基于LCD互近似熵和相关向量机的轴承故障诊断方法

发布时间：2018-01-13 04:09

本文关键词：基于LCD互近似熵和相关向量机的轴承故障诊断方法　出处：《机械传动》2017年11期 　论文类型：期刊论文

【摘要】：针对滚动轴承的故障诊断问题,提出了基于局部特征尺度分解(Local Characteristic-scale Decomposition,LCD)互近似熵(Cross Approximate Entropy,CAE)和相关向量机(Relevance Vector Machine,RVM)的滚动轴承故障诊断方法。该方法首先利用LCD将轴承振动信号分解成若干个具有不同频率成分的内禀尺度分量(Intrinsic Scale Component,ISC);然后通过能量筛选出包含主要故障信息的ISC分量,计算其CAE并作为故障特征向量以体现不同的运行状态;最后将故障特征输入RVM进行故障识别。滚动轴承不同类别和不同损失程度故障实验验证了该方法的有效性。
[Abstract]:In order to solve the fault diagnosis problem of rolling bearing, a local Characteristic-scale Decomposition based on local characteristic scale decomposition is proposed. Cross Approximate Entropy. Cae) and correlation vector machine (Relevance Vector Machine). In this method, the bearing vibration signal is decomposed into several intrinsic scale components with different frequency components by LCD. Intrinsic Scale Component. ISCN; Then the ISC component which contains the main fault information is filtered by energy, and its CAE is calculated and used as the fault feature vector to reflect the different running state. Finally, the fault features are input into RVM for fault identification. The effectiveness of this method is verified by fault experiments of different types and different loss degrees of rolling bearings.
【作者单位】：郑州旅游职业学院信息工程系;郑州旅游职业学院成人教育学院;驻江津地区军代室;
【分类号】：TH133.33
【正文快照】： 0引言在滚动轴承的故障诊断中,故障特征提取和故障识别是两个重要的环节,但如何从具有非线性、非平稳性振动信号中提取有效的故障特征、采用何种有效的故障识别方法,是很多学者一直在研究的问题[1-3]。局部特征尺度分解[4]216-220(LCD)能够将复杂的多分量信号分解成一系列单分

【相似文献】