基于互补的总体经验模式分解算法的齿轮箱故障诊断

Fault Diagnosis of Gearboxes based on Complementary Ensemble Empirical Mode Decomposition

针对经验模式分解(EMD)和总体经验模式分解(EEMD)算法在齿轮箱故障诊断中的缺陷,提出了一种基于互补的总体经验模式分解(CEEMD)算法的齿轮箱故障诊断方法。首先介绍了CEEMD方法,然后将CEEMD方法用于实际齿轮箱的故障诊断中。结果表明,与基于EMD/EEMD算法的齿轮箱故障诊断方法相比,基于CEEMD算法的齿轮箱故障诊断方法不但可以有效地克服模态混叠和能量泄露现象,而且大大提高了计算效率,为齿轮箱的故障诊断提供了一种新的方法。

Aiming at the shortcomings of both empirical mode decomposition （EMD） and ensemble empirical mode decomposition （EEMD） in fault diagnosis of gearboxes, a novel method for fault diagnosis of gearboxes based on complementary ensemble empirical mode decomposition （CEEMD） is proposed. For one thing, the CEEMD method is introduced. Subsequently, the CEEMD method, as well as the EMD/EEMD method, is used to explore the signals from the realistic gearbox with a nonalignment fault. As a result, compared with the EMD/EEMD based method, the CEEMD based method not only successfully relieves mode mixing and energy leakage of the EMD method, but also greatly raises the computation efficiency of the EEMD method. Moreover, the CEEMD method seems to be a hopeful method for fault diagnosis of gearboxes.