基于簇特征加权的航空发动机状态监视方法

周媛; 左洪福; 王丽娜

doi:10.13224/j.cnki.jasp.2015.07.030

基于簇特征加权的航空发动机状态监视方法

doi: 10.13224/j.cnki.jasp.2015.07.030

1. 南京航空航天大学民航学院, 南京 210016;
2. 南京信息工程大学电子与信息工程学院, 南京 210044

基金项目:

国家自然科学基金委员会与中国民用航空总局联合项目(60939003)

国家自然科学基金(61079013)

江苏省自然科学基金(BK2011737)

详细信息

作者简介:
周媛(1980-),女,安徽池州人,讲师,博士生,从事模式识别、航空发动机健康管理的研究.

中图分类号: V37;TP391
计量
- 文章访问数: 1268
- HTML浏览量: 101
- PDF量: 549
- 被引次数: 0
出版历程
- 收稿日期: 2014-06-10
- 刊出日期: 2015-07-28

Aero-engine condition monitoring method based on cluster features weighting

1. College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China;
2. School of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China

摘要

摘要: 提出了基于簇特征加权模糊C-均值聚类算法(FWFCM)的航空发动机状态监视模型,该模型主要分为离线学习和在线监视两个部分,离线学习模块计算出模型参数输出到在线监视模块,在线监视模块根据模型参数对实时数据进行分类,实时数据又输入到离线学习模块中参与更新模型参数.结果表明:相比基于数据加权策略的模糊聚类算法(DWFCM)以及经典模糊C-均值聚类算法(FCM),该方法平均离线状态识别率和在线状态识别率分别提高了5.233%和8.358%.实验证明此方法性能好且有很好的鲁棒性和泛化能力,对于不确定性的航空发动机在线状态监视有较好的应用价值.
- 状态监视 /
- 模糊聚类 /
- 簇特征加权 /
- 鲁棒性 /
- 泛化能力
Abstract: A model for aeroengine condition monitoring based on fuzzy C-means clustering algorithm with cluster features weighting(FWFCM) was proposed. This model is composed of two parts: one is offline-learning module, in which the module parameters are iteratively computed, and the other is online-monitoring module, in which the realtime data can be classified according to the parameters. Then the realtime data are inputed into the offline-module and the module parameters are updated. Result shows that, compared with the data weighted fuzzy clustering algorithm(DWFCM) and the classic fuzzy C-means clustering algorithm (FCM), the average condition recognition accuracy of the proposed method in offline module and in online module is 5.233% and 8.358% higher than the other two algorithms, respectively. It can be shown that the FWFCM works well for aeroengine condition monitoring with good rebustness and generalization, and has practical application value for uncertained aeroengine condition monitoring.
- condition monitoring /
- fuzzy clustering /
- cluster features weighting /
- robustness /
- generalization

HTML

参考文献(18)

