基于双谱能量算子的碰摩转子故障特征提取  

Fault feature extraction of rub rotor based on bispectrum energy operator

作　　者：张超[1] ZHANG Chao(Department of Mechanical Engineering,North China Electricity Power University,Baoding 071003,Hebei,China)

机构地区：[1]华北电力大学机械工程系,河北保定071003

出　　处：《中国工程机械学报》2018年第3期269-273,共5页Chinese Journal of Construction Machinery

基　　金：国家自然科学基金资助项目(51675178);中央高校基本科研业务费专项资金资助项目(2017MS152)

摘　　要：双谱分析能够有效地抑制信号中的高斯噪声,准确地分析信号中存在的二次相位耦合成分.但是,传统的双谱分析方法对于转子全周碰摩故障,尤其是早期碰摩故障,存在丢失信息的问题,无法区分正常转子与碰摩转子,诊断能力较弱.为此,基于双通道矢量谱的概念,提出了双谱能量法,并应用于碰摩转子故障的特征提取.实验结果表明,基于双谱能量的碰摩故障特征提取方法继承了双谱的优良特性,能够更加全面、准确地判别早期碰摩故障,是处理碰摩转子非线性信息的一种有效方法.Bispectrum analysis is able to restrain the Gaussian noise and analyze accurately quadratic phase coupling in the signals.However,traditional bispectrum has the problem of losing fault information of full annular rubbing rotor,which leads to weak diagnostic capacity,especially for early rubbing fault.For this reason,a new feature extraction method called bispectrum energy based on double channel vector-bispectrum is presented,and is used to obtain the feature of full annular rubbing fault.The result shows that the feature extraction method based on bispectrum energy inherits the excellent properties of bispectrum,which can comprehensively and exactly embody non-linear information of full annular rubbing rotor.

关 键 词：碰摩转子 故障特征提取 高阶统计量 双谱能量 

分 类 号：TH133[机械工程—机械制造及自动化]