基于多源诊断信息融合的发动机气路分析

孙见忠; 左洪福

基于多源诊断信息融合的发动机气路分析

南京航空航天大学民航学院, 南京 210016

基金项目: 国家自然基金委员会与中国民用航空局联合基金(60939003, 61179058)

计量
- 文章访问数: 1537
- HTML浏览量: 3
- PDF量: 1027
- 被引次数: 0
出版历程
- 收稿日期: 2012-09-09
- 刊出日期: 2013-08-28

Gas path analysis based on multi-sources diagnostics information fusion

College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China

摘要

摘要: 针对气路可测信息的有限性及不确定性易导致航空发动机气路分析结果准确度和精度不高的问题,提出了一种基于贝叶斯网络的多源诊断信息融合机制,以提高气路部件故障诊断的准确度和精确度.介绍了基于贝叶斯网络的气路分析方法,在此基础上提出了改进的用于多源诊断信息融合的气路分析贝叶斯网络,即以常规的气路可测参数为主,而其他诊断信息则借助故障模式先验概率表引进贝叶斯网络,实现多源信息的融合.仿真实验表明:通过融合多源信息能够准确地诊断出传统的气路分析难以识别的故障,同时降低了健康参数估计值的方差,提高了诊断结果的精确度;在观测噪声放大一倍、健康参数变化量小于1%的情况下,通过融合多源信息仍能准确的估计出健康参数变化量,且标准差均于0.1%.
- 发动机健康管理 /
- 气路分析 /
- 故障诊断 /
- 信息融合 /
- 贝叶斯网络 /
- 贝叶斯推理
Abstract: Considering the poor accuracy and precision of the gas path analysis (GPA) results due to lack of enough measured gas path parameters and the associated uncertainty,a Bayesian network based multi-source diagnostics information fusion mechanism was proposed to improve the performance of the GPA.The Bayesian network based GPA (BN-GPA) was introduced briefly,then an improved BN-GPA was developed to incorporate diagnostics information from multi sources.In the framework based on the diagnostics information inferred from the measured gas path parameters,other diagnostics information was incorporated into the Bayesian network by the fault mode prior probability table.The results of the simulation show that by fusing the multi sources information, the fault mode which cannot be identified by the traditional GPA now can be identified accurately with reduced variance for the estimation of the health parameters; In another case where the standard deviation of the measurement noise is doubled and the deviations of the health parameters of the faulty components are set less than 1%, the estimation results of the health parameters are still relative accurate with the standard deviation of the estimation result less than 0.1%.
- engine health management /
- gas path analysis /
- fault diagnostics /
- information fusion /
- Bayesian network /
- Bayesian inference

HTML

参考文献(23)

