| 93 | 2 | 85 |
| 下载次数 | 被引频次 | 阅读次数 |
针对深度神经网络故障诊断方法存在参数量大、难以应用在移动设备上的问题，提出一种基于逆残差卷积的轻量级电机轴承故障诊断方法。提出用电机轴承原始振动信号数据的小波包节点系数重构二维小波包图像，具体来说，以轻量级残差网络(ResNet)为基础，将其中卷积改为更轻量级的深度可分离卷积，从而达到了缩短模型训练时间之目标。实验结果验证了所提方法用于轴承故障诊断的有效性。
Abstract：For fault diagnosis method used deep neural network has the problems of large number of parameters and difficulty in use of mobile devices. In this paper, a lightweight motor bearing fault diagnosis method based on inverse residual convolution is proposed. The method reconstructs a two-dimensional wavelet packet image with the wavelet packet node coefficients of the original vibration signal data of the motor bearing. Specifically, the lightweight residual network(ResNet) is used as the basis, in which the convolution is changed to a more lightweight depth-separable convolution, thus the goal of reducing the model training time is achieved. The experimental results verify the effectiveness of the proposed method for bearing fault diagnosis.
[1] DING X X,HE Q B.Energy-fluctuated Multiscale Feature Learning with Deep ConvNet for Intelligent Spindle Bearing Fault Diagnosis[J].IEEE Instrumentation and Measurement,2017,66(8):1926-1935.
[2] NIKOLAOU N G,ANTONIADIS I A.Rolling Element Bearing Fault Diagnosis Using Wavelet Packets[J].NDT & International,2002,35(3):197-205.
[3] SAMANTA B,NATARAJ C.Use of Particle Swarm Optimization for Machinery Fault Detection[J].Engineering Applications of Artificial Intelligence,2008,22(2):308-316.
[4] MALHI A,GAO R X.PCA-based Feature Selection Scheme for Machine Defect Classification[J].IEEE Transactions on Instrumentation and Measurement,2004,53(6):1517-1525.
[5] 邓燕山，赵凯利，吕文超，等.基于深度神经网络的电力变压器故障诊断[J].微型电脑应用，2021,37(6):84-86,94.
[6] BHADNE M,RAMACHANDRAN K I.Bearing Fault Identification and Classification with Convolutional Neural Network[C]//2017 International Conference on Circuit,Power and Computing Technologies (ICCPCT).April 20-21,2017,Kollam,India.IEEE,2017:1-5.
[7] GUGULOTHU N,TV V,MALHOTRA P,et al.Predicting Remaining Useful Life Using Time Series Embeddings Based on Recurrent Neural Networks[EB/OL].2017:arXiv:1709.01073.https://arxiv.org/abs/1709.01073.
[8] EREN L.Bearing Fault Detection by One-Dimensional Convolutional Neural Networks[J].Mathematical Problems in Engineering,2017,2017:1-9.
[9] 郑远攀，李广阳，李晔.深度学习在图像识别中的应用研究综述[J].计算机工程与应用，2019,55(12):20-36.
[10] 唐琳，孙叶，周鹏，等基于卷积神经网络的多媒体视频压缩研究[J].微型电脑应用，2022,28(2):70-72.
[11] Case Western Reserve University.Bearing Data Center [DB/OL].[2021-09-22].https://csegroups.case.edu/bearingdatacenter/home.
基本信息:
中图分类号:TP183;TM307
引用信息:
[1]徐丽红.基于逆残差卷积的轻量级电机轴承故障诊断方法[J].微型电脑应用,2023,39(05):155-158.
2023-05-20
2023-05-20