基于灰度图像纹理分析的电主轴不平衡故障诊断方法

Unbalance fault diagnosis method of electric spindle based on gray image texture analysis

针对转子不平衡,首次提出了基于灰度图像纹理分析的故障诊断方法。首先将转子振动信号转化为二维灰度图像,并利用局部二值模式提取灰度图像的纹理特征;通过二维傅里叶变换提取灰度图像的特征频率,并采用灰度图像二维矩阵的平方和来表征图像的明暗程度,由此来区分不同程度的不平衡故障。在某电主轴系统平台上,完成了转子正常和3种不同程度转子不平衡的故障诊断试验,结果表明所提出的方法能够有效区分不同程度的转子不平衡,为旋转机械的故障诊断提供了一种新方法。

For the rotor imbalance,a fault diagnosis method based on gray image texture analysis is proposed for the first time.Firstly,the rotor vibration signal is converted into a two-dimensional gray image,and the texture feature of gray image is extracted by using a Local Binary Patterns;the feature frequency of gray image is extracted by two-dimensional Fourier transform,and the square of two-dimensional matrix of gray image is used to characterize the brightness of image,thereby distinguishing different degrees of unbalanced faults.On the platform of an electric spindle system,the fault diagnosis test of normal rotor and three different degrees of rotor imbalance is completed.The results show that the proposed method can effectively distinguish different degrees of rotor imbalance to provide a new method for fault diagnosis of rotating machinery.