Unbalanced Data-Based Fault Diagnosis Method of Bearing Utilizing Time-Frequency DCGAN Processing

被引：0
作者：
Fei, Sheng-Wei [1 ]
Liu, Ying-Zhe [1 ]
机构：
[1] Donghua Univ, Coll Mech Engn, Shanghai 201620, Peoples R China
来源：
MECHANIKA | 2024年 / 30卷 / 04期
关键词：
DCGAN; unbalanced data; fault diagnosis; bearing;
D O I：
10.5755/j02.mech.35031
中图分类号：
O3 [力学];
学科分类号：
08 ; 0801 ;
摘要：
Aiming at the unbalanced datasets of fault samples of bearing, a fault diagnosis method of bearing based on time-frequency DCGAN processing is proposed in this paper. Firstly, through STFT, the vibration signals are converted into the time-frequency images, and then the time-frequency images are input into DCGAN to expand the fault samples. Secondly, the expanded fault samples are evaluated for image quality through the comprehensive method of PSNR and SSIM. Thirdly, the Canny edge detection algorithm is used to extract features from the time-frequency image, and the obtained binary image is used as the feature. Finally, k-nearest neighbor algorithm is used for classification to testify the superiority of time-frequency DCGAN processing. The experimental results show that the expanded samples can effectively improve the unbalance of the samples and improve the accuracy of fault diagnosis of bearing.
引用
收藏
页码：371 / 376
页数：6
相关论文
共 50 条
  • [11] Rolling bearing fault diagnosis based on 2D time-frequency images and data augmentation technique
    Fu, Wenlong
    Jiang, Xiaohui
    Li, Bailin
    Tan, Chao
    Chen, Baojia
    Chen, Xiaoyue
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2023, 34 (04)
  • [12] A time-frequency spectral amplitude modulation method and its applications in rolling bearing fault diagnosis
    Jiang, Zuhua
    Zhang, Kun
    Xiang, Ling
    Yu, Gang
    Xu, Yonggang
    MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2023, 185
  • [13] Bearing fault diagnosis method based on the generalized S transform time-frequency spectrum de-noised by singular value decomposition
    Cai, Jianhua
    Xiao, Yongliang
    PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE, 2019, 233 (07) : 2467 - 2477
  • [14] Method for Fault Diagnosis of Track Circuits Based on a Time-Frequency Intelligent Network
    Peng, Feitong
    Liu, Tangzhi
    ELECTRONICS, 2024, 13 (05)
  • [15] Rolling Bearing Fault Diagnosis Based on Time-Frequency Feature Extraction and IBA-SVM
    Zhang, Mei
    Yin, Jun
    Chen, Wanli
    IEEE ACCESS, 2022, 10 : 85641 - 85654
  • [16] Fault diagnosis for analog circuits utilizing time-frequency features and improved VVRKFA
    He, Wei
    He, Yigang
    Luo, Qiwu
    Zhang, Chaolong
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2018, 29 (04)
  • [17] Train Bearing Fault Diagnosis Based on Time-Frequency Signal Contrastive Domain Share CNN
    Zhang, Yupeng
    Hua, Juntao
    Zhang, Dingcheng
    He, Jiayuan
    Fang, Xia
    IEEE SENSORS JOURNAL, 2024, 24 (20) : 33669 - 33681
  • [18] Noise-resistant time-frequency analysis method and its application in fault diagnosis of rolling bearing
    The State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai
    200240, China
    不详
    100161, China
    不详
    200090, China
    不详
    046012, China
    Jixie Gongcheng Xuebao, 1 (90-96): : 90 - 96
  • [19] A Novel Method of Bearing Fault Diagnosis in Time-Frequency Graphs Using InceptionResnet and Deformable Convolution Networks
    Li, Shaobo
    Yang, Wangli
    Zhang, Ansi
    Liu, Huibin
    Huang, Jinyuan
    Li, Chuanjiang
    Hu, Jianjun
    IEEE ACCESS, 2020, 8 : 92743 - 92753
  • [20] The application of time-frequency reconstruction and correlation matching for rolling bearing fault diagnosis
    Xu, Jian
    Tong, Shuiguang
    Cong, Feiyun
    Zhang, Yidong
    PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE, 2015, 229 (17) : 3291 - 3295
12345