基于IPSOElman神经网络的航空发动机故障诊断

皮骏; 黄江博

doi:10.13224/j.cnki.jasp.2017.12.028

基于IPSOElman神经网络的航空发动机故障诊断

doi: 10.13224/j.cnki.jasp.2017.12.028

皮骏¹,
黄江博²

1.
中国民航大学中欧航空工程师学院,天津 300300
2.
中国民航大学航空工程学院,天津 300300

基金项目: 中央高校基本科研业务费中国民航大学专项资金（3122013H001）

计量
- 文章访问数: 843
- HTML浏览量: 0
- PDF量: 411
- 被引次数: 0
出版历程
- 收稿日期: 2017-03-03
- 刊出日期: 2017-12-28

Aeroengine fault diagnosis based on IPSOElman neural network

摘要

摘要: 为提高航空发动机故障诊断的精度,提出改进粒子群优化的Elman神经网络对航空发动机故障诊断的方法。利用MIV(平均影响值)对神经网络的输入端自变量进行筛选，降低输入维度；采用改进粒子群优化算法对Elman神经网络的权值和阀值进行优化，并对优化的神经网络进行训练；用训练好的神经网络对航空发动机故障进行诊断并与常规的BP（back propagation）、Elman神经网络、GM（1,n）、SVM (support vector machines)进行对比。仿真结果表明：IPSOElman(improved particle swarm optimization Elman neural network)神经网络的诊断误差在不同数量训练样本时都小于其他方法，并且在参选故障诊断的性能参数不同时，其诊断误差相近，展现出较强的适应能力。
- 航空发动机 /
- Elman神经网络 /
- 平均影响值 /
- 改进粒子群优化算法 /
- 故障诊断
Abstract: An Elman neural network optimized by improved particle swarm optimization algorithm was proposed to improve the accuracy of aeroengine fault diagnosis. The input variables of the neural network were selected by MIV (mean impact value) to reduce the dimension. The improved particle swarm optimization algorithm was used to optimize the weights and thresholds of the Elman neural network, and the optimized neural network was trained. The trained neural network was used to diagnose the aeroengine fault and compared with the conventional BP（back propagation）, Elman neural networks, GM(1,n), SVM (support vector machines). The simulation results show that the diagnostic error of IPSOElman (improved particle swarm optimization Elman neural network) is smaller than other methods，and it has a good diagnosis ability and strong adaptability when the selection fault diagnosis performance parameters have changed.
- aero-engine /
- Elman neural network /
- mean impact value /
- imporved particle swarm optimization algorithm /
- fault diagnosis

HTML

参考文献(18)

[1]	曲建岭,唐昌盛,肖辉雄.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.Integrated diagnosis of aeroegines’gas path faults using artificial neural network［J］.Journal of Aerospace Power,2008,23(11):2124-2127.（in Chinese）
[2]	陈恬,孙建国.粗糙集与神经网络在航空发动机气路故障诊断中的应用［J］.航空动力学报，2006，21(1):207-212.CHEN Tian,SUN Jianguo.Aeroegine gas path fault disgnoeie using rough sets and nerual networks［J］.Journal of Aerospace Power,2006,21(1):207-212.（in Chinese）
[3]	丁刚,徐敏强,侯立国.基于过程神经网络的航空发动机排气温度预测［J］.航空动力学报,2009,24(5):1035-1039.DING Gang,XU Minqiang,HOU Liguo.Prediction of aeroengine exhaust gas temperature using processneural network［J］.Journal of Aerospace Power,2009,24(5):1035-1039.(in Chinese）
[4]	VOLPONI A J,DE POLD H,GANGULI R.The use of kalman filter and neural network methodologies in gas turbine performance diagnostics:a comparative study［J］.Journal of Engineering for Gas Turbines and Power,2003,125(4):917-924.
[5]	LEE S M,CHOI W J,ROH T S.A study on separate learning algorithm using support vector machine for defect diagnostics of gas turbine engine［J］.Journal of Mechanical Science and Technology,2008,22(12):2489-2497.
[6]	CHANG Xiaodong,HUANG Jinquan,LU Feng.Robust inflight sensor fault diagnostics for aircraft engine based on sliding mode observers［J］.Sensors,2017,17(4):835.1-835.15.
[7]	JOESPH C G,GARY D R.专家系统原理与编程［M］.印鉴，刘星成，汤庸，等译.北京:科学出版社,2007.
[8]	温熙森.模式识别与状态监控［M］.北京:科学出版社，2007.
[9]	肖建华.智能模式识别方法［M］.广州：华南理工大学出版社,2007.
[10]	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）
[11]	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）
[12]	陈果.用结构自适应神经网络预测航空发动机性能趋势［J］.航空学报,2007,28(3):535-539.CHEN Guo.Forecasting engine performance trend by using structure selfadaptive neural network［J］.Acta Aeronautica et Astronautica sinica,2007,28(3):535-539.(in Chinese）
[13]	傅荟璇,赵红，王宇超，等.MATLAB神经网络应用设计［M］.北京:机械工业出版社,2010.
[14]	史峰,王小川,郁磊,等MATLAB神经网络30个案列分析［M］.北京:北京航空航天大学出版社,2010.
[15]	李东年,周以齐.采用改进粒子群优化粒子滤波的三维人手跟踪［J］.光学精密工程,2014,22(10):2870-2878.LI Dongnian,ZHOU Yiqi.Three dimensional hand tracking by improved particle swarm optimized particle filter［J］.Optics and Precision Engineering,2014,22(10):2870-2878.(in Chinese）
[16]	LING S H,IU H,LEUNG F H,et al.Improved hybrid particle swarm optimized wavelet neural network for modeling the development of fluid dispensing for electronic packaging［J］.IEEE Transactions on Industrial Electronics,2008,55(9):3447-3460.
[17]	范作民,孙春林,白杰.航空发动机故障诊断导论［M］.北京:科学出版社,2004.
[18]	陈法法,汤宝平,黄庆卿.免疫遗传优化Elman神经网络的旋转机械故障诊断［J］.重庆大学学报,2012,35(5):7-13.CHEN Fafa,TANG Baoping,HUANG Qingqing.Ratating machinery fault diagnosis based on Elman neural network optimized by immune genetic algorithm［J］.Journal of Chongqing University,2012,35(5):7-13.(in Chinese）