Research on Feature Extraction and Classification Method of Vibration Signal of Escalator Sprocket Bearing  

作　　者：Deyang Liu Yuhang Su Ningxiang Yang Jianxun Chen Jicheng Li 

机构地区：[1]Zhuhai Branch,Guangdong institute of Special Equipment Inspection and Research,Zhuhai,Guangdong,China

出　　处：《电气工程与自动化（中英文版）》2023年第1期1-10,共10页Electrical Engineering and Automation

摘　　要：In order to improve the accuracy of escalator sprocket bearing fault diagnosis,the problem of the feature extraction method of bearing vibration signal is addressed.In this paper,empirical mode is used to decompose the original signal,and the optimal modal component among the multiple modal components is obtained after the optimization decomposition is selected by the envelope spectrum method,and the multi-angle feature measure is introduced to extract the fault characteristic value.According to the vibration characteristics of the bearing vibration signal data,a bearing signal feature group that is more inclined to the fault feature category information is established,which avoids the absolute problem of extracting a single metric feature.The fuzzy C-means clustering algorithm is used to cluster the sample data with similar characteristics into the same cluster area,which effectively solves the problem that a single measurement analysis cannot characterize the complex internal characteristics ofthe bearing vibration signal.

关 键 词：BEARING VIBRATION Multi-Angle Feature Measurement Signal Feature Group Empirical Mode Fuzzy C-Means Clustering 

分 类 号：TN9[电子电信—信息与通信工程]