Transfer across bearings produces a greater domain shift than transfer across working conditions (WCs). Because different bearings may have differences in structural parameters, measurement environments, and WCs, a direct transfer may significantly lower the diagnostic accuracy of the target bearing. A novel fault diagnosis method based on pseudo-label transitive domain adaptation networks (PLTDANs) is proposed to address this problem. First, empirical selection criteria are offered to ensure that appropriate intermediate domains are selected and can better bridge the source and target domains. The intermediate-domain-added TDAN can split the direct transfer process into source-intermediate and intermediate-target transfer diagnoses. This division allows for the gradual correction of the domain shift. Second, the cross-domain pseudo-label constraint (CDPLC) is proposed to select high-confidence intermediate domain samples and generate corresponding pseudo-labels. Pseudo-labels highlight the health status of intermediate domain samples. The application of CDPLC aims to minimize the cumulative error of the TDAN. A cross-bearing fault diagnosis experiment demonstrated the PLTDAN's effectiveness.
AzamfarMSinghJLiX, et al. (2021) Cross-domain gearbox diagnostics under variable working conditions with deep convolutional transfer learning. Journal of Vibration and Control27(7–8): 854–864. DOI: 10.1177/1077546320933793.
2.
Ben-DavidSBlitzerJCrammerK, et al. (2007) Analysis of representations for domain adaptation. In: Advances in Neural Information Processing Systems 19:Proceedings of the 2006 Conference, Vancouver, British Columbia, Canada, 4–7 December 2006, pp. 137–144.
3.
Ben-DavidSBlitzerJCrammerK, et al. (2010) A theory of learning from different domains. Machine Learning79(1–2): 151–175. DOI: 10.1007/s10994-009-5152-4.
4.
ChenZHeGLiJ, et al. (2020) Domain adversarial transfer network for cross-domain fault diagnosis of rotary machinery. IEEE Transactions on Instrumentation and Measurement69(11): 8702–8712. DOI: 10.1109/TIM.2020.2995441.
5.
ChenMShaoHDouH (2022) Data augmentation and intelligent fault diagnosis of planetary gearbox using ILoFGAN under extremely limited samples. IEEE Transactions on Reliability72: 1029–1037. DOI: 10.1109/TR.2022.3215243.
6.
ChengCZhouBMaG, et al. (2020) Wasserstein distance based deep adversarial transfer learning for intelligent fault diagnosis with unlabeled or insufficient labeled data. Neurocomputing409: 35–45. DOI: 10.1016/j.neucom.2020.05.040.
7.
GrettonABorgwardtKMRaschMJ, et al. (2012a) A Kerneltwo-sample test. Journal of Machine Learning Research13: 723–773.
8.
GuoLLeiYXingS, et al. (2019) Deep convolutional transfer learning network: a new method for intelligent fault diagnosis of machines with unlabeled data. IEEE Transactions on Industrial Electronics66(9): 7316–7325. DOI: 10.1109/TIE.2018.2877090.
9.
HanTLiuCYangW, et al. (2019) A novel adversarial learning framework in deep convolutional neural network for intelligent diagnosis of mechanical faults. Knowledge-Based Systems165: 474–487. DOI: 10.1016/j.knosys.2018.12.019.
10.
LeeD-H (2013) Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In Workshop on challenges in representation learning. ICML3(2): 896.
11.
LeiYYangBJiangX, et al. (2020) Applications of machine learning to machine fault diagnosis: a review and roadmap. Mechanical Systems and Signal Processing138: 106587. DOI: 10.1016/j.ymssp.2019.106587.
12.
LessmeierCKimothoJKZimmerD, et al. (2016) Condition Monitoring of Bearing Damage in Electromechanical Drive Systems by Using Motor Current Signals of Electric Motors: A Benchmark Data Set for Data-Driven Classification. PHM Society European Conference3(1). DOI: 10.36001/phme.2016.v3i1.1577.
13.
LiWHuangRLiJ, et al. (2022) A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios: theories, applications and challenges. Mechanical Systems and Signal Processing167: 108487. DOI: 10.1016/j.ymssp.2021.108487.
