摘要
针对转子碰摩故障信号的非平稳性和信噪比低的特点,提出采用变分模态分解和支持向量机相结合的转子碰摩的故障诊断方法。通过变分模态分解对原信号做预处理,分解得到若干本征模函数,采用相关系数法选取有效本征模函数进行重构,提高其信噪比,并构造特征矩阵。采用粒子群优化算法优化支持向量机参数,提高支持向量机诊断模型的识别率。通过实验验证,该方法能有效对转子碰磨故障信号进行分解及提取特征,提高了识别率,具有一定的工程实用性。
Aiming at the non-stationary and low signal-to-noise ratio of the rotor rubbing fault signal,a fault diagnosis method based on the combination of variational mode decomposition and support vector machine is proposed.The original signal is preprocessed by variational mode decomposition,and some eigenmode functions are decomposed.The effective eigenmode function is selected by correlation coefficient method to reconstruct,improve the signal-to-noise ratio,and construct the feature matrix.The particle swarm optimization algorithm is used to optimize the parameters of the support vector machine to improve the recognition rate of the support vector machine diagnostic model.The experimental results show that the method can effectively decompose and extract the rotor rubbing fault signal,improve the recognition rate and have certain engineering practicability.
作者
魏永合
曹怀
卢子乾
WEI Yonghe;CAO Huai;LU Ziqian(Shenyang Ligong University,Shenyang 110159,China)
出处
《沈阳理工大学学报》
CAS
2019年第4期45-51,共7页
Journal of Shenyang Ligong University
关键词
转子碰摩
变分模态分解
粒子群优化支持向量机
rotor rubbing
variational mode decomposition
particle swarm optimization support vector machin