New transfer learning fault diagnosis method of rolling bearing based on ADC-CNN and LATL under variable conditions

被引:49
作者
Huo, Chunran [1 ]
Jiang, Quansheng [1 ]
Shen, Yehu [1 ]
Qian, Chenhui [1 ]
Zhang, Qingkui [1 ]
机构
[1] Suzhou Univ Sci & Technol, Suzhou 215009, Peoples R China
基金
中国国家自然科学基金;
关键词
Fault diagnosis; Rolling bearing; Convolutional neural network; Transfer learning;
D O I
10.1016/j.measurement.2021.110587
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Convolutional neural network with transfer learning are effective methods for rolling bearing unsupervised learning fault diagnosis. In view of the problem that 1D-CNN cannot give full play to the feature extraction, an improved Adaptive Dimension Convert convolutional neural network (ADC-CNN) is proposed, which can adaptively process one-dimensional vibration signals into two-dimension matrices and input them into 2D-CNN for learning, making full use of the ability of CNN to extract two-dimensional data features. In order to further reduce the data distribution distance between source domain and target domain, the training method of transfer learning is improved by Layered Alternately Transfer Learning (LATL), which layering calculate the CORAL and MK-MMD loss function alternately. To verify the reliability of the proposed method, we carry out experimental verification on the rolling bearing datasets of CWRU and PU. Compared with the traditional 1D-CNN model, the diagnostic classifier accuracy of the proposed ADC-CNN-FLATL is improved by 9% per transfer mission on PU dataset on average, which proves the validity of the proposed method.
引用
收藏
页数:14
相关论文
共 37 条
[1]   Cross-domain gearbox diagnostics under variable working conditions with deep convolutional transfer learning [J].
Azamfar, Moslem ;
Singh, Jaskaran ;
Li, Xiang ;
Lee, Jay .
JOURNAL OF VIBRATION AND CONTROL, 2021, 27 (7-8) :854-864
[2]  
Case Western Reserve University, CAS W RES U CWRU BEA
[3]   A review on data-driven fault severity assessment in rolling bearings [J].
Cerrada, Mariela ;
Sanchez, Rene-Vinicio ;
Li, Chuan ;
Pacheco, Fannia ;
Cabrera, Diego ;
de Oliveira, Jose Valente ;
Vasquez, Rafael E. .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2018, 99 :169-196
[4]   Convolutional neural network based bearing fault diagnosis of rotating machine using thermal images [J].
Choudhary, Anurag ;
Mian, Tauheed ;
Fatima, Shahab .
MEASUREMENT, 2021, 176
[5]   Adaptive iterative generalized demodulation for nonstationary complex signal analysis: Principle and application in rotating machinery fault diagnosis [J].
Feng, Zhipeng ;
Chen, Xiaowang .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2018, 110 :1-27
[6]   A neuro-wavelet based approach for diagnosing bearing defects [J].
Gharesi, Niloofar ;
Arefi, Mohammad Mehdi ;
Razavi-Far, Roozbeh ;
Zarei, Jafar ;
Yin, Shen .
ADVANCED ENGINEERING INFORMATICS, 2020, 46
[7]   Deep Convolutional Transfer Learning Network: A New Method for Intelligent Fault Diagnosis of Machines With Unlabeled Data [J].
Guo, Liang ;
Lei, Yaguo ;
Xing, Saibo ;
Yan, Tao ;
Li, Naipeng .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2019, 66 (09) :7316-7325
[8]   Deep transfer network with joint distribution adaptation: A new intelligent fault diagnosis framework for industry application [J].
Han, Te ;
Liu, Chao ;
Yang, Wenguang ;
Jiang, Dongxiang .
ISA TRANSACTIONS, 2020, 97 :269-281
[9]   Learning transferable features in deep convolutional neural networks for diagnosing unseen machine conditions [J].
Han, Te ;
Liu, Chao ;
Yang, Wenguang ;
Jiang, Dongxiang .
ISA TRANSACTIONS, 2019, 93 :341-353
[10]   Acoustic spectral imaging and transfer learning for reliable bearing fault diagnosis under variable speed conditions [J].
Hasan, Md Junayed ;
Islam, M. M. Manjurul ;
Kim, Jong-Myon .
MEASUREMENT, 2019, 138 :620-631