航空发动机传感器信号重构的K-ELM方法

尤成新; 鲁峰; 黄金泉

doi:10.13224/j.cnki.jasp.2017.01.029

航空发动机传感器信号重构的K-ELM方法

doi: 10.13224/j.cnki.jasp.2017.01.029

尤成新^1,2,
鲁峰^1,2,3,
黄金泉^1,3

1.
南京航空航天大学能源与动力学院江苏省航空动力系统重点实验室，南京 210016
2.
中国航空发动机集团有限公司航空动力控制系统研究所，江苏无锡 214063
3.
先进航空发动机协同创新中心，北京 100191

基金项目: 国家自然科学基金(51276087)；中央高校基本科研业务费专项资金(NP2012504)；南京航空航天大学研究生创新基地（实验室）开放基金（kfjj20150205）

计量
- 文章访问数: 709
- HTML浏览量: 3
- PDF量: 372
- 被引次数: 0
出版历程
- 收稿日期: 2015-05-14
- 刊出日期: 2017-01-28

K-ELM method for sensor signal reconfiguration of aeroengine

摘要

摘要: 针对航空发动机传感器信号重构，提出了评价核极限学习机（KELM）模型性能的一种快速留一交叉验证方法.结果表明:该方法可以避免原始的留一验证方法N次模型的显式训练，将计算复杂度降低为原来的1/N（N为样本数目）.该算法可以快速准确评价核极限学习机的性能，为核极限学习机确定最优的核参数.
- 航空发动机 /
- 燃烧室航空发动机 /
- 传感器信号重构 /
- 核极限学习机 /
- 留一交叉验证方法 /
- 核参数
Abstract: Northwestern Polytechnical University，Xian 710072，China)(1.Jiangsu Province Key Laboratory of Aerospace Power System,College of Energy and Power Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China;2.Collaborative Innovation Center for Advanced AeroEngine,Beijing 100191,China;3.AeroEngine Control System Institute,Aero Engine (Group) Corporation of China,Wuxi Jiangsu 214063,China)Abstract：A fast leaveoneout cross validation method was presented to provide a criterion for kernelbased extreme learning machine (K-ELM) used for sensor signal reconfiguration of aeroengine. The procedure can avoid N times explicit training (N is the number of training samples) so that the computation cost was reduced 1/N when compared with normal leaveoneout procedure. Simulation results show that this method can provide a fast and accurate criterion, allowing to select best kernel parameters for K-ELM.
- aeroengine /
- combustoraeroengine /
- sensor signal reconfiguration /
- kernelbased extreme learning machine (K-ELM) /
- leaveoneout cross validation method /
- kernel parameters

HTML

参考文献(18)

