改进MCKD方法及轴承早期故障诊断研究  

Research on Improved MCKD Method and Bearing Incipient Fault Diagnosis

作　　者：刘尚坤 王家忠[1] 王泽河[1] 弋景刚[1] LIU Shang-kun;WANG Jia-zhong;WANG Ze-he;YI Jing-gang(College of Mechanical and Electrical Engineering,Hebei Agricultural University,Hebei Baoding 071001,China)

机构地区：[1]河北农业大学机电工程学院,河北保定071001

出　　处：《机械设计与制造》2021年第5期56-58,共3页Machinery Design & Manufacture

基　　金：国家重点研发计划(2018YFD0700901);河北农业大学引进人才科研专项(YJ201814);河北农业大学理工基金项目(LG201809);河北省省属高校基本科研业务费项目(KY202014)。

摘　　要：针对最大相关峭度解卷积(MCKD)算法滤波器阶数需要人工选择的问题,提出了一种采用变步长搜索方式的改进MCKD故障诊断方法。该方法以故障特征能量比最大化为目标,首先在全部搜索范围内用大步长计算特征能量比,确定最优目标所在的峰值位置,再用小步长进一步在峰值位置附近精确搜索最优滤波器阶数的具体数值,然后对原信号进行滤波并进行包络解调分析,最后由解调出的故障特征频率确诊故障。实测滚动轴承全寿命数据分析验证了该方法的有效性,为滚动轴承早期故障的自适应诊断提供了一条思路。Aiming at the problem that the filter order of maximum correlation kurtosis deconvolution(MCKD)algorithm needs manual selection,an improved MCKD fault feature detection method based on variable step search is proposed.This method aims at maximizing the fault characteristic energy ratio.Firstly,the characteristic energy ratio of each filter order is calculated with a large step in the whole search range to determine the peak position of the optimal target.Then,the specific value of the optimal filter order is further accurately searched with a small step nearby the peak position.Finally,the envelope demodulation is carried out,and the fault is diagnosed by the demodulated fault characteristic frequency.The validity of this method is verified by the analysis results of rolling bearings full life data.It provides a thought for the adaptive diagnosis of rolling bearing faults.

关 键 词：MCKD 变步长搜索 包络谱 滚动轴承 故障诊断 

分 类 号：TH16[机械工程—机械制造及自动化] TH133.3