滚动轴承剩余使用寿命预测综述  

Review on Remaining Useful Life Prediction of Rolling Bearing

作　　者：张金豹 邹天刚[1] 王敏[1] 桂鹏[1] 戈红霞[1] 王成[1] ZHANG Jinbao;ZOU Tiangang;WANG Min;GUI Peng;GE Hongxia;WANG Cheng(Science and Technology on Vehicle Transmission Laboratory,China North Vehicle Research Institute,Beijing 100072,China)

机构地区：[1]中国北方车辆研究所车辆传动重点实验室,北京100072

出　　处：《机械科学与技术》2023年第1期1-23,共23页Mechanical Science and Technology for Aerospace Engineering

摘　　要：滚动轴承作为旋转机械的关键零部件,其剩余使用寿命(RUL)预测对生产维修和人身安全具有重要意义。由于滚动轴承复杂多变的工作环境,使得同工况的参考样本少而变工况的参考样本较多,具有不平衡、不完整、无标签及噪声干扰等特性,增加了滚动轴承RUL预测的困难。随着大数据时代的来临和人工智能的发展,滚动轴承RUL预测方法也变得更加丰富。因此,在故障预测与健康管理(PHM)的框架下,对滚动轴承失效模式和故障数据特点进行阐述,对故障特征提取、降维和融合方法以及得到的性能退化指标分别进行了分类和对比分析。结合数据驱动算法,对滚动轴承RUL的预测方法、模型选择和评估标准进行了梳理和对比。最后对滚动轴承RUL预测未来的发展趋势进行了展望。Rolling bearing are a key component of rotating machinery,and remaining useful life prediction of them will be of great significance to production,maintenance and personal safety.Due to the complex and changeable working environment of the rolling bearing,there are fewer reference samples in the same working condition but more in different working conditions.Moreover,the samples have the characteristics of unbalanced,incomplete,no label and noise interference,which increases the difficulty of RUL prediction.With the advent of the era of big data and the development of artificial intelligence,rolling bearing RUL prediction methods have become more abundant.Therefore,based on the framework of prognosis and health management,the failure modes and fault data characteristics of the rolling bearing are stated,methods concerning fault feature extraction,dimension reduction and fusion,as well as the obtained performance degradation indicators are respectively classified and contrastive analysis are performed.Combining with the data driven algorithms,the prediction approach,model selection and evaluation criteria of rolling bearing RUL are sorted and compared.Finally,the future development trend of rolling bearing RUL prediction is prospected.

关 键 词：滚动轴承 剩余使用寿命 性能退化指标 数据驱动算法 预测方法 

分 类 号：TH133.33[机械工程—机械制造及自动化]