A novel adversarial learning framework in deep convolutional neural network for intelligent diagnosis of mechanical faults

被引:368
作者
Han, Te [1 ,2 ]
Liu, Chao [1 ,3 ]
Yang, Wenguang [1 ,2 ]
Jiang, Dongxiang [1 ,2 ]
机构
[1] Tsinghua Univ, Dept Energy & Power Engn, Beijing 100084, Peoples R China
[2] Tsinghua Univ, State Key Lab Control & Simulat Power Syst & Gene, Beijing 100084, Peoples R China
[3] Tsinghua Univ, Key Lab Thermal Sci & Power Engn, Minist Educ, Beijing 100084, Peoples R China
基金
中国国家自然科学基金;
关键词
Adversarial training; Generative adversarial network; Deep convolutional neural network; Intelligent fault diagnosis; Rotating machinery; LOCALIZATION DIAGNOSIS; ENCODER;
D O I
10.1016/j.knosys.2018.12.019
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In recent years, deep learning has become an emerging research orientation in the field of intelligent monitoring and fault diagnosis for industry equipment. Generally, the success of supervised deep models is largely attributed to a mass of typically labeled data, while it is often limited in real diagnosis tasks. In addition, the diagnostic model trained with data from limited conditions may generalize poorly for conditions not observed during training. To tackle these challenges, adversarial learning is introduced as a regularization into the convolutional neural network (CNN), and a novel deep adversarial convolutional neural network (DACNN) is accordingly proposed in this paper. By adding an additional discriminative classifier, an adversarial learning framework can be developed to train the convolutional blocks with the split data subsets, leading to a minimax two-player game. This process contributes to making the feature representation robust, boosting the generalization ability of the trained model as well as avoiding overfitting with a small size of labeled samples. The comparison studies with respect to conventional deep models on two fault datasets demonstrate the applicability and superiority of proposed method. (C) 2018 Elsevier B.V. All rights reserved.
引用
收藏
页码:474 / 487
页数:14
相关论文
共 42 条
  • [1] [Anonymous], PHM DAT CHALL
  • [2] [Anonymous], 2016, P 30 INT C NEURAL IN
  • [3] [Anonymous], 2018, UNSUPERVISED DOMAIN
  • [4] [Anonymous], 2016, SEMISUPERVISED LEARN
  • [5] [Anonymous], CROSS DOMAIN REGULAR
  • [6] [Anonymous], 2018, J MANUF SYST
  • [7] [Anonymous], J MACHINE LEARNING R
  • [8] [Anonymous], CAS W RES U BEAR DAT
  • [9] Toward Condition Monitoring of Damper Windings in Synchronous Motors via EMD Analysis
    Antonino-Daviu, Jose A.
    Riera-Guasp, Martin
    Pons-Llinares, Joan
    Roger-Folch, Jose
    Perez, Rafael B.
    Charlton-Perez, Cristina
    [J]. IEEE TRANSACTIONS ON ENERGY CONVERSION, 2012, 27 (02) : 432 - 439
  • [10] Data-driven cost estimation for additive manufacturing in cybermanufacturing
    Chan, Siu L.
    Lu, Yanglong
    Wang, Yan
    [J]. JOURNAL OF MANUFACTURING SYSTEMS, 2018, 46 : 115 - 126