摘要
针对高速列车滚动轴承振动信号噪声大、信噪比低的问题,提出了一种新型的基于奇异值分解(SVD)与排列熵(PE)的滚动轴承故障诊断方法。首先,运用奇异值分解方法对采集的列车轴承振动信号进行分解,在选取合适的奇异值后对信号进行重组;然后对重组后的信号进行排列熵计算,将计算结果进行标量量化并组成特征向量输入支持向量机进行故障类型判别。试验结果表明,该滚动轴承故障诊断方法对高速列车滚动轴承故障信号具有很好的判别效果。
A new method for fault diagnosis of rolling bearings based on singular value decomposition(SVD)and permutation entropy(PE)is proposed to solve the problem of high speed train bearing vibration signal noise and low signal-to-noise ratio.Firstly,the singular value decomposition method is used to decompose the train bearing vibration signal,and then the signal is reconstructed after the proper singular value is selected,then the permutation entropy of the reconstructed signal is calculated,the calculation result is quantified and the eigenvector is formed to identify the fault type.The test results show that the fault diagnosis method of the rolling bearing has good discriminating effect on the fault signal of the rolling bearing of the high-speed train.
作者
冯波
FENG Bo(Sichuan Vocational and Technical College of Communications,Chengdu 611130,China)
出处
《组合机床与自动化加工技术》
北大核心
2018年第7期108-110,114,共4页
Modular Machine Tool & Automatic Manufacturing Technique
基金
国家科技重大专项资助项目(2015ZX04011-012)
四川交通职业技术学院教学专项基金(2018-XM-09)
关键词
高速列车
滚动轴承
奇异值分解
排列熵
high speed train
rolling bearing
singular value decomposition
permutation entropy
