A Simple but Effective Way to Handle Rotating Machine Fault Diagnosis With Imbalanced-Class Data: Repetitive Learning Using an Advanced Domain Adaptation Model

被引：0
|
作者：
Yoo, Donghwi [1 ]
Choi, Minseok [1 ]
Oh, Hyunseok [1 ]
Han, Bongtae [2 ]
机构：
[1] Gwangju Institute of Science and Technology, School of Mechanical and Robotics Engineering, Gwangju,61005, Korea, Republic of
[2] University of Maryland, Department of Mechanical Engineering, College Park,MD,20742, United States
来源：
IEEE Access | 2024年 / 12卷
关键词：
Fault data from in-service rotating machines are extremely scarce. This is usually true even when healthy data are abundant; leading to the problem of class imbalance. Numerous solutions have been proposed to cope with the problem of class imbalance; each solution has its own advantages and disadvantages in implementation. This paper proposes a much simpler and efficient method for fault diagnosis of rotating machines. By employing pseudo-labeling; weighted random sampling; and time-shifting; the proposed repetitive learning method generates pseudo-augmented source and target fault data. Deep convolutional domain adaptation networks are followed to extract features by minimizing different losses. The evaluation results demonstrate the effectiveness of the proposed method; achieving accuracy rates of 90.79% (CWRU); 76.26% (XJTU); and 86.45% (GIST) under extreme imbalance conditions (ρ =0.01); outperforming existing methods by 10-30% while maintaining computational efficiency. The evaluation results show that repetitive learning produces accurate prediction performance even in situations with extremely imbalanced data; which corroborates the effectiveness offered by the proposed method; despite its simplicity. © 2013 IEEE;
D O I：
10.1109/ACCESS.2024.3516525
中图分类号：
学科分类号：
摘要：
引用
下载
收藏
页码：189789 / 189803
相关论文
共 10 条
  • [1] A Novel Domain Adaptation-Based Intelligent Fault Diagnosis Model to Handle Sample Class Imbalanced Problem
    Zhang, Zhongwei
    Shao, Mingyu
    Wang, Liping
    Shao, Sujuan
    Ma, Chicheng
    SENSORS, 2021, 21 (10)
  • [2] Imbalanced data fault diagnosis of rotating machinery using synthetic oversampling and feature learning
    Zhang, Yuyan
    Li, Xinyu
    Gao, Liang
    Wang, Lihui
    Wen, Long
    JOURNAL OF MANUFACTURING SYSTEMS, 2018, 48 : 34 - 50
  • [3] Deep Self-Supervised Domain Adaptation Network for Fault Diagnosis of Rotating Machine With Unlabeled Data
    Li, Jipu
    Huang, Ruyi
    Chen, Junbin
    Xia, Jingyan
    Chen, Zhuyun
    Li, Weihua
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2022, 71
  • [4] Class-Imbalance Adversarial Transfer Learning Network for Cross-Domain Fault Diagnosis With Imbalanced Data
    Kuang, Jiachen
    Xu, Guanghua
    Tao, Tangfei
    Wu, Qingqiang
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2022, 71
  • [5] Class-Imbalance Adversarial Transfer Learning Network for Cross-Domain Fault Diagnosis with Imbalanced Data
    Kuang, Jiachen
    Xu, Guanghua
    Tao, Tangfei
    Wu, Qingqiang
    IEEE Transactions on Instrumentation and Measurement, 2022, 71
  • [6] Learning from Class-imbalanced Data with a Model-Agnostic Framework for Machine Intelligent Diagnosis
    Wu, Jingyao
    Zhao, Zhibin
    Sun, Chuang
    Yan, Ruqiang
    Chen, Xuefeng
    RELIABILITY ENGINEERING & SYSTEM SAFETY, 2021, 216
  • [7] A Variational Auto-Encoder-Based Multisource Deep Domain Adaptation Model Using Optimal Transport for Cross-Machine Fault Diagnosis of Rotating Machinery
    Yuan, Shi-Zheng
    Liu, Zhao-Hua
    Wei, Hua-Liang
    Chen, Lei
    Lv, Ming-Yang
    Li, Xiao-Hua
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2024, 73
  • [8] Effective data-balancing methods for class-imbalanced genotoxicity datasets using machine learning algorithms and molecular fingerprints
    Bae, Su-Yong
    Lee, Jonga
    Jeong, Jaeseong
    Lim, Changwon
    Choi, Jinhee
    COMPUTATIONAL TOXICOLOGY, 2021, 20
  • [9] Dual Weighted-Class Adversarial Network for Rotary Machine Fault Diagnosis Using Multisource Domain with Class-Inconsistent Data
    Yang, Shengkang
    Lei, Boyang
    Wang, Qibin
    Chang, Jiantao
    Kong, Xianguang
    Cheng, Han
    IEEE-ASME TRANSACTIONS ON MECHATRONICS, 2024, 29 (05) : 1 - 12
  • [10] Reduced-Kernel Weighted Extreme Learning Machine Using Universum Data in Feature Space (RKWELM-UFS) to Handle Binary Class Imbalanced Dataset Classification
    Choudhary, Roshani
    Shukla, Sanyam
    SYMMETRY-BASEL, 2022, 14 (02):
1