一种航空发动机性能监控的免疫神经网络模型

侯胜利; 王威; 胡金海; 周根娜

一种航空发动机性能监控的免疫神经网络模型

1.
徐州空军学院, 徐州 221006
2.
空军工程大学工程学院, 西安 710038

计量
- 文章访问数: 1456
- HTML浏览量: 3
- PDF量: 462
- 被引次数: 0
出版历程
- 收稿日期: 2007-09-17
- 修回日期: 2008-01-17
- 刊出日期: 2008-09-28

Immune-neural networks model of aeroengine performance monitoring

1.
Xuzhou Air Force College, Xuzhou 221006, China
2.
The Engineering Institute, Air Force Engineering University, Xi'an 710038, China

摘要

摘要: 提出了一种基于免疫神经网络的航空发动机性能监控与故障检测模型.利用人工免疫系统的识别机理,并结合人工神经网络,确定发动机性能偏离正常值的程度(异常度),实现发动机性能趋势的监控.该方法能够灵敏、准确地反映发动机整体性能的变化情况,提高发动机性能正常与否的识别率,并以此来发现发动机潜在早期故障,防止故障的扩大.通过对某型涡扇发动机进行监控,证明该方法确实有效.
- 免疫神经网络 /
- 航空发动机 /
- 性能监控 /
- 人工免疫系统
Abstract: Amodel for aeroengine performance monitoring and fault detection was proposed based on immune-neural networks.With immune recognition mechanism of the artificial immune system,this model was combined with artificial neural networks to attain the degrees of engine performance's abnormal state for monitoring engine performance.The approach can sensitively and accurately reflect the whole performance of the engine.Meanwhile,this method improves the rate of identifying whether the performance of the engine is normal or not,finds out the potential forepart fault of engine and prevents the spread of the fault.The validity of this method is testified by monitoring certain type of turbo-fan engine.
- immune-neural networks /
- aeroengine /
- performance monitoring /
- artificial immune system

HTML

参考文献(9)

[1]	谢寿生.某型飞机发动机故障诊断与性能趋势监测研究[D].西安:西北工业大学,1998.XIE Shousheng.Investigation on fault diagnosis and performanee tendency monitoring for certain type of turbofan engine[D].Xi' an:Northwes tern Polytechnical University,1998.(in Chinese)
[2]	胡金海,谢寿生.基于遗传算法的航空发动机性能监控与故障诊断[J].推进技术,2003,24(3):198-200.HU Jinhai,XIE Shousheng.The performance monitoring and fault diagnoses of engines based genetic algorithm[J].Journal of Propulsion Technology,2003,24 (3),198-200.(in Chinese)
[3]	侯胜利,胡金海,李应红.基于混沌变量的航空发动机性能监控与故障诊断[J].航空动力学报,2005,20(2):314-317.HOU Shengli,HU Jinhai,LI Yinghong.Aeroengine performance monitoring and fault diagnosis based on chaos variable[J].Journal of Aerospace Power,2005,20 (2):314-317.(in Chinese)
[4]	侯胜利,李应红,尉询楷.基于主元核相似度免疫机制的故障诊断方法及应用[J].推进技术,2006,27(2):154-157.HOU Shengli,LI Yinghong,WEI Xunkai.Fault diagnosis based on immunity strategy with similarity measurement of principle component kernel and its application[J].Journal of Propulsion Technology,2006,27 (2):154-157.(in Chinese)
[5]	侯胜利,李应红,尉询楷.基于免疫聚类分析的特征提取及其在发动机故障诊断中的应用[J].推进技术,2006,27(6):554-558.HOU Shengli,LI Yinghong,WEI Xunkai.Feature extraction based on immune clustering analysis and its application in aeroengine fault diagnosis[J].Journal of Propulsion Technology,2006,27(6):554-558.(in Chinese)
[6]	Gonzalez F,Dasgupta D,Kozma R.Combining negative selection and classification techniques for anomaly detection[R].Hawaii:Proceedings of the Congress on Evolutionary Computation,May 2002,705-710.
[7]	Esponda F,Forrest S,Helman P.A formal framework for positive and negative detection schemes[J].IEEE Trans.Syst.,Man,Cybern.B,Cybern.,2004,34(1):357-373.
[8]	李珈,陶增元.某型发动机性能衰退的统计分析和预测[J].航空动力学报,1994,7(2):173-176.LI Jia,TAO Zengyuan.Statisical analysis of aeroengine and its significance[J].,iournal of Aerospace Power,1994,7(2):173-176.(in Chinese)
[9]	Roemer M J,Nwadiogbu E O.Development of diagnostic and prognostic technologies for aerospace health management applications[R].Munich,Germany:Paper 2001-GT-30,ASME and IGTI Turbo Expo 2001,February 2001.