摘要
提出了基于经验模态分解(EMD)和径向基(RBF)的滚动轴承故障诊断方法。同时给出了诊断实例:利用EMD将滚动轴承震动信号分解成若干个固有模态函数(IMF)分量,然后对每一个IMF进行Hilbert变换,最后提取每个IMF分量的平均频率及能量比,并以此作为RBF神经网络的输入参数来判断轴承的工作状态。诊断结果表明该方法能够实现轴承故障的诊断,而且速度快,准确率高,易于实现自动化监测。
A roller bearing fault diagnosis method was proposed,which was based on EMD and RBF.At the same time,one example of this method was given.EMD method was used to decompose the roller bearing vibration signal into a finite number of IMFs,then Hilbert transformation was used to distill average frequency and energy percentage from each IMF,the average frequency and energy percentage were regarded as the fault characteristic vectors and served as input parameters of RBF nerve network to classify working condition of roller bearings.The experimental results showed that the method can classify the working condition of roller bearings fast,accurate and can be used in atomization of the fault diagnosis.
出处
《舰船电子工程》
2014年第7期149-151,172,共4页
Ship Electronic Engineering
