To overcome information loss and difficulty in fusion of heterogeneous signals due to forced temporal transimaging in existing convolutional neural network CNN bearing fault diagnosis methods, this paper proposes a multi-scale one-dimensional attention convolutional network (1D-AM-CNN) based on Bayesian optimization. The method synchronously extracts fault cross-frequency band features through a multi-scale parallel architecture, uses Bayesian optimization to achieve adaptive optimal weighted fusion of current and vibration signals, and employs a stylized recalibration module with a coordinate attention mechanism to perform channel-space bi-dimensional feature recalibration. Experiments on the PU 6203 bearing dataset show that the proposed method achieves an accuracy of 99.09% for six types of fault identification with an AUC of 0.991 and an F1 score of over 99.11%, and a recall rate of 98.85% for early weak faults (damage area ≤ 2%), which demonstrates the effectiveness and practical applicability of the proposed framework for intelligent fault diagnosis.
AzamfarMSinghJBravo-ImazI, et al. (2020) Multisensor data fusion for gearbox fault diagnosis using 2-D convolutional neural network and motor current signature analysis. Mechanical Systems and Signal Processing144: 106861. https://doi.org/10.1016/j.ymssp.2020.106861
2.
BasirOYuanX (2007) Engine fault diagnosis based on multi-sensor information fusion using dempster–shafer evidence theory. Information Fusion8(4): 379–386. https://doi.org/10.1016/j.inffus.2005.07.003
3.
ChenQZhangFWangY, et al. (2025) Bearing fault diagnosis based on efficient cross space multiscale CNN transformer parallelism. Scientific Reports15(1): 12344. https://doi.org/10.1038/s41598-025-95895-x
4.
GuemmourMNegadiKArariaR, et al. (2025) Analysis and fault diagnosis in point absorber wave energy conversion systems using fault tree and Bayesian networks. Diagnostyka26: 1–16.
5.
HajnayebAGhasemlooniaAKhademSE, et al. (2011) Application and comparison of an ANN-based feature selection method and the genetic algorithm in gearbox fault diagnosis. Expert Systems with Applications38(8): 10205–10209. https://doi.org/10.1016/j.eswa.2011.02.065
6.
HaoSGeFXLiY, et al. (2020) Multisensor bearing fault diagnosis based on one-dimensional convolutional long short-term memory networks. Measurement159: 107802. https://doi.org/10.1016/j.measurement.2020.107802
7.
HeCHeDLaoZ, et al. (2022) A lightweight model for train bearing fault diagnosis based on multiscale attentional feature fusion. Measurement Science and Technology34(2): 025113. https://doi.org/10.1088/1361-6501/aca170
8.
HoangDTKangHJ (2019) A motor current signal-based bearing fault diagnosis using deep learning and information fusion. IEEE Transactions on Instrumentation and Measurement69(6): 3325–3333.
9.
HoangDTTranXTVanM, et al. (2021) A deep neural network-based feature fusion for bearing fault diagnosis. Sensors21(1): 244. https://doi.org/10.3390/s21010244
10.
HouQZhouDFengJ (2021) Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 13713–13722.
11.
JinZHuXWangH, et al. (2025) Rolling bearing fault diagnosis model based on multi-scale depthwise separable convolutional neural network integrated with spatial attention mechanism. Sensors25: 4064. https://doi.org/10.3390/s25134064
12.
LiYWangLJiangL (2020) Rolling bearing fault diagnosis based on DBN algorithm improved with PSO. J. Vib. Shock39: 89–96.
13.
LeCunYBengioYHintonG (2015) Deep learning. nature521(7553): 436–444.
14.
LiGQiYLiYQ, et al. (2021) Research progress on fault diagnosis and state prediction of wind turbine. Automation of Electric Power Systems45(04): 180–191.
15.
LiuYYanXZhangC, et al. (2019) An ensemble convolutional neural networks for bearing fault diagnosis using multi-sensor data. Sensors19(23): 5300. https://doi.org/10.3390/s19235300
MalhotraPRamakrishnanAAnandG, et al. (2016) LSTM-based encoder-decoder for multi-sensor anomaly detection. arXiv preprint arXiv:1607.00148.
18.
OrhanAYordanovNErtarğınM, et al. (2025) A comparative study of time–frequency representations for bearing and rotating fault diagnosis using vision transformer. Machines13(8): 737. https://doi.org/10.3390/machines13080737
19.
PandhareVSinghJLeeJ (2019) Convolutional neural network based rolling-element bearing fault diagnosis for naturally occurring and progressing defects using time-frequency domain features. In: 2019 Prognostics and System Health Management Conference (PHM-Paris). IEEE, 320–326.
20.
Qi-caiZHe-hongSJiongZ (2019) Bearing fault diagnosis based on improved stacked recurrent neural network. Journal of Tongji University (Natural Science)47(10): 1500–1507.
