基于小波神经网络的直升机主减速器故障诊断系统
Fault diagnostics system for helicopter main gearbox using wavelet neural network
-
摘要: 应用离散小波变换(DWT)和神经网络相结合构建直升机主减速器速器故障诊断系统: DWT对振动信号进行特征提取,神经网络对故障进行辨识和分类。阐述了DWT、帕塞瓦尔定理和广义回归神经网络(GRNN)基本理论,提出了直升机主减速器的故障诊断系统流程图,最后用某型直升机飞行时主减速器上的振动数据对该系统进行验证。实验使用了BPNN(back-propagation neural network)和GRNN两种神经网络,结果表明:提出的故障诊断系统能对主减速器故障进行较好的辨识和分类,这将为直升机主减速器故障诊断系统的进一步开发提供新的技术参考。
-
关键词:
- 故障诊断 /
- 离散小波变换(DWT) /
- 广义回归神经网络(GRNN) /
- 帕塞瓦尔定理 /
- 主减速器
Abstract: A fault diagnostics system for helicopter main gearbox(MGB) was constructed using discrete wavelet transform(DWT) and neural network,and the DWT was used to extract feature vectors and neural network was used for fault distinguish and classification. Firstly, the theory of DWT, Parseval theorem and GRNN were introduced, and then,the flowchart of fault diagnostics system for helicopter MGB was proposed, finally, the system was verified by the vibration data which were collected during helicopter flying, and both generalized regression neural network(GRNN) and back-propagation neural network(BPNN) were used and compared on the experimental platform. Experimental results indicate that the proposed diagnostics system can distinguish the MGB fault better, which would provide a new technical reference for the further development of helicopter MGB fault diagnostics system. -
[1] Samuel P D,Pines D J.A review of vibration-based techniques for helicopter transmission diagnostics[J].Journal of Sound and Vibration,2005,282(1/2):475-508. [2] Blunt D M,Keller J A.Detection of a fatigue crack in a UH-60A planet gear carrier using vibration analysis[J].Mechanical Systems and Signal Processing,2006,20(8):2095-2111. [3] GrabillP,Jacobs J,Johnson T,et al.Helicopter structural life modeling:flight regime and gross weight estimation .ASME Paper GT2007-27894,2007. [4] Wang W J.Application of wavelet to gearbox vibration signals for fault detection[J].Journal of Sound and Vibration,1996,192(5):927-939. [5] Kar C,Mohanty A R.Monitoring gear vibrations through motor current signature analysis and wavelet transform[J].Mechanical Systems and Signal Processing,2006,20(1):158-187. [6] Avci E.Performance comparison of wavelet families for analog modulation classification using expert discrete wavelet neural network system[J].Expert Systems with Applications,2007,33(1):23-35. [7] Gaing Z L.Wavelet-based neural network for power disturbance recognition and classification[J].IEEE Transactions on Power Delivery,2004,19(4):1560-1568. [8] Wang D Y,Zhang W Z,Zhang J G.Fault bearing identification based on wavelet packet transform technique and artificial neural network //Proceeding of 2010 International Conference on System Science,Engineering Design and Manufacturing Informatization.Yichang,Hubei China:IEEE Computer Society,2010:11-14. [9] WU Jianda,LIU Chiuhong .An expert system for fault diagnosis in internal combustion engines using wavelet packet transform and neural network[J].Expert Systems with Applications,2009,36(3):4278-4286. [10] Saravanan N,Ramachandran K I.Incipient gear box fault diagnosis using discrete wavelet transform (DWT) for feature extraction and classification using artificial neural network (ANN)[J].Expert Systems with Applications,2010,37(6):4168-4181. [11] WU Jianda,HUANG Chengkai,CHANG Yowei.Fault diagnosis for internal combustion engines using intake manifold pressure and artificial neural network[J].Expert Systems with Applications,2010,37(2):949-958. [12] WU Jianda,KUO Junming .An automotive generator fault diagnosis system using discrete wavelet transform and artificial neural network[J].Expert Systems with Applications,2009,36(6):9776-9783. [13] Goulermas J Y,ZENG Xiaojun,Liatsis P,et al.Generalized regression neural networks with multiple-bandwidth sharing and hybrid optimization[J] .IEEE Transactions on Systems,Man,and Cybernetics Part B:Cybernetics,2007,37(6):1434-1445.
点击查看大图
计量
- 文章访问数: 1459
- HTML浏览量: 1
- PDF量: 623
- 被引次数: 0