基于拉普拉斯分值和模糊C均值聚类的滚动轴承故障诊断

针对滚动轴承故障振动信号的非平稳特征和故障征兆的模糊性，提出了基于拉普拉斯分值和模糊C均值（FCM）聚类的滚动轴承故障诊断方法。该方法首先在时域和频域对滚动轴承振动信号进行特征提取，组成初始特征向量;然后利用拉普拉斯分值进行特征选择，形成故障特征向量;最后以FCM聚类为故障分类器，实现滚动轴承不同故障类型的识别。应用实例和对比实验表明，该方法能有效提取滚动轴承振动信号特征，诊断滚动轴承故障。

Rolling Bearing Fault Diagnosis Based on Laplacian Score and Fuzzy C-means Clustering

According to the non-stationary features and fuzzy fault symptoms of the vibration signals of a rolling bearing with faults, a fault diagnosis method of rolling bearings was proposed using Laplacian score and FCM clustering. Firstly, the features of a vibration signal of a rolling bearing were extracted in time domain and frequency domain, from which an initial feature vector was formed. Then by using Laplacian score method to select feature, fault feature vectors were obtained. Finally, a FCM clustering method was used as a fault feature classifier to recognize different fault types of a rolling bearing. Application examples and contrast tests show that this method can be used to extract the features of vibration signals of rolling bearings and diagnoses the faults of rolling bearings effectively.