21.
RenHLiuSQiuB, et al. (2024) A novel intelligent fault diagnosis method of bearing based on multi-head self-attention convolutional neural network. Artificial Intelligence for Engineering Design, Analysis and Manufacturing38: e9. https://doi.org/10.1017/s0890060423000197
22.
SnoekJLarochelleHAdamsRP (2012) Practical bayesian optimization of machine learning algorithms. Advances in Neural Information Processing Systems25: 2951–2959.
23.
TongYPangXYWeiZH (2021) Fault diagnosis method of rolling bearing based on GADF-CNN. Journal of Vibration and Shock40(5): 247–253+260.
24.
VanMHoangDTKangHJ (2020) Bearing fault diagnosis using a particle swarm optimization-least squares wavelet support vector machine classifier. Sensors20(12): 3422. https://doi.org/10.3390/s20123422
25.
WangJXieJZhaoR, et al. (2017) Multisensory fusion based virtual tool wear sensing for ubiquitous manufacturing. Robotics and Computer-Integrated Manufacturing45: 47–58. https://doi.org/10.1016/j.rcim.2016.05.010
26.
WangJMaYZhangL, et al. (2018) Deep learning for smart manufacturing: methods and applications. Journal of Manufacturing Systems48: 144–156. https://doi.org/10.1016/j.jmsy.2018.01.003
27.
WangZXuXSongD, et al. (2025) A novel bearing fault diagnosis method based on improved convolutional neural network and multi-sensor fusion. Machines13(3): 216. https://doi.org/10.3390/machines13030216
28.
WenLLiXGaoL, et al. (2017) A new convolutional neural network-based data-driven fault diagnosis method. IEEE Transactions on Industrial Electronics65(7): 5990–5998. https://doi.org/10.1109/tie.2017.2774777
29.
WenJTYanCHSunJD, et al. (2018) Bearing fault diagnosis method based on compressed acquisition and deep learning. Chinese Journal of Scientific Instrument39(1): 171–179.
30.
XiaoF (2020) GIQ: a generalized intelligent quality-based approach for fusing multisource information. IEEE Transactions on Fuzzy Systems29(7): 2018–2031. https://doi.org/10.1109/tfuzz.2020.2991296
31.
XiaoFCaoZJolfaeiA (2020) A novel conflict measurement in decision-making and its application in fault diagnosis. IEEE Transactions on Fuzzy Systems29(1): 186–197. https://doi.org/10.1109/tfuzz.2020.3002431
32.
XuKHuiY (2024) Multi-scale adaptive fusion for rolling bearing fault diagnosis. Journal of Electronics and Information Science9: 54–61.
33.
XuGHouDQiH, et al. (2021) High-speed train wheel set bearing fault diagnosis and prognostics: a new prognostic model based on extendable useful life. Mechanical Systems and Signal Processing146: 107050. https://doi.org/10.1016/j.ymssp.2020.107050
34.
YangWHuMPengX, et al. (2025) Multi-scale feature fusion convolutional neural network fault diagnosis method for rolling bearings. Processes13: 3929. https://doi.org/10.3390/pr13123929
35.
ZhangTGaoFDongJ, et al. (2022) Remote sensing image translation via style-based recalibration module and improved style discriminator. IEEE Geoscience and Remote Sensing Letters19: 1–5. https://doi.org/10.1109/lgrs.2021.3068558
36.
ZhangLHuYLiJ (2023) Fault diagnosis of rolling bearings using recurrence plot coding technique and residual network. Journal of Xi'an Jiaotong University2023: 1–12.
37.
ZhaoHSZhangXKGuoW (2014) Optimized maintenance strategy with imperfect repair for the gearbox of wind turbine. Power System Protection and Control42(10): 15–22.
38.
ZhaoRYanRChenZ, et al. (2019) Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing115: 213–237. https://doi.org/10.1016/j.ymssp.2018.05.050
39.
ZhaoJYangSLiQ, et al. (2021) A new bearing fault diagnosis method based on signal-to-image mapping and convolutional neural network. Measurement176: 109088. https://doi.org/10.1016/j.measurement.2021.109088
40.
Zhang W, Peng G, Li C (2017) Rolling element bearings fault intelligent diagnosis based on convolutional neural networks using raw sensing signal. Advances in Intelligent Information Hiding and Multimedia Signal Processing: Proceeding of the Twelfth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Nov., 21-23, Kaohsiung, Taiwan, Volume 2. Springer International Publishing: 77-84.
41.
Zhao (2025) Multi scale convolutional neural network combining BiLSTM and attention mechanism for bearing fault diagnosis under multiple working conditions. Scientific Reports15: 1-14.
42.
ZhaoSLiuXLiangC, et al. (2024) Rolling bearing fault diagnosis method based on multi-scale convolutional neural network with selective kernel attention mechanism. Research Square.
