论文部分内容阅读
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。
The combination of discrete wavelet transform (DWT) and neural network is used to construct the helicopter main gearbox fault diagnosis system: DWT is used to extract the characteristic of vibration signals and the neural network is used to identify and classify the faults. The basic theories of DWT, Passewahl and GRNN are expounded. A flow chart of fault diagnosis system of helicopter main reducer is put forward. Finally, the system is carried out by the vibration data of the main reducer when a helicopter is flying verification. The experiments use BPNN and GRNN neural networks. The results show that the proposed fault diagnosis system can better identify and classify the main reducer fault, which will be the main reducer fault diagnosis system The further development of the new technical reference.