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。
The incipient fault characteristic of rolling bearing vibration signals is weak and difficult to extract. In order to extract the characteristic parameters from a bearing vibration signal for bearing fault diagnosis, a signal characteristics extraction method based on the variational mode decomposition and permutation entropy was proposed. The support vector machine was used for fault recognition. Firstly,the bearing vibration signal was decomposed by the variational mode decomposition,and the intrinsic mode functions were obtained in different scales. Secondly,the permutation entropy of each intrinsic mode function was calculated and used to compose the multiscale feature vector.Finally,the high-dimensional feature vector was input to the support vector machine for bearing fault diagnosis. The comparison is made with EEMD and WPD（ wavelet packet decomposition）. The experimental results show that the proposed method can be used to diagnose bearing faults effectively.
出处
《振动与冲击》
EI
CSCD
北大核心
2017年第22期22-28,共7页
Journal of Vibration and Shock
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)
关键词
变分模态分解
排列熵
支持向量机
滚动轴承
故障诊断
variational mode decomposition
permutation entropy
support vector machine
rolling bearing
fault diagnosis
