基于变分模态分解和排列熵的滚动轴承故障诊断
发布时间：2018-12-12 13:19
【摘要】：滚动轴承早期故障信号特征微弱且难以提取,为了从轴承振动信号中提取特征参数用于轴承故障诊断和识别,提出基于变分模态分解(Variational Mode Decomposition,VMD)和排列熵(Permutation Entropy,PE)的信号特征提取方法,并采用支持向量机(Support Vector Machine,SVM)进行故障识别。对轴承振动信号进行变分模态分解,得到不同尺度的本征模态函数;计算各本征模态函数的排列熵,组成多尺度的复杂性度量特征向量;将高维特征向量输入基于支持向量基建立的分类器进行故障识别分类。通过滚动轴承实验数据分析了算法中参数选取问题,将该方法应用于滚动轴承实验数据,并与集合经验模态分解和小波包分解进行对比,分析结果表明,基于变分模态分解和排列熵的诊断方法有更高的诊断准确率,能够有效实现滚动轴承的故障诊断。
[Abstract]:The early fault signals of rolling bearings are weak and difficult to extract. In order to extract characteristic parameters from bearing vibration signals for bearing fault diagnosis and identification, a new method based on variational mode decomposition (Variational Mode Decomposition,VMD) and permutation entropy (Permutation Entropy,) is proposed. PE) and support vector machine (Support Vector Machine,SVM) for fault identification. Based on the variational mode decomposition of bearing vibration signal, the eigenmode functions of different scales are obtained, the permutation entropy of each intrinsic mode function is calculated, and the complexity metric eigenvector of multiple scales is formed. The high dimensional feature vector is input into the classifier based on support vector basis for fault identification and classification. Based on the experimental data of rolling bearing, the problem of parameter selection in the algorithm is analyzed. The method is applied to the experimental data of rolling bearing, and compared with the empirical mode decomposition and wavelet packet decomposition. The analysis results show that, The diagnosis method based on variational mode decomposition and permutation entropy has higher diagnostic accuracy and can effectively realize the fault diagnosis of rolling bearings.
【作者单位】： 上海电力学院自动化工程学院;上海东海风力发电有限公司;
【基金】：国家自然科学基金(51507098) 上海绿色能源并网工程技术研究中心(13DZ2251900) 上海市科委重点科技攻关项目(14DZ1200905) 上海市电站自动化技术重点实验室项目(13DZ2273800)
【分类号】：TH133.33
本文编号：2374637
[Abstract]:The early fault signals of rolling bearings are weak and difficult to extract. In order to extract characteristic parameters from bearing vibration signals for bearing fault diagnosis and identification, a new method based on variational mode decomposition (Variational Mode Decomposition,VMD) and permutation entropy (Permutation Entropy,) is proposed. PE) and support vector machine (Support Vector Machine,SVM) for fault identification. Based on the variational mode decomposition of bearing vibration signal, the eigenmode functions of different scales are obtained, the permutation entropy of each intrinsic mode function is calculated, and the complexity metric eigenvector of multiple scales is formed. The high dimensional feature vector is input into the classifier based on support vector basis for fault identification and classification. Based on the experimental data of rolling bearing, the problem of parameter selection in the algorithm is analyzed. The method is applied to the experimental data of rolling bearing, and compared with the empirical mode decomposition and wavelet packet decomposition. The analysis results show that, The diagnosis method based on variational mode decomposition and permutation entropy has higher diagnostic accuracy and can effectively realize the fault diagnosis of rolling bearings.
【作者单位】： 上海电力学院自动化工程学院;上海东海风力发电有限公司;
【基金】：国家自然科学基金(51507098) 上海绿色能源并网工程技术研究中心(13DZ2251900) 上海市科委重点科技攻关项目(14DZ1200905) 上海市电站自动化技术重点实验室项目(13DZ2273800)
【分类号】：TH133.33
【相似文献】
相关博士学位论文 前3条
1 吕中亮;基于变分模态分解与优化多核支持向量机的旋转机械早期故障诊断方法研究[D];重庆大学;2016年
2 王晓龙;基于振动信号处理的滚动轴承故障诊断方法研究[D];华北电力大学(北京);2017年
3 李永波;滚动轴承故障特征提取与早期诊断方法研究[D];哈尔滨工业大学;2017年
相关硕士学位论文 前4条
1 王振威;基于变分模态分解的故障诊断方法研究[D];燕山大学;2015年
2 王敬;基于离散模态分解法的表面建模与装配仿真研究[D];浙江大学;2017年
3 马艳丽;基于全矢MEMD的滚动轴承状态退化研究[D];郑州大学;2017年
4 金兵;基于信息融合与VPMCD的滚动轴承智能诊断研究[D];郑州大学;2017年
，本文编号：2374637
本文链接：https://www.wllwen.com/jixiegongchenglunwen/2374637.html
