航空发动机性能参数的混沌识别与预测
|
摘要
性能参数监控是航空发动机监控的重要手段之一,而对性能参数进行预测可以提前掌握航空发动机在未来时刻的性能状况,从而预防和排除故障。本文首先介绍了改进的加权一阶局域混沌预测算法,然后对航空发动机性能参数(转差率S)进行了混沌识别,最后采用改进的加权一阶局域预测算法对航空发动机性能参数进行了混沌预测。实验结果表明,改进的加权一阶局域预测算法具有很好的学习能力和较高的预测精度,适用于航空发动机性能参数监控。
Performance parameter monitoring is a key means of aeroengine monitoring, and performance parameter forecasting can be used to obtain the future performance condition of aeroengine, thus preventing and eliminating faults. This article firstly introduces the improved local weighted linear chaotic forecast model briefly, then the aeroengine character parameter(i.e. rotor speed ratio S) is recognized as chaotic, at last the aeroengine character parameter is forecasted by using the improved local weighted linear forecast model. Experimental results show that the improved local weighted linear forecast model has good learning capability and high forecasting accuracy, which is suitable to aeroengine character parameters monitoring.
Performance parameter monitoring is a key means of aeroengine monitoring, and performance parameter forecasting can be used to obtain the future performance condition of aeroengine, thus preventing and eliminating faults. This article firstly introduces the improved local weighted linear chaotic forecast model briefly, then the aeroengine character parameter(i.e. rotor speed ratio S) is recognized as chaotic, at last the aeroengine character parameter is forecasted by using the improved local weighted linear forecast model. Experimental results show that the improved local weighted linear forecast model has good learning capability and high forecasting accuracy, which is suitable to aeroengine character parameters monitoring.
引文
[1]Armstrong J B,Simon D L.Implementation of an integrated on-board aircraft diagnostic architecture[R].Reston,VA:AIAA,2011-5859,2011.
[2]Sanja G.Aircraft turbine engine control research at NASA glenn research center[R].NASA/TM-2013-217821,NASA,2013.
[3]赵连春,杰克,马丁利.飞机发动机控制—设计、系统分析和健康监视[M].北京:航空工业出版社,2011.
[4]Simo D L,Litt J S.A data filter for identifying steady-state operating points in engine flight data for condition monitoring applications[J].Journal of Engineering for Gas Turbines and Power,2011,133:1-8.
[5]Linda C.NASA aviation safety reporting system[R].NASA/ARC-E-DAA-TN2844,NASA,2014.
[6]Volphni A.Enhanced self turning on-board realtime model for aircraft engine performance health tracking[R].NASA/CR-2008-215272,Washington:NASA,2008.
[7]谭巍,李冬,樊照远,等.基于模型信息熵的航空发动机性能评估和可靠性分析[J].航空发动机,2011,37(5):45-48.
[8]王桓.电力时间序列的混沌识别与短期预测[D].长沙:湖南大学,2009.
[9]Sun L Y.Prediction of multivariable chaotic time series with local polynomial fitting[J].Computers and Mathematics with Application,2010,59:737-744.
[10]QU Jian-ling,WANG Xiao-fei,QIAO Yu-chuan.An improved local weighted linear prediction model for chaotic times series[J].Chinese Physics.Letters,2014,31(1):1-9.
[11]周胜明,曲建岭,高峰.非线性支持向量回归在航空发动机性能参数预测中的应用[J].测控技术,2012,2:35-41.
[12]何立明.飞机推进系统原理[M].北京:国防工业出版社,2006.
[13]张科星.基于混沌时间序列理论的民航发动机性能参数预测模型研究[D].天津:中国民航大学,2009.
[14]Vaccari D A,Wang H K.Multivariate polynomial regression for identification of chaotic time series[J].Mathematical and Computer Modelling of Dynamical Systems,2007,13(4):395-412.
[15]Samanta B.Prediction of chaotic time series using computational intelligence[J].Expert Systems with Application,2011(38):11406-11411.
[2]Sanja G.Aircraft turbine engine control research at NASA glenn research center[R].NASA/TM-2013-217821,NASA,2013.
[3]赵连春,杰克,马丁利.飞机发动机控制—设计、系统分析和健康监视[M].北京:航空工业出版社,2011.
[4]Simo D L,Litt J S.A data filter for identifying steady-state operating points in engine flight data for condition monitoring applications[J].Journal of Engineering for Gas Turbines and Power,2011,133:1-8.
[5]Linda C.NASA aviation safety reporting system[R].NASA/ARC-E-DAA-TN2844,NASA,2014.
[6]Volphni A.Enhanced self turning on-board realtime model for aircraft engine performance health tracking[R].NASA/CR-2008-215272,Washington:NASA,2008.
[7]谭巍,李冬,樊照远,等.基于模型信息熵的航空发动机性能评估和可靠性分析[J].航空发动机,2011,37(5):45-48.
[8]王桓.电力时间序列的混沌识别与短期预测[D].长沙:湖南大学,2009.
[9]Sun L Y.Prediction of multivariable chaotic time series with local polynomial fitting[J].Computers and Mathematics with Application,2010,59:737-744.
[10]QU Jian-ling,WANG Xiao-fei,QIAO Yu-chuan.An improved local weighted linear prediction model for chaotic times series[J].Chinese Physics.Letters,2014,31(1):1-9.
[11]周胜明,曲建岭,高峰.非线性支持向量回归在航空发动机性能参数预测中的应用[J].测控技术,2012,2:35-41.
[12]何立明.飞机推进系统原理[M].北京:国防工业出版社,2006.
[13]张科星.基于混沌时间序列理论的民航发动机性能参数预测模型研究[D].天津:中国民航大学,2009.
[14]Vaccari D A,Wang H K.Multivariate polynomial regression for identification of chaotic time series[J].Mathematical and Computer Modelling of Dynamical Systems,2007,13(4):395-412.
[15]Samanta B.Prediction of chaotic time series using computational intelligence[J].Expert Systems with Application,2011(38):11406-11411.