基于多尺度局部二值模式的滚动轴承故障诊断  

Fault Diagnosis of Rolling Bearing Based on Multi-Scale Local Binary Model

作　　者：王明罡 周坪 蔡志雄 尹旭晔 李颖杰 WANG Ming-gang;ZHOU Ping;CAI Zhi-xiong;YIN Xu-ye;LI Ying-jie(Zhejiang Chitic-Safeway New Energy Technology Co.,Ltd.,Hangzhou 310000,China;School of Mechatronic Engineering,China University of Mining and Technology,Xuzhou 221116,China;不详)

机构地区：[1]浙江中自庆安新能源技术有限公司,杭州310000 [2]中国矿业大学机电工程学院,徐州221116 [3]国家电投集团湖北新能源有限公司,武汉430074

出　　处：《组合机床与自动化加工技术》2022年第12期44-47,共4页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：中央高校基本科研业务费专项资金资助(2021YCPY0203);深部煤矿采动响应与灾害防控国家重点实验室开放基金资助(SKLMRDPC21KF21)。

摘　　要：针对滚动轴承早期故障特征较为微弱,容易被淹没在背景噪声中,仅从振动信号单一尺度提取出的特征很难准确表示轴承状态的问题,提出一种基于多尺度局部二值模式的滚动轴承特征提取方法。首先,通过变分模态分解(variational mode decomposition,VMD),得到振动信号在不同尺度下的本征模态分量(intrinsic mode function,IMF);其次,将每个IMF转换成灰度图像的形式,使用局部二值模式(local binary pattern,LBP)提取振动信号在不同尺度的局部纹理特征;最后,将提取出的特征输入反向传播神经网络(back propagation neural network,BPNN)进行分类。通过实测振动信号进行试验,结果表明提出的方法能够很好地提取不同故障状态的轴承特征,且诊断准确率较高。Aiming at the problem that the early fault features of rolling bearings are relatively weak and are often submerged in background noise.It is difficult to accurately represent the state of the bearing with the features extracted from a single scale of the vibration signal.A feature extraction method for rolling bearings based on multi-scale local binary mode is proposed.Firstly,through variational mode decomposition(VMD),the intrinsic mode component(IMF)of the vibration signal at different scales is obtained,and then each IMF is converted into a gray-scale image.Local binary pattern(LBP)is used to extract local texture features of vibration signals at different scales.Finally,the extracted features are input into back propagation neural network(BPNN)for classification.Experiments with measured vibration signals show that the method proposed in this paper can extract the bearing characteristics of different fault states well,and the diagnosis accuracy rate is high.

关 键 词：故障诊断 滚动轴承 变分模态分解 局部二值模式 特征提取 

分 类 号：TH133.3[机械工程—机械制造及自动化] TG502[金属学及工艺—金属切削加工及机床]