2025年04月04日 星期五 首页   |    期刊介绍   |    编 委 会   |    投稿指南   |    期刊订阅   |    统合信息   |    联系我们
计量学报  2023, Vol. 44 Issue (1): 12-20    DOI: 10.3969/j.issn.1000-1158.2023.01.03
  力学计量 本期目录 | 过刊浏览 | 高级检索 |
基于时频增强的滚动轴承少样本故障诊断方法
胡向东,梁川,杨希
重庆邮电大学 自动化学院/工业互联网学院,重庆 400065
A Method of Fault Diagnosis with Few Samples for Rolling Bearing Based on Time-Frequency Enhancement
HU Xiang-dong,LIANG Chuan,YANG Xi
School of Automation/School of Industrial Internet, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
全文: PDF (5641 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 针对滚动轴承故障样本稀缺、振动特征提取困难导致故障诊断准确率低的难题,提出一种基于时频增强的滚动轴承少样本故障诊断方法。首先,对滚动轴承一维振动信号进行重叠采样,利用连续小波变换对采样信号段进行时频域特征映射,构造二维时频矩阵;其次,通过深度卷积生成对抗网络对真实时频样本进行训练后,将生成时频样本加入到训练集中;然后,采用时序卷积网络融合深层次的时频域特征;最后,构建Softmax分类器输出与故障类别对应的状态。仿真实验结果表明,在仅有10个训练样本的条件下,该方法在凯斯西储大学滚动轴承数据集中的诊断准确率均值达91.00%,相较未经时频增强的方法提高了7.56%,并利用实测数据验证了时频增强方法能够显著提升少样本情形下的故障诊断准确率。
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
胡向东
梁川
杨希
关键词 计量学滚动轴承故障诊断时频增强少样本    
Abstract:Aiming at the problem of low fault diagnosis accuracy due to the scarcity of fault samples of rolling bearings and the difficulty in extracting vibration features, a fault diagnosis method of rolling bearings with few samples based on time-frequency enhancement is proposed. Firstly, one-dimensional vibration signals of rolling bearings are overlapped and sampled, and a two-dimensional time-frequency matrix is constructed by using continuous wavelet transform to map the sampled signals in time-frequency domain. Secondly, the real time-frequency samples are trained by deep convolutional generative adversarial network, and the generated time-frequency samples are added to the training set. Then, the time-series convolutional network is used to fuse the deep time-frequency domain features. Finally, Softmax classifier is constructed to output states corresponding to fault categories. Simulation experiment results show that under the condition of only 10 training samples, the method in the diagnosis of rolling bearing at case western reserve university data set average accuracy of 91.00%, compared with an enhanced time-frequency method is increased by 7.56%, and the time-frequency method is validated by the measured data can significantly improve the fault diagnosis accuracy of less sample circumstances.
Key wordsmetrology    rolling bearing    fault diagnosis    time-frequency enhancement    less sample
收稿日期: 2022-03-09      发布日期: 2023-01-13
PACS:  TB936  
基金资助:重庆市自然科学基金(cstc2021jcyj-msxmX0330)
作者简介: 胡向东(1971-),男,四川广安人,重庆邮电大学教授,研究方向为智能感知、网络化测量及工业互联网安全,物联网安全智能理论与技术,复杂系统建模、仿真与优化。Email:huxd@cqupt.edu.cn
引用本文:   
胡向东,梁川,杨希. 基于时频增强的滚动轴承少样本故障诊断方法[J]. 计量学报, 2023, 44(1): 12-20.
HU Xiang-dong,LIANG Chuan,YANG Xi. A Method of Fault Diagnosis with Few Samples for Rolling Bearing Based on Time-Frequency Enhancement. Acta Metrologica Sinica, 2023, 44(1): 12-20.
链接本文:  
http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2023.01.03     或     http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2023/V44/I1/12
京ICP备:14006989号-1
版权所有 © 《计量学报》编辑部
地址:北三环东路18号(北京1413信箱)  邮编:100029 电话:(010)64271480
本系统由北京玛格泰克科技发展有限公司设计开发  技术支持:support@magtech.com.cn