基于融合特征与数模联动的轴承寿命预测方法  

Research on Remaining Useful Life Prediction of Rolling Bearings Based on Fusion Feature and Model-Data-Fusion

作　　者：王前 黄强 江星星 徐坤 朱忠奎 WANG Qian;HUANG Qiang;JIANG Xingxing;XU Kun;ZHU Zhongkui(School of Optical and Electronic Information,Suzhou City University Suzhou,215104,China;School of Rail Transportation,Soochow University Suzhou,215131,China;College of Energy and Power Engineering,Nanjing University of Aeronautics and Astronautics Nanjing,210016,China)

机构地区：[1]苏州城市学院光学与电子信息学院,苏州215104 [2]苏州大学轨道交通学院,苏州215131 [3]南京航空航天大学能源与动力学院,南京210016

出　　处：《振动．测试与诊断》2023年第4期705-711,828,829,共9页Journal of Vibration,Measurement & Diagnosis

基　　金：国家自然科学基金资助项目(52172406);中国博士后科学基金资助项目(2021M702752);苏州市重点产业技术创新资助项目(SYG202111);江苏省高等学校自然科学研究资助项目(20KJB460006);运输车辆检测、诊断与维修技术交通行业重点实验室开放基金项目(JTZL2104)。

摘　　要：针对现有数模联动剩余使用寿命(remaining useful life,简称RUL)预测方法易受随机噪声干扰、没有考虑轴承的退化特性等问题,提出了一种基于融合指标与数模联动的轴承RUL预测方法,以提高原始数模联动RUL预测方法的准确性。首先,利用主成分分析及指数加权移动平均算法融合表征轴承退化状态的多种特征,构建单调趋势良好的性能退化融合指标;其次,基于3σ准则建立一种首次预测时间确定方案,以触发RUL预测模型的启动,避免RUL预测的无效性;最后,考虑轴承的退化特性,嵌入Rauch-Tung-Striebel平滑滤波算法,以减小退化模型的随机波动,实现轴承RUL的可靠预测。仿真数据和试验信号分析结果证明了所提方法的有效性,相较于现有数模联动方法,显著提高了轴承RUL的预测精度。Due to the interference of random noise and the degradation characteristics of rolling bearings,tradi-tional model-data-fusion based remaining useful life(RUL)prediction method of rolling bearings might be af-fected.Thus,a novel RUL prediction method is proposed based on the fusion indictor and model-data-fusion to improve the accuracy of RUL prediction of rolling bearings.First,the principle component analysis and ex-ponentially weighted moving average algorithm are used to fuse the multiple charactering features for construct-ing a monotonous fusion indictor.Then,a determining scheme for the first predicting time is built on 3σcrite-ria to trigger the RUL prediction process,which can avoid the invalidity of the prediction process.Lastly,the Rauch-Tung-Striebel smooth filter algorithm is embedded into the prediction model to reduce the random fluc-tuation and achieve the reliable RUL of rolling bearing.Simulated and experimental cases demonstrate the ef-fectiveness of the proposed method and its superiority over the traditional model-data-fusion RUL prediction method.

关 键 词：剩余寿命预测 数模联动 滚动轴承 融合特征 平滑滤波 

分 类 号：TH133.3[机械工程—机械制造及自动化] TN713[电子电信—电路与系统]