A lightweight intra-class inter-class domain adaptation network approach for diagnosing bearing faults under different operating conditions

Abstract

In unsupervised domain adaptation (UDA), existing methods primarily focus on reducing the distributional discrepancy between domains, often neglecting domain shifts and intra-domain variances. A lightweight intra-class and inter-class domain adaptive network (LIIDAN) is proposed to overcome these challenges and facilitate fault diagnosis across varying working conditions. The model consists of two main components: the lightweight and optimized DarkNet19 (LODN19) module for fault feature extraction and the intra-class and inter-class domain adaptation module (IIDAM). The DarkNet19 model’s optimization is achieved by using lightweight processing to remove selected convolutional and max-pooling layers, which simplify the network structure. In addition, a gated recurrent unit layer is added to capture time-related features, while a multi-head self-attention mechanism is applied to boost the network’s capability in efficiently capturing global dependencies. Subsequently, the IIDAM incorporates an improved adversarial domain classifier, where the domain loss function is defined using the Jensen–Shannon divergence to differentiate whether the extracted features originate from the source or target domain. Next, intra-class and inter-class loss functions are defined using weighted conditional maximum mean discrepancy to minimize intra-class distances and enhance inter-class separation. To balance the model’s migration and recognition capabilities, an adaptive factor is introduced, which refines the overall loss function. Two bearing datasets have shown the efficiency of the algorithm, with an average recognition rate of 99.4% across 12 transfer tasks in the Case Western Reserve University (CWRU) dataset, and an improvement in execution time of 44.9%. An average recognition rate of 97.8% and a 46.7% improvement in execution time were obtained for a dataset containing composite faults from a self-constructed test bench.

Keywords

Variable working conditions bearing fault diagnosis lightweight intra-class and inter-class domain adaptation

Get full access to this article

View all access options for this article.

References

Sun

Bearing fault diagnosis based on optimal convolution neural network. Measurement 2022; 190: 110702.

Ruan

Wang

Yan

, et al. CNN parameter design based on fault signal analysis and its application in bearing fault diagnosis. Adv Eng Inform 2023; 55: 101877.

Tuerxun

Guo

, et al. Fault diagnosis of wind turbines based on a support vector machine optimized by the sparrow search algorithm. IEEE Access 2021; 9: 69307–69315.

Hosseinpour

Mohammad Omid

, et al. Fault diagnosis of tractor auxiliary gearbox using vibration analysis and random forest classifier. Inform Process Agric 2022; 9: 60–67.

Wang

Wei

, et al. Weighted K-NN classification method of bearings fault diagnosis with multi-dimensional sensitive features. IEEE Access 2021; 9: 45428–45440.

Sun

Bearing fault diagnosis based on optimal convolution neural network. Measurement 2022; 190: 110702.

Tang

Zhang

, et al. Deep learning-based bearing fault diagnosis using a trusted multi-scale quadratic attention-embedded convolutional neural network. IEEE Trans Instrumen Meas 2024; 73: 1–15.

Zhao

Guo

Rolling bearing fault diagnosis model based on DSCB-NFAM. Meas Sci Technol 2023; 35(1): 015029.

Zhao

Wang

Cai

, et al. Multiscale inverted residual convolutional neural network for intelligent diagnosis of bearings under variable load condition. Measurement 2022; 188: 110511.

10.

Zhao

Yang

, et al. A new bearing fault diagnosis method based on signal-to-image mapping and convolutional neural network. Measurement 2021; 176: 109088.

11.

Liu

Yoo

Xing

, et al. Deep unsupervised domain adaptation: a review of recent advances and perspectives. APSIPA Trans Signal Inform Process 2022; 11(1): e25. doi:10.1561/116.00000192.

12.

Chen

Zhao

, et al. Unsupervised domain adaptation of bearing fault diagnosis based on join sliced Wasserstein distance. ISA Trans 2022; 129: 504–519.

13.

Yoo

Lee

Kang

JW.

Transferring structured knowledge in unsupervised domain adaptation of a sleep staging network. IEEE J Biomed Health Inform 2021; 26(3): 1273–1284.

14.

Zhang

, et al. Open-set domain adaptation in machinery fault diagnostics using instance-level weighted adversarial learning. IEEE Trans Ind Inform 2021; 17(11): 7445–7455.

15.

Shao

Xia

Han

, et al. Intelligent fault diagnosis of rotor-bearing system under varying working conditions with modified transfer convolutional neural network and thermal images. IEEE Trans Ind Inform 2021; 17(5): 3488–3496.

16.

Liu

Cui

Wang

, et al. Interpretable domain adaptation transformer: a transfer learning method for fault diagnosis of rotating machinery. Struct Health Monit 2024; 24(2): 1187–1200.

