故障特征增强的滚动轴承状态评估方法  

Condition Assessment Method for Rolling Bearing with Fault Features Enhancement

作　　者：胡旭辉 杨文安[1,2] HU Xuhui;YANG Wenan(State Key Laboratory of Helicopter Transmission Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China;College of Mechanical and Electrical Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China)

机构地区：[1]南京航空航天大学直升机传动技术国家重点实验室,江苏南京210016 [2]南京航空航天大学机电学院,江苏南京210016

出　　处：《机械制造与自动化》2023年第3期79-82,105,共5页Machine Building & Automation

基　　金：国家自然科学基金面上项目(51707501);江苏省重点研发计划项目(BE2018127)。

摘　　要：针对现有滚动轴承状态评估方法对早期故障不敏感、严重依赖历史全生命周期数据等问题,提出一种增强故障信息的滚动轴承状态评估方法。采用小波包变换提取信号特征,基于隐马尔可夫模型结合指数加权移动平均建立评估指标,以评估轴承健康状况并增强早期故障信息;早期故障发生后,应用改进的增强功率谱对信号的频域特征进行增强并诊断故障类型。实验结果表明:该方法能有效描述滚动轴承的退化趋势,及时发现早期故障并快速诊断故障类型。To improve the insensitiveness to early faults and reduce the heavy dependency on historical full life cycle data by the existing assessment methods for bearing conditions,a rolling bearing condition assessment method with fault features enhancement is proposed.Wavelet packet transform is used to extract the signal features,and based on the hidden Markov model and exponential weighted moving average,the evaluation indicator is established to evaluate bearing health status and enhance early fault information.After initial failure occurs,the enhanced power spectrum is applied to lift the frequency domain features of the signal and identify the fault types.Experiment results indicate that the proposed method can effectively describe the degradation trends of rolling bearings,find early faults in time and identify fault types.

关 键 词：状态评估 滚动轴承 故障特征增强 指数加权移动平均 隐马尔科夫模型 

分 类 号：TH165.3[机械工程—机械制造及自动化] TH133.33