估提供了新的方法和思路。

关键词: 航空发动机滑油系统, SOM神经网络, 健康评估, QAR

Abstract:

The health assessment method of oil system based on SOM neural network is researched. SOM neural network is used to define the health parameters under different system conditions comparing with the health parameters under fault conditions. Different health levels are divided to provide a basis for health judgement of oil system in a timely manner. The normal samples and fault samples are used to verify effectiveness of SOM neural network.SOM neural network shows lots of advantages when it is applied to health assessments such as good generalization ability,fast learning rate,intuitive result of output layer and so on,providing new methods and ideas for health assessment of oil system.

Key words: aero-engine oil system, SOMneural network, health assessment, QAR

中图分类号: