基于高阶瞬态提取变换的滚动轴承故障诊断  

Fault Diagnosis of Rolling Bearings Based on High-order Transient-extraction Transform

作　　者：韦成龙 周以齐[1] 于刚 刘朋川 WEI Chenglong;ZHOU Yiqi;YU Gang;LIU Pengchuan(School of Mechanical Engineering,Shandong University,Jinan 250061,China;School of Automation and Electrical Engineering,University of Jinan,Jinan 250022,China)

机构地区：[1]山东大学机械工程学院,济南250061 [2]济南大学自动化与电气工程学院,济南250022

出　　处：《噪声与振动控制》2024年第6期116-122,142,共8页Noise and Vibration Control

基　　金：国家自然科学基金资助项目(61901190,62271230)。

摘　　要：传统时频分析方法通过构建信号的时频模型,获得非平稳信号的瞬时频率特征,然而,由于短时瞬态信号在时域上不连续,受限于海森伯格不确定性原理,无法为短时瞬态信号提供精确时间信息。针对旋转机械中瞬态故障信号的提取问题,提出一种高阶瞬态提取变换(High-order Transient-extracting Transform, HTET),该方法利用泰勒展开估计高阶群延迟算子,替换低阶时频方法中的关键参数,通过获得能量更集中的时频表示,对机械故障中形成的冲击特征进行精确定位,并且能够有效提取信号中的冲击成分,去除本底噪声的干扰。仿真分析验证所提出方法在时频特征刻画以及抑噪方面的性能。实验分析对提出方法能够用于人工缺陷与自然演化形成的缺陷轴承故障诊断加以验证,对于信号时频分析理论的拓展与机械故障的诊断均具有实际意义。The traditional time-frequency analysis method obtains the instantaneous frequency characteristics of nonstationary signals by constructing the time-frequency model of signals.However,due to the discontinuity of short-time transient signals in time domain and the limitation of Heisenberg uncertainty principle,it is impossible to provide accurate time information for the short-time transient signals.In this work,aiming at the extraction of transient fault signals in rotating machinery,a high-order transient extracting transform(HTET)was proposed.In this method,Taylor expansion was used to estimate the high-order group delay operator,which was used to replace the key parameters in the low-order time-frequency method.Through obtaining a more concentrated time-frequency representation,the accurate location of the impact characteristics formed in mechanical faults was determined.In addition,the impact component in the signal could be effectively extracted and the interference of background noise was removed.Simulation analysis verified the performance of the proposed method in time-frequency feature characterization and noise suppression.The experimental analysis verified that the proposed method can be used for bearing fault diagnosis of artificial defects and naturally formed defects,which has practical significance for the expansion of signal processing theory and mechanical fault diagnosis.

关 键 词：故障诊断 瞬态提取变换 时频分析 滚动轴承 

分 类 号：TN911.7[电子电信—通信与信息系统]