| 引用本文: | 孙岩,彭高亮.改进胶囊网络的滚动轴承故障诊断方法[J].哈尔滨工业大学学报,2021,53(1):23.DOI:10.11918/202004163 |
| SUN Yan,PENG Gaoliang.Improved capsule network method for rolling bearing fault diagnosis[J].Journal of Harbin Institute of Technology,2021,53(1):23.DOI:10.11918/202004163 |
|
| 摘要: |
| 针对滚动轴承工作环境噪声复杂,振动信号信噪比低且呈现非平稳和非线性的特点,以及传统诊断方法在噪声环境下分类诊断准确率低等问题,提出一种基于改进胶囊网络特征提取结构和反向传播损失值计算方法的滚动轴承故障诊断模型. 应用多尺度卷积核Inception结构和空间注意力机制,替代传统胶囊网络单一卷积层进行特征提取,得到不同尺度下、重点区域突出的特征数据,利用胶囊结构构建向量神经元,通过动态路由的特征传递方式,得到分类结构数字胶囊,实现故障诊断；训练过程损失计算采用间隔损失和重构损失相结合的方法,通过调节二者比例系数,构建更加合理的反向传播计算过程. 为验证模型的实际诊断效果,利用凯斯西储大学轴承数据集中4种转速及对应4种负载工况下的实验数据,通过添加不同幅值能量的高斯白噪声,以降低信噪比的方式开展实验；与双卷积层胶囊网络和传统卷积神经网络进行对比分析. 结果表明,与其他诊断方法相比,提出的方法在噪声环境下能得到良好的诊断结果,抗噪性方面具有明显优势. |
| 关键词: 滚动轴承 改进胶囊网络 特征提取结构 损失值计算 故障诊断 抗噪性 |
| DOI：10.11918/202004163 |
| 分类号:TH133.3 |
| 文献标识码:A |
| 基金项目:国家自然科学基金(51875138) |
|
| Improved capsule network method for rolling bearing fault diagnosis |
|
SUN Yan,PENG Gaoliang
|
|
(School of Mechanical and Electrical Engineering, Harbin Institute of Technology, Harbin 150001, China)
|
| Abstract: |
| Rolling bearing noise environment is complex, low signal-to-noise ratio and the vibration signal is nonstationary and nonlinear, the accuracy of traditional diagnostic methods is low in noisy environment, thus an improved capsule network feature extraction structure and the calculation method of back propagation loss value is proposed. The Inception structure of multi-scale convolutional kernel and spatial attention mechanism are applied to extract features instead of the single convolutional layer of capsule network, so as to obtain prominent feature data in key areas under different scales. Vector neurons are constructed with capsule structure, and digital capsules of classification structure are obtained through dynamic routing, so as to realize fault diagnosis. The loss calculation of training process adopts the method of combining interval loss and reconstruction loss, and a more reasonable calculation process of back propagation is constructed by adjusting the proportional coefficient of the two. To verify the actual diagnostic effect of the model, the experiment was carried out by adding gaussian white noise of different amplitude energy and adjusting the signal-to-noise ratio by using the experimental data of four rotating speeds and corresponding four load conditions in the bearing data set of Caesar western reserve university. The double convolutional layer capsule network was compared with the traditional convolutional neural network. The results show that the method can get good diagnostic results in noisy environment and has obvious advantages over other diagnostic methods in noise resistance. |
| Key words: Rolling bearing improved capsule network feature extraction structure loss calculation fault diagnosis noise resistance |
