基于NN-ELM的航空发动机燃油系统执行机构故障诊断

姜洁; 李秋红; 张高钱; 李业波

doi:10.13224/j.cnki.jasp.2016.02.029

基于NN-ELM的航空发动机燃油系统执行机构故障诊断

doi: 10.13224/j.cnki.jasp.2016.02.029

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

基金项目:

航空科学基金(20110652003)

江苏高校优势学科建设工程资助项目

中央高校基本科研业务专项基金(NN2012033)

详细信息

作者简介:
姜洁(1990-),女,江苏南通人,硕士生,主要研究方向为航空发动机故障诊断.

中图分类号: V233.7
计量
- 文章访问数: 1050
- HTML浏览量: 2
- PDF量: 429
- 被引次数: 0
出版历程
- 收稿日期: 2014-06-18
- 刊出日期: 2016-02-28

Fault diagnosis for actuators of aero-engine fuel system based on NN-ELM

Jiangsu Province Key Laboratory of Aerospace Power System, College of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China

摘要

摘要: 提出了一种航空发动机执行机构及其传感器单一故障诊断及定位方法.首先通过执行机构模型判断是否发生故障,然后运用发动机逆模型对故障进行定位.基于离线训练BP(back propagation)神经网络建立执行机构模型,根据某半物理仿真试验台的测试数据训练网络参数.提出离线训练和在线训练相结合的极端学习机(ELM)算法建立发动机逆模型,使网络在初始时刻就具有诊断能力,工作过程中具有适应能力,且在线训练过程采用阈值判别法筛选训练样本,减小了在线训练时间,提高了逆模型的实时性.以某型发动机燃油系统执行机构为例的设计和仿真结果表明:该诊断系统能够准确地对发动机在稳态和动态工况以及蜕化状态下的执行机构及其传感器单一故障进行准确诊断和定位,具有很好的实时性.
- 航空发动机 /
- 执行机构 /
- 故障诊断 /
- 神经网络 /
- 极端学习机
Abstract: A single fault diagnosis and location method of aero-engine actuator and its sensor was proposed. Fault of actuator was diagnosed according to the actuator model and located according to the inverse engine model. The actuator model was built based on offline training BP(back propagation) neural network (NN). The network parameters were trained according to the test data of a semi-physical simulation test bed. The inverse engine model based on offline and online extreme learning machine (ELM) had original diagnosis ability and adaptability during operation. The training samples were selected using the threshold discrimination, which can reduce the online training time and improve the real-time property of inverse model during the online training process. Design and simulation results of a certain engine fuel system actuator show that,the proposed system can diagnose and locate the single faults of engine actuator or its sensor accurately in steady state, dynamic state and degradation state. The real-time property can be satisfied.
- aero-engine /
- actuator /
- fault diagnosis /
- neural network (NN) /
- extreme learning machine

HTML

参考文献(17)

[1]	Garg S.Controls and health management technologies for intelligent aerospace propulsion systems[R].AIAA-2004-0949,2004.
[2]	Chen R H,Speyer J L.Sensor and actuator fault reconstruction[J].Journal of Guidance,Control and Dynamics,2004,27(2):186-196.
[3]	Garg S,Schadow K,Horn W,et al.Sensor and actuator needs for more intelligent gas turbine engines[R].NASA/TM-2010-216746,2010.
[4]	Kobayashi T,Simon D L.A hybrid neural network-genetic algorithm technique for aircraft engine performance diagnostics[R].AIAA-2001-3763,2001.
[5]	Dewallef P,Leonard O.On-line validation of measurements on jet engines using automatic learning methods[R].International Society for Air Breathing Engines,ISABE Paper 2001-1031,2001.
[6]	HUANG Xianghua.Sensor fault diagnosis and reconstruction of engine control system based on auto-associative neural network[J].Chinese Journal of Aeronautics,2004,17(1):23-27.
[7]	Zhou D H,Frank P M.Actuator fault diagnosis of a class of nonlinear systems in closed-loops: a case study[C]//United Kingdom Automatic Control Council International Conference.Duisburg,Germany:Institution of Engineering and Technology,1996:311-316.
[8]	Alessandri A,Caccia M,Veruggio G.Fault detection of actuator faults in unmanned underwater vehicles[J].Control Engineering Practice,1999,7(3):357-368.
[9]	Ho L M.Application of adaptive thresholds in robust fault detection of an electro-mechanical single-wheel steering actuator[J].Fault Detection,Supervision and Safety of Technical Processes,2012,8(1):259-264.
[10]	Napolitano M R,Silvestri G.Sensor validation using hardware-based on-line learning neural networks[J].IEEE Transactions on Aerospace and Electronic Systems,1998,34(2):56-66.
[11]	尹俊,郭迎清.神经网络和卡尔曼滤波器融合的航空发动机传感器故障诊断[J].计算机测量与控制,2011,19(8):1936-1942. YIN Jun,GUO Yingqing.Neural network and Kalman filter based fusion fault diagnosis for aero-engine sensor[J].Computer Measurement and Control,2011,19(8):1936-1942.(in Chinese)
[12]	刘艳春,杨德辉,刘艳丽,等.基于神经网络的某型飞机发动机故障诊断研究[J].电子设计工程,2012,20(11):89-92. LIU Yanchun,YANG Dehui,LIU Yanli,et al.Failure diagnose research for the plane engine of basic neural network[J].Electronic Design Engineering,2012,20(11):89-92.(in Chinese)
[13]	Huang G B,Zhu Q Y,Siew C K.Extreme learning machine:theory and applications[J].Neurocomputing,2006,70(1/2/3):489-501.
[14]	张弦,王宏力.基于贯序正则极端学习机的时间序列预测及其应用[J].航空学报,2011,32(7):1302-1308. ZHANG Xian,WANG Hongli.Time series prediction based on sequential regularized extreme learning machine and its application[J].Acta Aeronautica et Astronautica Sinica,2011,32(7):1302-1308.(in Chinese)
[15]	Huang G B,Liang N Y,Rong H J,et al.Online sequential extreme learning machine[R].Calgary,Canada:the International Association of Science and Technology for Development International Conference on Computational Intelligence,2005.
[16]	李业波,李秋红,王健康,等.基于ImOS-ELM的航空发动机传感器故障自适应诊断技术[J].航空学报,2013,34(10):2316-2324. LI Yebo,LI Qiuhong,WANG Jiankang,et al.Sensor fault adaptive diagnosis of aero-engine based on ImOS-ELM[J].Acta Aeronautica et Astronautica Sinica,2013,34(10):2316-2324.(in Chinese)
[17]	程月华,姜斌,杨明凯,等.应用自组织模糊神经网络估计卫星姿态系统执行机构故障[J].应用科技学报,2010,28(1):72-76. CHENG Yuehua,JIANG Bin,YANG Mingkai,et al.Self-organizing fuzzy neural network-based actuator fault estimation for satellite attitude systems[J].Journal of Applied Sciences,2010,28(1):72-76.(in Chinese)