To address the limitations of conventional convolutional neural network (CNN) in feature extraction of vibration signals and improve fault discriminative capability in adversarial domain adaptation in cross-domain fault diagnosis of rotating machinery, this study proposes a novel fault diagnosis approach based on a Multi-scale Conditional Domain Adversarial Network with Spectral Penalization (MCDANSP). The model directly uses raw vibration signals as input. Its feature extraction module combines multi-scale convolutions and a channel attention mechanism to enhance shared feature extraction between source and target domains. For knowledge transfer, the method uses a conditional domain adversarial network (CDAN) and adds batch spectral penalization (BSP) to preserve feature discriminability during domain alignment. Evaluation on the PU, PHM2009, and SEU datasets yielded accuracies of 82.96%, 84.63%, and 64.03%, respectively. These results surpassed other methods in this research, confirming the method’s superior performance.
CaiMChenSLiuJ, et al. (2025) Global receptive field graph attention network for unsupervised domain adaptation fault diagnosis in variable operating conditions. Journal of Intelligent Manufacturing36(5): 3285–3312.
2.
ChenXWangSLongM, et al. (2019) Transferability vs. discriminability: Batch spectral penalization for adversarial domain adaptation. In: International Conference on Machine Learning, Long Beach, CA, 9–15 June 2019, pp. 1081–1090. New York: PMLR.
3.
GaninYUstinovaEAjakanH, et al. (2016) Domain-adversarial training of neural networks. Journal of Machine Learning Research17(59): 1–35.
4.
GopalanRLiRChellappaR (2013) Unsupervised adaptation across domain shifts by generating intermediate data representations. IEEE Transactions on Pattern Analysis and Machine Intelligence36(11): 2288–2302.
5.
HanKWangWGuoJ (2024) Research on a bearing fault diagnosis method based on a CNN-LSTM-GRU model. Machines12(12): 927.
6.
HuBLiuJZhaoR, et al. (2024) A new dual-channel convolutional neural network and its application in rolling bearing fault diagnosis. Measurement Science and Technology35(9): 096130.
7.
HuJShenLSunG (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, 18–22 June 2018, pp. 7132–7141. New York: IEEE.
8.
JiangYHeYShiZ, et al. (2024) Cross-conditions fault diagnosis of rolling bearing based on transitional domain adversarial network. IEEE Sensors Journal25(1): 1978–1993.
9.
JinYHaoLHeX, et al. (2024) A multi-scale temporal convolutional capsule network with parameter-free attention module-dynamic routing for intelligent diagnosis of rolling bearing. Measurement Science and Technology36(1): 016151.
10.
KangSTangXWangY, et al. (2024) Cross-domain fault diagnosis method for rolling bearings based on contrastive universal domain adaptation. ISA Transactions146: 195–207.
11.
KhanASohailAZahooraU, et al. (2020) A survey of the recent architectures of deep convolutional neural networks. Artificial Intelligence Review53: 5455–5516.
12.
LeeDChooHJeongJ (2024) GCN-based LSTM autoencoder with self-attention for bearing fault diagnosis. Sensors24(15): 4855.
LiRLiSXuK, et al. (2022) Adversarial domain adaptation of asymmetric mapping with CORAL alignment for intelligent fault diagnosis. Measurement Science and Technology33(5): 055101.
15.
LiTZhaoZSunC, et al. (2021) Domain adversarial graph convolutional network for fault diagnosis under variable working conditions. IEEE Transactions on Instrumentation and Measurement70: 1–10.
16.
LiXXiaoSZhangF, et al. (2024a) A fault diagnosis method with AT-ICNN based on a hybrid attention mechanism and improved convolutional layers. Applied Acoustics225: 110191.
17.
LiXYuanPSuK, et al. (2024b) Innovative integration of multi-scale residual networks and MK-MMD for enhanced feature representation in fault diagnosis. Measurement Science and Technology35(8): 086108.
18.
LiangPYuZWangB, et al. (2023) Fault transfer diagnosis of rolling bearings across multiple working conditions via subdomain adaptation and improved vision transformer network. Advanced Engineering Informatics57: 102075.
19.
LongMCaoYWangJ, et al. (2015) Learning transferable features with deep adaptation networks. In: International Conference on Machine Learning, Lille, 6–11 July 2015, pp. 97–105. New York: PMLR.
20.
LongMCaoZWangJ, et al. (2018) Conditional adversarial domain adaptation. Advances in Neural Information Processing Systems31: 1647–1657.
