宇航计测技术

• 论文 • 上一篇    下一篇

基于贝叶斯网络工况分类的民机引气系统异常检测

梁坤1，2；左洪福1；孙见忠1；李怀远1；丁旋1；刘若晨1   

  1. 1、南京航空航天大学民航学院，南京 210016；
    2、淮阴工学院交通工程学院，淮安 223300
  • 出版日期:2014-12-15 发布日期:2014-12-15
  • 作者简介:梁坤（1978-），男，讲师，博士生，主要研究方向：航空器健康管理、故障诊断、数据挖掘、交通安全等。
  • 基金资助:
    国家自然科学基金与中国民航联合资助基金项目（60939003）

Fault Detection for Civil Aircraft Bleed Air Systems Based on Bayesian Network State Classification

LIANG Kun1，2；ZUO Hong-fu1；SUN Jian-zhong1；LI Huai-yuan1；DING Xun1；LIU Ruo-cheng1   

  1. 1、College of Aerospace Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016；
    2、College of Transportation, Huaiyin Institute of Technology, Huai′an 223003
  • Online:2014-12-15 Published:2014-12-15

PDF (PC)

456

摘要： 状态监控与健康管理技术是国产民机运营支持亟待突破的关键技术，以民机引气系统为对象，设计实现了基于飞行数据（QAR，Quick access recorder）的民机引气系统异常检测流程，提出了贝叶斯网络分类的同工况数据提取和指数加权滑动平均(Exponentially Weighted Moving Average，EWMA)控制图的引气系统异常检测方法。借助航空公司收集的实际数据对方法进行了验证，结果表明可有效检测民机引气系统异常，并提前故障发现时间，为航空公司合理安排飞机维修计划、减少飞机停场时间提供了支持。

关键词: 飞机引气系统, 飞行数据, 异常检测, 贝叶斯网络, EWMA控制图

Abstract: The technology of condition monitoring and health management is the breakthrough key technical of the domestic civil aircraft operators support. With civil aircraft bleed air system as the object of the research，a fault detection process based on flight data is designed and a method of fault detection for civil aircraft bleed air systems are proposed by the same state data extraction using bayesian network classification and exponentially weighted moving average control chart. The method is validated by using actual data collected in airline.The results show that the proposed method not only can detect fault for civil aircraft bleed air system, but also found fault ahead of time, which provides support for the airline to arrange aircraft maintenance programs reasonably, reduces aircraft downtime.

Key words: Aircraft bleed air system, Flight data, Fault detection, Bayesian network, EWMA control chart

京ICP备09048426号-4　 京公网安备 11010602060144号　版权所有 © 《宇航计测技术》编辑部