基于SPWVD-CNN的滚动轴承故障诊断（英文）
发布时间：2023-05-24 22:32
针对传统的滚动轴承故障诊断方法难以提取轴承振动数据有效特征的缺陷,提出一种基于平滑伪Wigner-Vill分布(smooth and pseudo Wigner-Ville distribution,SPWVD)和卷积神经网络(convolutional neural network,CNN)的网络模型SPWVD-CNN。对振动数据进行平滑伪Wigner-Vill分布变换,将获得的时频图进行压缩,作为CNN的输入,利用迁移学习的思想进行网络训练,使得模型对于不同负载的数据具有良好的诊断性能,提高了网络的泛化能力。实验结果表明:SPWVD-CNN对轴承故障数据的平均分类准确率提升至99. 27%,总体性能优于使用单一的CNN和其他传统的故障诊断方法。
【文章页数】：8 页
【文章目录】：
1 Theoretical basis of the method
1.1 Smooth and pseudo Wigner-Vill distribution
1.2 Convolution neural network
2 Modeling and analysis of fault diagnosis of rolling bearings based on SPWVD-CNN
2.1 Description of the problem
2.2 Fault diagnosis process
2.3 Network training method
3 Case analysis
3.1 Structure data sets
3.2 Analysis of diagnostic performance of SPWVD-CNN under different working conditions
3.3 Analysis of diagnostic performance of SPWVD-CNN and traditional methods
4 Conclusion
本文编号：3822409
【文章页数】：8 页
【文章目录】：
1 Theoretical basis of the method
1.1 Smooth and pseudo Wigner-Vill distribution
1.2 Convolution neural network
2 Modeling and analysis of fault diagnosis of rolling bearings based on SPWVD-CNN
2.1 Description of the problem
2.2 Fault diagnosis process
2.3 Network training method
3 Case analysis
3.1 Structure data sets
3.2 Analysis of diagnostic performance of SPWVD-CNN under different working conditions
3.3 Analysis of diagnostic performance of SPWVD-CNN and traditional methods
4 Conclusion
本文编号：3822409
本文链接：https://www.wllwen.com/jixiegongchenglunwen/3822409.html