应用时频图像纹理特征的行星齿轮故障诊断

Fault Diagnosis of Planetary Gear Used Time-Frequency Image Texture Features

行星齿轮箱结构复杂,当发生故障时其振动信号呈非线性非平稳特点且故障信号微弱,为了能够准确提取行星齿轮磨损故障信息的特征,提出局部均值分解(local mean decomposition,简称LMD)结合S变换(LMD-S)的信号处理方法,且转化为时频分布图像,应用时频图像纹理特征进行行星齿轮故障诊断。首先,把振动信号经由LMD-S变换处理后利用相关分析方法滤除干扰且转化为时频分布图像;其次,利用非均匀局部二值模式(local binary patterns,简称LBP)提取不同工况下采集数据的图像纹理特征;最后,采用极限学习机识别出3种故障类型,故障识别准确率达到90%,证明了此方法的有效性。

The structure of the planetary gearbox is very complicated.When a fault occurs,its vibration signal ap⁃pears non-linear and non-stationary feature,and the fault signal is weak.In order to accurately extract features expressing planetary gear failure information,the signal processing method of local mean decomposition(LMD)combined with S-transform is proposed,and transform it into time-frequency distribution image.First,the vibration signal is processed by LMD-S transform,then the interference is filtered by correlation analysis method and transformed into time-frequency distributed image.Subsequently,the non-uniform local binary pat⁃tern(LBP)is used to extract image texture features under different working conditions.Finally,the limited learning machine is used to identify three fault types.The accuracy of fault recognition reaches 90%,which proves the effectiveness of this method.