17.

Zhong

Liu

Mao

, et al. Rolling bearing fault diagnosis across operating conditions based on unsupervised domain adaptation. Lubricants 2023; 11(9): 383.

18.

Yan

Cycle-reconstructive subspace learning with class discriminability for unsupervised domain adaptation. Pattern Recognit 2022; 129: 108700.

19.

Zhao

Wang

Zhang

, et al. Diffusion-UDA: diffusion-based unsupervised domain adaptation for submersible fault diagnosis. Electron Lett 2024; 60(3): e13122.

20.

Wang

, et al. Fusing feature and output space for unsupervised domain adaptation on medical image segmentation. Int J Imag Syst Technol 2023; 33(5): 1672–1681.

21.

Chang

Fang

Fan

, et al. A dynamic weighted joint distribution domain adaptation network for cross-machine fault diagnosis of rolling bearings. Struct Health Monit 2025; 0(0). doi:10.1177/14759217241312080

22.

Wang

Jiang

, et al. Adaptive variational autoencoding generative adversarial networks for rolling bearing fault diagnosis. Adv Eng Inform 2023; 56: 102027.

23.

Park

Jang

, et al. Adaptive bearing fault diagnosis using reference frequency and modified scalogram. Struct Health Monit 2024; 23(5): 2781–2794.

24.

Diao

Yin

Chen

, et al. Two-stage adversarial learning based unsupervised domain adaptation for retinal OCT segmentation. Med Phys 2024; 51: 5374–5385.

25.

Zhang

Chai

, et al. Domain adaptation network base on contrastive learning for bearings fault diagnosis under variable working conditions. Expert Syst Appl 2023; 212: 118802.

26.

Baygin

Yaman

Barua

, et al. Exemplar Darknet19 feature generation technique for automated kidney stone detection with coronal CT images. Artif Intell Med 2022; 127: 102274.

27.

Choudhry

Shahid

Aziz

, et al. DarkNet-19 based intelligent diagnostic system for ocular diseases. Iran J Sci Technol Trans Elect Eng 2022; 46(4): 959–970.

28.

Agarwal

Bhargava

On-tree fruit detection system using Darknet-19 based SSD network. J Food Meas Charact 2024; 18(8): 7067–7076.

29.

Wang

Guo

Shi

Fault distance measurement in distribution networks based on markov transition field and darknet-19. Mathematics 2024; 12(11): 1665.

30.

Fatima

Khan

Sharif

, et al. Two-stage intelligent DarkNet-SqueezeNet architecture-based framework for multiclass rice grain variety identification. Comput Intelligence Neurosci 2022; 1: 1339469.

31.

Zhang

Wang

, et al. Transfer fault diagnosis based on local maximum mean difference and K-means. Comput Ind Eng 2022; 172: 108568.

32.

Mahjoub

Chrifi-Alaoui

Marhic

, et al. Predicting energy consumption using LSTM, multi-layer GRU and drop-GRU neural networks. Sensors 2022; 22(11): 4062.

33.

Wang

Yang

, et al. Arrhythmia classification algorithm based on multi-head self-attention mechanism. Biomed Signal Process Control 2023; 79: 104206.

34.

Pan

Gao

Deng

, et al. Enhanced mass Jensen–Shannon divergence for information fusion. Exp Syst Appl 2022; 209: 118065.

35.

Zang

, et al. Extreme learning machine based on maximum weighted mean discrepancy for unsupervised domain adaptation. IEEE Access 2020; 9: 2283–2293.

36.

Zhao

Jiang

, et al. A novel transfer learning fault diagnosis method based on manifold embedded distribution alignment with a little labeled data. J Intell Manufact 2022; 33: 151–165.

37.

Zhao

Wang

, et al. Fault diagnosis of rolling bearing based on cross-domain divergence alignment and intra-domain distribution alienation. J Vibroeng 2023; 25(6): 1124–1140.

38.

Zhang

Wavelet transform. Fund Image Data Mining Anal Feat Classification Retrieval 2019; 35–44. doi:10.1007/978-3-030-17989-2_3

39.

Wang

Shen

Xia

, et al. Multi-scale deep intra-class transfer learning for bearing fault diagnosis. Reliab Eng Syst Saf 2020; 202: 107050.

40.

Sicilia

Zhao

Hwang

SJ.

Domain adversarial neural networks for domain generalization: when it works and how to improve. Mach Learn 2023; 112(7): 2685–2721.

41.

Heydarian

Doyle

Samavi

MLCM: multi-label confusion matrix. IEEE Access 2022; 10: 19083–19095.

42.

Cai

Theoretical foundations of T-SNE for visualizing high-dimensional clustered data. J Mach Learn Res 2022; 23(301): 1–54.