ESMD-SRCC与GG聚类在轴承故障诊断的应用  

Application of ESMD-SRCC and GG Clustering in Bearing Fault Diagnosis

作　　者：黄文静 戚建国 Huang Wen-jing;Qi Jian-guo(Hebei Vocational University of Industry and Technology,Hebei Shijiazhuang 050091;ELEKTA Instrument Ltd,Beijing Branch,Beijing 100000)

机构地区：[1]河北工业职业技术大学智能制造学院,河北石家庄050091 [2]医科达(北京)医疗器械有限公司,北京100000

出　　处：《内燃机与配件》2024年第10期101-103,共3页Internal Combustion Engine & Parts

基　　金：河北省冶金工业过程数字化控制技术创新中心支撑,编号:SG2021185.

摘　　要：轴承是旋转机械的关键设备,一旦发生故障会造成严重的经济损失及人员伤亡。对轴承进行状态监测及故障诊断,是机械安全运行的重要保证。为提高轴承故障诊断的准确性,以轴承外圈、内圈、滚动体故障为例,通过ESMD分解有效解决传统EMD模态混叠问题;同时计算SRCC,提取关联性大的IMF分量作为轴承故障的特征向量;再将特征向量输出到GG聚类中进行模式识别。通过仿真验证,ESMD-SRCC与GG聚类的方法实现了轴承故障的准确识别。Bearings are key equipment in rotating machinery,and once they fail,they can cause serious economic losses and casualties.Monitoring the condition and diagnosing faults of bearings is an important guarantee for the safe operation of machinery.To improve the accuracy of bearing fault diagnosis,taking bearing outer ring,inner ring,and rolling element faults as examples,ESMD decomposition can effectively solve the problem of traditional EMD mode aliasing.Calculating SRCC,IMF components with high correlation can be extracted as feature vectors for bearing faults.Then output the feature vectors to GG clustering for pattern recognition.Through simulation verification,the ESMD-SRCC and GG clustering methods have achieved accurate identification of bearing faults.

关 键 词：轴承 故障诊断 ESMD分解 GG聚类 

分 类 号：TH133.3[机械工程—机械制造及自动化]