Deep Transfer Learning for Bearing Fault Diagnosis using CWT Time-Frequency Images and Convolutional Neural Networks

被引:9
作者
Djaballah, Said [1 ]
Meftah, Kamel [1 ,2 ]
Khelil, Khaled [3 ]
Sayadi, Mounir [4 ]
机构
[1] Univ Biskra, LGEM Lab, Biskra, Algeria
[2] Univ Batna 2, Fac Technol, Batna, Algeria
[3] Univ Souk Ahras, Fac Sci & Technol, LEER Lab, Souk Ahras, Algeria
[4] Univ Tunis, SIME Lab, ENSIT, Tunis, Tunisia
关键词
Deep learning; Convolution neural network (CNN); Bearing fault diagnosis; Transfer learning; Fine tuning;
D O I
10.1007/s11668-023-01645-4
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Deep transfer learning has evolved into a powerful method for defect identification, particularly in mechanical systems that lack sufficient training data. Nonetheless, domain divergence and absence of overlap between the source and target domains might result in negative transfer. This study examines the partial knowledge transfer, for bearing fault diagnosis, by freezing layers in varying proportions to take advantage of both freezing and fine-tuning strategies. To assess the proposed strategy, three distinct pre-trained models are used, namely ResNet-50, GoogLeNet, and SqueezeNet. Each network is trained using three different optimizers: root mean square propagation, adaptive moment estimation, and stochastic gradient descent with momentum. The suggested technique performance is evaluated in terms of fault classification accuracy, specificity, precision, and training time. The classification results obtained using the CWRU datasets show that the proposed technique reduces training time while enhancing diagnostic accuracy, hence improving bearing defect diagnosis performance.
引用
收藏
页码:1046 / 1058
页数:13
相关论文
共 38 条
[1]   Vibration analysis of rotating machinery using time-frequency analysis and wavelet techniques [J].
Al-Badour, F. ;
Sunar, M. ;
Cheded, L. .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2011, 25 (06) :2083-2101
[2]  
[Anonymous], 2016, Int. J. Appl. Eng. Res
[3]   Rolling Bearing Fault Diagnosis Using Time-Frequency Analysis and Deep Transfer Convolutional Neural Network [J].
Chen, Zhihao ;
Cen, Jian ;
Xiong, Jianbin .
IEEE ACCESS, 2020, 8 :150248-150261
[4]   Intelligent Analysis of Exercise Health Big Data Based on Deep Convolutional Neural Network [J].
Cui, Cui .
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2022, 2022
[5]  
Dauphin YN, 2015, ADV NEUR IN, V28
[6]  
Eren L., 2004, Proceedings of the 21st IEEE Instrumentation and Measurement Technology Conference (IEEE Cat. No.04CH37510), P1657, DOI 10.1109/IMTC.2004.1351399
[7]   Rolling Bearing Diagnosing Method Based on Time Domain Analysis and Adaptive Fuzzy C-Means Clustering [J].
Fu, Sheng ;
Liu, Kun ;
Xu, Yonggang ;
Liu, Yi .
SHOCK AND VIBRATION, 2016, 2016
[8]  
Gehring J, 2013, INT CONF ACOUST SPEE, P3377, DOI 10.1109/ICASSP.2013.6638284
[9]  
Grover C., 2021, ENG SCI TECHNOL INT, V31, P1245
[10]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778