摘要
提出应用频谱法和小波神经网络对水电机组的振动故障进行诊断。在对水电机组振动信号进行频谱分析后,提取该信号在频率域的特征量,将频谱特征向量作为学习样本,通过训练,使构造的小波神经网络能够反映频谱特征向量和故障类型之间的映射关系,从而达到故障诊断的目的。诊断结果表明,与常规神经网络诊断方法相比,频谱分析与这种小波神经网络相结合的方法进行故障诊断简单有效、并具有诊断速度快和泛化能力强等优点。
The vibration fault diagnosis of hydro-turbine generating unit is investigated by the method of spectrum analysis and wavelet neural network classifier. After collecting the characteristics of this signal in frequency domain, the samples are learned to train the constructed wavelet neural network （WNN） for realizing the mapping relationship between the fault and the spectrum characteristic, this method can be used for diagnosis of the unit faults efficiently. The fault diagnosis experiments show that the proposed method has a better diagnostic, fast and generalized performances.
出处
《水力发电学报》
EI
CSCD
北大核心
2007年第1期123-128,共6页
Journal of Hydroelectric Engineering
基金
国家自然基金重点项目资助(90410019)
关键词
水电机组
故障诊断
频谱分析
小波神经网络
神经网络
hydro-turbine generating unit
fault diagnosis
spectrum analysis
wavelet network
neural network
