自适应广义形态滤波和GG聚类在轴承故障识别中的应用研究

Application research of adaptive generalized morphological filtering and GG clustering in bearing fault identification

针对复杂工况下滚动轴承受机械噪声等因素影响轴承故障类型区分难的问题,提出了一种基于自适应广义形态滤波和GG聚类的轴承故障诊断方法。采用自适应广义形态滤波对轴承振动信号进行降噪处理,对降噪后的信号进行变模式分解,去除虚假分量和噪声分量,最后对去噪后故障特征较多的信号分量求解近似熵,作为特征向量输入GG聚类分类器中,达到故障分类。仿真实验结果证明该方法能有效提取信号特征信息,准确识别故障类型。

In order to improve the bearing type under the complicated working conditions and solve the difficulty to distinguish the bearing fault type,this paper proposes a bearing fault diagnosis method based on adaptive generalized morphological filtering and GG clustering.The method firstly uses adaptive generalized morphological filtering to denoise the bearing vibration signal,and then performs variable mode decomposition on the denoised signal to remove the false component and noise component.Finally,the signal component with more fault characteristics after denoising is solved by approximate entropy and is input into the GG cluster classifier as a feature vector to achieve the purpose of fault classification.The simulation results show that the method can effectively extract the signal characteristic information and accurately identify the fault type.