[1]	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.
[2]	Volponi A.Data fusion for enhanced aircraft engine prognostics and health management [R].NASA/CR-2005-214055,E-15412,2005.
[3]	陈恬,孙健国,郝英.基于神经网络和证据融合理论的航空发动机气路故障诊断[J].航空学报,2006 27(6):1014-1017. CHEN Tian,SUN Jianguo,HAO Ying.Neural network and dempster-shafter theory based fault diagnosis for aeroengine gas path[J].Acta Aeronautica et Astronautica Sinica,2006,27(6):1014-1017.(in Chinese)
[4]	曲建岭,唐昌盛,肖辉雄,等.人工神经网络融合诊断航空发动机气路故障[J].航空动力学报,2008,23(11):2124-2127. QU Jianling,TANG Changsheng,XIAO Huixiong,et al.Integrated diagnosis of aeroengines gas path faults using artificial neural network[J].Journal of Aerospace Power,2008,23(11):2124-2127.(in Chinese)
[5]	鲁峰,黄金泉,陈煜.航空发动机部件性能融合故障诊断方法研究[J].航空动力学报,2009,24(7):1649-1653. LU Feng,HUANG Jinquan,CHEN Yu.Research on performance fault fusion diagnosis of aero-engine component[J].Journal of Aerospace Power,2009,24(7):1649-1653.(in Chinese)
[6]	鲁峰,黄金泉.基于 ESVR信息融合的航空发动机故障诊断研究[J].应用基础与工程科学学报,2010,18(6):982-989. LU Feng,HUANG Jinquan.Fault diagnosis for aero-engine based on ESVR information fusion[J].Journal of Basic Science and Engineering,2010,18(6):982-989.(in Chinese)
[7]	陈果.航空器检测与诊断技术导论[M].北京:中国民航出版社,2007.
[8]	Kyriazis A,Tsalavoutas A,Mathioudakis K.Gas turbine fault identification by fusing vibration trending and gas path analysis [R].Orlando,Florida,USA:ASME Turbo.Expo.Power for Land,Sea,and Air,2009.
[9]	Fisher C E.Gas path debris monitoring:a 21st century PHM tool [R].IEEE Aerospace Conference Proceedings,2000.
[10]	李耀华,左洪福.碰摩故障静电监测方法及模拟实验[J].航空学报,2010,31(6):1156-1163. LI Yaohua,ZUO Hongfu.Method for rub fault detection based on electrostatic technique:model and simulated experiments[J].Acta Aeronautica et Astronautica Sinica,2010,31(6):1156-1163.(in Chinese)
[11]	Tappert P,Von Flotow A,Mercadal M.Autonomous PHM with blade-tip-sensors:algorithms and seeded fault experience [R].Aerospace Conference,2001,IEEE Proceedings,2001.
[12]	Von Flotow A,Mercadal M,Tappert P.Health monitoring and prognostics of blades and disks with blade tip sensors [R].Big Sky,MT,USA:IEEE Aerospace Conference Proceedings,2000.
[13]	Breese J S,Horvitz E J,Peot M A,et al.Automated decision-analytic diagnosis of thermal performance in gas turbines [R].ASME Paper 92-GT-399,1992.
[14]	Palmer C A.Combining Bayesian belief networks with gas path analysis for test cell diagnostics and overhaul [R].ASME Paper 98-GT-168,1998.
[15]	Romessis C,Stamatis A,Mathioudakis K.Setting up a belief network for turbofan diagnosis with the aid of an engine performance model [R].ISABE Paper 2001,No.1032,2001.
[16]	Romessis C,Mathioudakis K.Bayesian network approach for gas path fault diagnosis[J].ASME J.Eng.Gas Turbines Power,2006,128(1):64-72.
[17]	Lee Y K,Mavris D N,Volovoi V V,et al.A fault diagnosis method for industrial gas turbines using Bayesian data analysis[J].Journal of Engineering for Gas Turbines and Power,2010,132(4):041602.(6 pages).
[18]	Lee Y K,Mavris D N,Volovoi V V,et al.A Bayesian method for calibrating computer models to test data[J].Inverse Problems in Science and Engineering,2011,19(3):395-408.
[19]	孙见忠.面向单元体的航空发动机健康状态评估与预测方法研究 [D].南京:南京航空航天大学,2012. SUN Jianzhong.Research on the methods of health assessment and prognostics for aero engine on the module level [D].Nanjing:Nanjing University of Aeronautics and Astronautics,2012.(in Chinese)
[20]	Chupp R E,Ghasripoor F,Moore G D,et al.Applying abradable seals to industrial gas turbines [R].2002-GRC193,2002.
[21]	Dewallef P.Application of the Kalman filter to health monitoring of gas turbine engines:a sequential approach to robust diagnosis [D].Liège:University of Liège,2005.
[22]	Mathioudakis K,Kamboukos P H,Stamatis A.Gas turbine component fault detection from a limited number of measurements[J].Proc.Inst.Mech.Eng.:Part A,2004,218(8):609-618.
[23]	Lunn D J,Thomas A,Best N,et al.WinBUGS:a Bayesian modelling framework:concepts,structure,and extensibility[J].Statistics and Computing,2000,10(4):325-337.