为有效提取滚动轴承振动信号故障特征,提出了一种基于特征模态分解(Feature Mode Decomposition, FMD)与色散熵(Dispersion Entropy, DisEn)的信号特征提取方法。首先利用FMD方法将不同状态的滚动轴承振动信号分解为若干固有模态函数(Intrinsic Mode Function, IMF)分量;然后计算各IMF分量的DisEn,组合构建原始振动信号的特征向量。仿真实验表明该方法能有效提取滚动轴承振动信号特征,并且根据提取的特征能够较好地识别滚动轴承的故障类型。To effectively extract the vibration signal fault features of rolling bearings, this paper proposed a signal feature extraction method based on Feature Mode Decomposition (FMD) and Dispersion Entropy (DisEn). Firstly, the FMD method is used to decompose the vibration signals of rolling bearings in different states into several Intrinsic Mode Function (IMF) components. Then, the DisEn of each IMF component is calculated and combined to construct the feature vector of the original vibration signal. Simulation experiments show that this method can effectively extract the vibration signal characteristics of rolling bearings, and can identify the fault types of rolling bearings well based on the extracted features.