14.
LiangMZhouK (2022) A hierarchical deep learning framework for combined rolling bearing fault localization and identification with data fusion. Journal of Vibration and Control29: 3165–3174. DOI: 10.1177/10775463221091601.
15.
LinMChenQYanS (2014). Network in network. arXiv:1312.4400. arXiv. Available at:http://arxiv.org/abs/1312.4400 (accessed 12 July 2022).
16.
LiuDZhongSLinL, et al. (2022) Highly imbalanced fault diagnosis of gas turbines via clustering-based downsampling and deep siamese self-attention network. Advanced Engineering Informatics54: 101725. DOI: 10.1016/j.aei.2022.101725.
17.
SchwendemannSAmjadZSikoraA (2021) Bearing fault diagnosis with intermediate domain based Layered Maximum Mean Discrepancy: a new transfer learning approach. Engineering Applications of Artificial Intelligence105: 104415. DOI: 10.1016/j.engappai.2021.104415.
18.
ShenFYanR (2022) A new intermediate-domain SVM-based transfer model for rolling bearing RUL prediction. IEEE/ASME Transactions on Mechatronics27(3): 1357–1369. DOI: 10.1109/TMECH.2021.3094986.
19.
SongYLiYJiaL, et al. (2020) Retraining strategy-based domain adaption network for intelligent fault diagnosis. IEEE Transactions on Industrial Informatics16(9): 6163–6171. DOI: 10.1109/TII.2019.2950667.
20.
SunBSaenkoK (2016) Deep CORAL: correlation alignment for deep domain adaptation. In: HuaGJégouH (eds), Computer Vision – ECCV 2016 Workshops. Lecture Notes in Computer Science. Cham: Springer International Publishing, pp. 443–450. DOI: 10.1007/978-3-319-49409-8_35.
21.
TanBSongYZhongE, et al. (2015) Transitive transfer learning. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Sydney, NSW, Australia, 10 August 2015, ACM, pp. 1155–1164. DOI: 10.1145/2783258.2783295.
22.
WangKZhaoWXuA, et al. (2020) One-dimensional multi-scale domain adaptive network for bearing-fault diagnosis under varying working conditions. Sensors20(21): 6039. DOI: 10.3390/s20216039.
23.
WangDNingJZhaoF, et al. (2022) A small-amplitude hunting motion recognition method based on transfer learning. Journal of Vibration and Control0(0): 107754632211170. DOI: 10.1177/10775463221117056.
24.
WangCZhuGLiuT, et al. (2023) A sub-domain adaptive transfer learning base on residual network for bearing fault diagnosis. Journal of Vibration and Control29(1–2): 105–117. DOI: 10.1177/10775463211042976.
25.
XiangSQinYLuoJ, et al. (2021) Multicellular LSTM-based deep learning model for aero-engine remaining useful life prediction. Reliability Engineering & System Safety216: 107927. DOI: 10.1016/j.ress.2021.107927.
26.
YuKChuFWangX, et al. (2022) Frequency-domain energy-concentrated synchrosqueezing transform for frequency-varying signal with linear group delay. IEEE Transactions on Instrumentation and Measurement71: 1–15. DOI: 10.1109/TIM.2022.3141157.
27.
ZhangWPengGLiC, et al. (2017) A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals. Sensors17(2): 425. DOI: 10.3390/s17020425.
28.
ZhangKTangBDengL, et al. (2021) A hybrid attention improved ResNet based fault diagnosis method of wind turbines gearbox. Measurement179: 109491. DOI: 10.1016/j.measurement.2021.109491.
29.
ZhangTChenJLiF, et al. (2022) Intelligent fault diagnosis of machines with small & imbalanced data: a state-of-the-art review and possible extensions. ISA Transactions119: 152–171. DOI: 10.1016/j.isatra.2021.02.042.
30.
ZouYLiuYDengJ, et al. (2021) A novel transfer learning method for bearing fault diagnosis under different working conditions. Measurement171: 108767. DOI: 10.1016/j.measurement.2020.108767.