21.
LongMZhuHWangJ, et al. (2017) Deep transfer learning with joint adaptation networks. In: International Conference on Machine Learning, Sydney, NSW, Australia, 6–11 August 2017, pp. 2208–2217. New York: PMLR.
22.
LuYHuangYZhuD, et al. (2025) Domain adaptive fault diagnosis algorithm based on multi-graph convolution for rotating machinery. ISA Transactions168: 620–629.
23.
MaWZhangYMaL, et al. (2023) An unsupervised domain adaptation approach with enhanced transferability and discriminability for bearing fault diagnosis under few-shot samples. Expert Systems With Applications225: 120084.
24.
PanXChenHWangW, et al. (2025) Adversarial domain adaptation based on contrastive learning for bearings fault diagnosis. Simulation Modelling Practice and Theory139: 103058.
QinGZhangKLaiX, et al. (2024) An adaptive symmetric loss in dynamic wide-kernel ResNet for rotating machinery fault diagnosis under noisy labels. IEEE Transactions on Instrumentation and Measurement73: 3517512.
27.
QueHLiuXJinS, et al. (2024) Partial transfer learning method based on Inter-Class feature transfer for rolling bearing fault diagnosis. Sensors24(16): 5165.
28.
ShaoSMcAleerSYanR, et al. (2018) Highly accurate machine fault diagnosis using deep transfer learning. IEEE Transactions on Industrial Informatics15(4): 2446–2455.
29.
SongXCongYSongY, et al. (2022) A bearing fault diagnosis model based on CNN with wide convolution kernels. Journal of Ambient Intelligence and Humanized Computing13(8): 4041–4056.
30.
SunBSaenkoK (2016) Deep CORAL: Correlation alignment for deep domain adaptation. In: Computer Vision—ECCV 2016 Workshops, Amsterdam, 8–10 and 15–16 October 2016, Proceedings, part III 14 2016, pp. 443–450. Cham: Springer International Publishing.
31.
SunHFanY (2023) Fault diagnosis of rolling bearings based on CNN and LSTM networks under mixed load and noise. Multimedia Tools and Applications82(28): 43543–43567.
32.
SunLZhuXXiaoJ, et al. (2024) A hybrid fault diagnosis method for rolling bearings based on GGRU-1DCNN with AdaBN algorithm under multiple load conditions. Measurement Science and Technology35(7): 076201.
33.
SunSXiaXZhouH (2025) A graph representation learning-based method for fault diagnosis of rotating machinery under time-varying speed conditions. Nonlinear Dynamics11: 1–27.
34.
TangTLiuZQiuC, et al. (2024) Transfer learning for bearing fault diagnosis based on graph neural network with dilated KNN and adversarial discriminative domain adaptation. Measurement Science and Technology35(6): 065106.
35.
WanLLiYChenK, et al. (2022) A novel deep convolution multi-adversarial domain adaptation model for rolling bearing fault diagnosis. Measurement191: 110752.
36.
WangHDaiXShiL, et al. (2024) Data-augmentation based CBAM-ResNet-GCN method for unbalance fault diagnosis of rotating machinery. IEEE Access. Epub ahead of print 8 March. DOI: 10.1109/ACCESS.2024.3368755.
37.
WangHLiuZPengD, et al. (2019) Understanding and learning discriminant features based on multiattention 1DCNN for wheelset bearing fault diagnosis. IEEE Transactions on Industrial Informatics16(9): 5735–5745.
38.
WangZShiDXuY, et al. (2023) Early rolling bearing fault diagnosis in induction motors based on on-rotor sensing vibrations. Measurement222: 113614.
39.
WuCGZhaoDHanT, et al. (2024) Bearing fault diagnosis using gradual conditional domain adversarial network. Applied Soft Computing158: 111580.
40.
XiaoZCaoXHaoH, et al. (2025) A spatio-temporal joint diagnosis framework for bearing faults via graph convolution and attention-enhanced bidirectional gated networks. Sensors25(13): 3908.
41.
XueYYangRChenX, et al. (2023) A novel local binary temporal convolutional neural network for bearing fault diagnosis. IEEE Transactions on Instrumentation and Measurement72: 1–13.
42.
ZhaoZZhangQYuX, et al. (2021) Applications of unsupervised deep transfer learning to intelligent fault diagnosis: A survey and comparative study. IEEE Transactions on Instrumentation and Measurement70: 1–28.
