基于FDM的煤矿机械轴承劣化程度辨识  

Deterioration Degree Identification of Bearing for Coal Mine Machinery Based on FDM

作　　者：刘永亮 Liu Yongliang(China Mining Products Safety Approval and Certification Center Co.,Ltd.,Beijing 100013,China)

机构地区：[1]安标国家矿用产品安全标志中心有限公司,北京100013

出　　处：《煤矿机械》2024年第6期221-224,共4页Coal Mine Machinery

基　　金：“十三五”矿用新装备安标追溯管理平台及矿用重点装备联网监管支撑服务平台服务项目(CCTC30211636);安标国家矿用产品安全标志中心有限公司科技创新基金项目(2019ZL004;2019ZL005)。

摘　　要：针对煤矿机械轴承运行过程中劣化程度较难确定致使无法针对性地进行维护更换的问题,提出了基于傅里叶分解方法(FDM)的煤矿机械轴承劣化程度辨识方法。首先对齿轮箱轴承中不同劣化程度的振动信号进行FDM分解,进而得到一系列傅里叶固有频带函数分量;然后通过各分量与原信号的相关度分析,筛选出优选分量,并对其进行奇异值分解得到一系列奇异值特征向量;最后将各劣化程度对应的奇异值特征向量作为极限学习机(ELM)的输入进行轴承劣化程度的辨识。实验结果表明,该方法能较好地应用于轴承的劣化程度辨识,对轴承的预知性维护、更换具有较大的现实意义。Aiming at problem that the degree of bearing operation is difficult to determine,which makes it impossible to carry out targeted maintenance and replacement,a deterioration degree identification of bearing for coal mine machinery based on Fourier decomposition method(FDM)was proposed.Firstly,the vibration signals of different degrees of deteriorationbearings are decomposed by FDM.Then a series of Fourier intrinsic frequency band function components are obtained.Through the correlation analysis of each component and the original signal,the preferred components are selected,and a series of singular value feature vectors are obtained after singular value decomposition.Finally,the singular value feature vector corresponding to each degradation degree is used as the input of extreme learning machine(ELM)to identify the degradation degree of bearing.The results show that this method can be better applied to the identification of bearing for coal mine machinery degradation degree,which has great practical significance for the predictive maintenance and replacement of bearing.

关 键 词：FDM 奇异值分解 ELM 煤矿机械轴承 

分 类 号：TD407[矿业工程—矿山机电]