[1]	赵永平.支持向量回归机及其在智能航空发动机参数估计中的应用［D］.南京:南京航空航天大学,2009. ZHAO Yongping.Support vector regressions and their applications to parameter estimation for intelligent aeroengines［D］.Nanjing:Nanjing University of Aeronautics and Astronautics,2009.(in Chinese)
[2]	鲁峰,黄金泉,陈煜,等.基于SPSOSVR的融合航空发动机传感器故障诊断［J］.航空动力学报,2009,24(8):1856-1865. LU Feng,HUANG Jinquan,CHEN Yu,et al.Research on sensor fault diagnosis of aeroengine based on data fusion of SPSOSVR［J］.Journal of Aerospace Power,2009,24(8):1856-1865.(in Chinese)
[3]	XUE Wei,GUO Yingqing.Aircraft engine sensor fault diagnostics based on estimation of engines health degradation［J］.Chinese Journal of Aeronautics,2009,22(1):18-21.
[4]	FENG Zhigang,Shida K,WANG Qi.Sensor fault detection and data recovery based on LSSVM predictor［J］.Chinese Journal of Scientific Instrument,2007,28(2):193-197.
[5]	ZHAO Yongping,SUN Jianguo.Fast online approximation for hard suppport vector regression and its application to analytical redundancy for aeroengine［J］.Chinese Journal of Aeronautics,2010,23(2):145-152.
[6]	徐启华,师军,耿帅.应用快速多分类SVM的航空发动机故障诊断方法［J］.推进技术,2012,33(6):961-967. XU Qihua,SHI Jun,GENG Shuai.Aeroengine fault diagnosis by a new fast multiclass support vector algorithm［J］.Journal of Propulsion Technology,2012,33(6):961-967.(in Chinese)
[7]	吴斌,尉询楷,冯悦,等.航空发动机混沌支持向量预测模型应用［J］.火力与指挥控制,2011,36(5):29-33. WU Bin,WEI Xunkai,FENG Yue,et al.Applications of chaotic support vector forecasting model for aeroengine［J］.Fire Control and Command Control,2011,36(5):29-33.(in Chinese)
[8]	徐启华,耿帅,师军.基于大规模训练集SVM的发动机故障诊断［J］.航空动力学报,2011,26(12):2841-2848. XU Qihua,GENG Shuai,SHI Jun.Fault diagnosis method for aeroengine based on SVM with largescale training set［J］.Journal of Aerospace Power,2011,26(12):2841-2848.(in Chinese)
[9]	陈毅,黄金泉,张鹏.航空发动机控制系统传感器FDIA系统仿真［J］.航空动力学报,2008,23(2):396-400. CHEN Yi,HUANG Jinquan,ZHANG Peng.FDIA simulation of aeroengine control system sensor FDIA system［J］.Journal of Aerospace Power,2008,23(2):396-400. (in Chinese)
[10]	Huang G B,Zhu Q Y,Chee K S.Extreme learning machine:theory and applications［J］.Neurocomputing,2006,70(1/2/3):489-501.
[11]	Hua W,Mao C Q,Zhang L J.A brief review of machine learning and its application［C］∥Proceedings of International Conference on Information Engineering and Computer Science.Wuhan:IEEE,2009:1-4.
[12]	孙毅刚,刘静雅,赵珍.基于极限学习机的航空发动机传感器故障诊断［J］.传感器与微系统,2014(8):23-26. SUN Yigang,LIU Jingya,ZHAO Zhen.Aircraft engine sensor fault diagnosis based on extream learning machine［J］.Transducer and Microsystem Technologies,2014(8):23-26.(in Chinese)
[13]	李业波,李秋红,黄向华,等.航空发动机传感器故障与部件故障诊断技术［J］.北京航空航天大学学报,2013,39(9):1174-1180. LI Yebo,LI Qiuhong,HUANG Xianghua et al.Fault diagnosis for sensors and components of aeroengine［J］.Journal of Beijing University of Aeronautics and Astronautics,2013,39(9):1174-1180.(in Chinese)
[14]	Huang G B,Zhao H G,Ding X J,et al.Extreme learning machine for regression and multiclass classification［J］.IEEE Transactions on Systems,Man,and Cybernetics:Part B Cybernetics,2012,42(2):513-529.
[15]	刘学艺.极限学习机算法及其在高炉冶炼过程建模中的应用研究［D］.杭州:浙江大学,2013. LIU Xueyi.Research on extreme learning machine and its application to blast furnace ironmaking process［D］.Hangzhou:Zhejiang University,2013.(in Chinese)
[16]	Cawley G C,Talbot N.Fast exact leaveoneout crossvalidation of sparse leastsquares support vector machines［J］.Neural Networks,2004,17(10):1467-1475.
[17]	Ying Z,Keong K C.Fast leaveoneout evaluation and improvement on inference for LSSVMs［R］.Cambridge,UK:The 17th International Conference on Pattern Recognition,2004.
[18]	Frénay B,Verleysen M.Parameterinsensitive kernel in extreme learning for nonlinear support vector regression［J］.Neurocomputing,2011,74(16):25262531.