|
| 基于改进PSO-VMD的滚动轴承早期故障诊断 |
| Early Fault Diagnosis of Rolling Bearing Based on Improved PSO-VMD |
| |
| DOI：10.16018/j.cnki.cn32-1650/n.202302011 |
| 中文关键词: 复合多尺度模糊熵 粒子群算法 变分模态分解 快速谱峭度图 |
| 英文关键词: composite multiscale fuzzy entropy particle swarm optimization variational modal decomposition fast spectral kurtosis diagram |
| 基金项目: |
|
| 摘要点击次数: 44 |
| 全文下载次数: 71 |
| 中文摘要: |
| 针对滚动轴承早期故障信号微弱导致分类识别率低的问题，提出利用复合多尺度模糊熵作为适应度函数的粒子群算法优化变分模态分解，得到多个本征模态分量；利用快速谱峭度图选择最优的本征模态分量，并组成特征向量；将特征向量输入SSA-SVM中进行故障分类。实验结果表明基于复合多尺度模糊熵的PSO-VMD和SSA-SVM的滚动轴承故障诊断更能有效地识别出滚动轴承的早期故障。 |
| 英文摘要: |
| In response to the problem of low classification recognition rate caused by weak early fault signals of rolling bearings, a particle swarm optimization algorithm using composite multi-scale fuzzy entropy as a fitness function is proposed to optimize variational modal decomposition and obtain multiple intrinsic modal components. The optimal eigenmode components are selected by using the fast spectral kurtosis diagram, and the eigenvectors are formed. The feature vector is input into SSA-SVM for fault classification. The experimental results show that the fault diagnosis of rolling bearings of PSO-VMD and SSA-SVM based on composite multi-scale fuzzy entropy is more effective in identifying early faults of rolling bearings. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |