基于ELMD能量矩的坦克变速箱特征提取方法

Feature Extraction Method for Tank Gearbox Based on ELMD

针对坦克变速箱故障时振动信号的复杂性和不确定性,提出了总体局部均值分解(Ensemble Local Mean Decomposition,ELMD)能量矩的故障特征提取方法,对坦克实车试验中测取的变速箱正常、主轴滚动轴承滚动体点蚀和3挡被动齿轮断齿3种状态下的振动信号进行计算。结果表明:该方法提取的特征能很好地反映变速箱的状态,从而实现对变速箱的故障诊断。

Aiming at the complexity and the uncertainty of the gearbox fault vibration signal,a feature ex-traction method named Ensemble Local Mean Decomposition (ELMD)energy moment is presented.The vibration signals acquired from the actual tank gearbox with normal,bearing pitting corrosion and gear rupture are respectively calculated.The analysis results show that the feature can reflect gearbox condi-tions well and can be used to diagnose gearbox faults.