[1]	孙博,康锐,谢劲松.故障预测与健康管理系统研究和应用现状综述[J].系统工程与电子技术,2007,29(10):1762-1767. SUN Bo,KANG Rui,XIE Jinsong.Research and application of the prognostic and health management system[J].System Engineers and Electronics,2007,29(10):1762-1767.(in Chinese)
[2]	姜彩虹,孙志岩,王曦.航空发动机预测健康管理系统设计的关键技术[J].航空动力学报,2009,24(11):2589-2594. JIANG Caihong,SUN Zhiyan,WANG Xi.Critical technologies for aero-engine prognostics and health management systems development[J].Journal of Aerospace Power,2009,24(11):2589-2594.(in Chinese)
[3]	杨征山,俞刚,庄锡明,等.基于参数线性组合的航空发动机气路健康参数估计[J].航空动力学报,2014,35(3):408-412. YANG Zhengshan,YU Gang,ZHUANG Ximing,et al.Gas path health parameters estimation of aeroengine based on linear combination[J].Journal of Propulsion Technology,2014,35(3):408-412.(in Chinese)
[4]	薛薇,郭迎清,李睿.航空发动机状态监视、故障诊断研究及验证[J].推进技术,2011,32(2):271-275. XUE Wei,GUO Yingqing,LI Rui.Algorithm and experimental validation for condition monitoring,fault detection for gas turbine engine[J].Journal of Propulsion Technology,2011,32(2):271-275.(in Chinese)
[5]	钟诗胜,李洋.基于小波过程神经网络的飞机发动机状态监视[J].航空学报,2007,28(1):68-71. ZHONG Shisheng,LI Yang.Condition monitoring of aeroengine based on wavelet process neural networks[J].Acta Aeronautica et Astronautica Sinica,2007,28(1):68-71.(in Chinese)
[6]	单晓明,宋云峰,黄金泉,等.基于神经网络和模糊逻辑的航空发动机状态监视[J].航空动力学报,2009,24(10):2356-2361. SHAN Xiaoming,SONG Yunfeng,HUANG Jinquan,et al.Condition monitoring of aero-engine based on neural network and fuzzy logic[J].Journal of Aerospace Power,2009,24(10):2356-2361.(in Chinese)
[7]	陈卫,程礼,李全通,等.航空发动机监控技术[M].北京:国防工业出版社,2011.
[8]	孙见忠.航空发动机气路部件健康管理若干关键技术研究[D].南京:南京航空航天大学,2012. SUN Jianzhong.Research on key technologies of health management for aero engine gas path components[D].Nanjing:Nanjing University of Aeronautics and Astronautics,2012.(in Chinese)
[9]	杨慧中,张文清.基于特征加权模糊聚类的多模型软测量建模[J].控制工程,2011,18(4):524-526. YANG Huizhong,ZHANG Wenqing.Multimodel soft-sensor modeling based on feature-weighted fuzzy clustering[J].Control Engineering of China,2011,18(4):524-526.(in Chinese)
[10]	蔡静颖,谢福鼎,张永.基于马氏距离特征加权的模糊聚类新算法[J].计算机工程与应用,2012,48(5):198-200. CAI Jingying,XIE Fuding,ZHANG Yong.Fuzzy c-means algorithm based on adaptive Mahalanobis distances[J].Computer Engineering and Applications,2012,48(5):198-200.(in Chinese)
[11]	唐成龙,王石刚,徐威.基于数据加权策略的模糊聚类改进算法[J].电子与信息学报,2010,32(6):1277-1283. TANG Chenglong,WANG Shigang,XU Wei.Improved fuzzy clustering algorithm based on data weighted ap-proach[J].Journal of Electronics and Information Technology,2010,32(6):1277-1283.(in Chinese)
[12]	鲁卿,冯金富,胡俊华,等.一种基于WFCM的故障诊断方法[J].振动、测试与诊断,2008,27(4):308-311. LU Qing,FENG Jinfu,HU Junhua,et al.Fault diagnosis based on WFCM[J].Journal of Vibration,Measurement and Diagnosis,2008,27(4):308-311.(in Chinese)
[13]	冯金富,鲁卿,张佳强,等.一种基于鲁棒 FCM 算法的故障诊断方法[J].仪器仪表学报,2008,29(10):2175-2180. FENG Jinfu,LU Qing,ZHANG Jiaqiang,et al.Fault diagnosis based on robust FCM algorithm[J].Chinese Journal of Scientific Instrument,2008,29(10):2175-2180.(in Chinese)
[14]	孙见忠,左洪福,刘鹏鹏,等.基于动态线性模型的民航发动机性能状态监控与在翼寿命预测[J].系统工程理论与实践,2013,33(12):3243-3250. SUN Jianzhong,ZUO Hongfu,LIU Pengpeng,et al.A method of condition monitoring and on-wing life prediction for civil aviation aircraft engine based on dynamic linear model[J].System Engineering-theory & Practice,2013,33(12):3243-3250.(in Chinese)
[15]	任淑红.民航发动机性能可靠性评估与在翼寿命预测方法研究[D].南京:南京航空航天大学,2010. REN Shuhong.Research on methods of performance reliability assessments and life on wing prediction for civil aeroengine [D].Nanjing:Nanjing University of Aeronautics and Astronautics,2010.(in Chinese)
[16]	Frederick D,DeCastro J,Litt J.User's guide for the commercial modular aero-propulsion system simulation (C-MAPSS)[R].NASA/TM2007-215026,2007.
[17]	Saxena A,Goebel K,Simon D,et al.Damage propagation modeling for aircraft engine run-to-failure simulation[R].Denver,CO:Prognostics and Health Management,International Conference,2008.
[18]	Heimes F O.Recurrent neural networks for remaining useful life stimation[R].Denver,CO:Prognostics and Health Management,International Conference,2008.