基于VMD和卷积深度信念网络的风电机组行星齿轮箱故障检测

针对传统的故障诊断方法面对风力发电机组行星齿轮箱振动信号时处理范围有限的问题,提出了一种基于VMD和卷积深度信念网络相结合的智能诊断方法,首先利用VMD对原始信号进行分解,基于峭度准则提取出冲击含量较大的本征模态函数,将特征信息明显的分量融合在一起组成多通道的输入,然后利用卷积深度信念网络进行特征提取,最后将特征输入到...

Fault Diagnosis of Wind Turbine Planetary Gearbox Based on Variational Mode Decomposition and Convolution Depth Belief Networks

Aiming at the problem that the traditional fault diagnosis method exists limited treatment range for dealing with the vibration signal of planetary gearbox of wind turbine,an intelligent diagnosis method based the combination of variable mode decomposition(VMD)and convolutional deep belief networks(DCBN)is proposed.Firstly,VMD is used to decompose the original signal,and the eigen mode function with larger impact is extracted by kurtosis criterion.Then the obvious components of the feature information are fused together to form the multi-channel input,and DCBN is used to extract the feature.Finally,the feature is input into the classifier for fault identification and classification.The experimental results show that the method can accurately classify the working conditions of wind turbine planetary gearbox and identify the fault types.