首页 | 本学科首页   官方微博 | 高级检索  
   检索      

结合动态时间弯曲与决策树方法的液体火箭发动机故障诊断
引用本文:胡小平,韩泉东,李京浩.结合动态时间弯曲与决策树方法的液体火箭发动机故障诊断[J].国防科技大学学报,2007,29(4):1-5.
作者姓名:胡小平  韩泉东  李京浩
作者单位:国防科技大学,航天与材料工程学院,湖南,长沙,410073
基金项目:国家自然科学基金资助项目(50376073)
摘    要:对某大型液体火箭发动机的热试车数据及通过发动机模型仿真得到的故障数据进行动态时间弯曲分析,得到弯曲路径集,然后结合决策树方法进行了故障检测和诊断。对于故障试车没有出现漏报警和误报警,对于正常试车没有出现误报警。通过与神经网络、支持向量机等方法所得结果的对比,证明该方法可以成功地应用于火箭发动机的故障检测和诊断。

关 键 词:液体火箭发动机  故障检测和诊断  数据挖掘  动态时间弯曲  决策树
文章编号:1001-2486(2007)04-0001-05
收稿时间:2007/1/28 0:00:00
修稿时间:2007年1月28日

Fault Diagnosis of Liquid Rocket Engine by Dynamic Time Warping Combined with Decision Tree Method
HU Xiaoping,HAN Quandong and LI Jinghao.Fault Diagnosis of Liquid Rocket Engine by Dynamic Time Warping Combined with Decision Tree Method[J].Journal of National University of Defense Technology,2007,29(4):1-5.
Authors:HU Xiaoping  HAN Quandong and LI Jinghao
Institution:College of Aerospace and Materials Engineering, National Univ. of Defense Technology, Changsha 410073, China;College of Aerospace and Materials Engineering, National Univ. of Defense Technology, Changsha 410073, China;College of Aerospace and Materials Engineering, National Univ. of Defense Technology, Changsha 410073, China
Abstract:Through dynamic time warping analysis to the hot-fire test data and simulated fault data of a certain liquid rocket engine,the warped path sets were obtained.Combined with the decision tree method,fault detection and diagnosis were carried out.Results show that there were no failing report and no misstatement for fault tests,and no misstatement for normal tests.Compared with those results by ANN and SVM methods,the successful application of the dynamic time warping method combined with decision tree was proved.
Keywords:liquid rocket engine  fault detection and diagnosis  data mining  dynamic time warping  decision tree
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《国防科技大学学报》浏览原始摘要信息
点击此处可从《国防科技大学学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号