ZHU R J, SONG E Z, YAO C, et al. Marine motor fault diagnosis based on CEEMDAN and BRECAN under strong noise conditions[J]. Chinese Journal of Ship Research, 2025, 20(2): 20–29 (in both Chinese and English). DOI: 10.19693/j.issn.1673-3185.04059
Citation: ZHU R J, SONG E Z, YAO C, et al. Marine motor fault diagnosis based on CEEMDAN and BRECAN under strong noise conditions[J]. Chinese Journal of Ship Research, 2025, 20(2): 20–29 (in both Chinese and English). DOI: 10.19693/j.issn.1673-3185.04059

Marine motor fault diagnosis based on CEEMDAN and BRECAN under strong noise conditions

More Information
  • Received Date: July 14, 2024
  • Revised Date: August 19, 2024
  • Available Online: August 19, 2024
  • Published Date: October 15, 2024
© 2025 The Authors. Published by Editorial Office of Chinese Journal of Ship Research. Creative Commons License
This is an Open Access article distributed under the terms of the Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • Objective 

    The background noise in the engine room during actual ship navigation leads to the poor accuracy in fault diagnosis methods. To address this issue, this paper proposes a ship motor fault diagnosis method based on complementary ensemble empirical mode decomposition (EEMD) with adaptive noise (CEEMDAN) and a Bayesian residual efficient channel attention network (BRECAN).

    Methods 

    First, the noisy motor fault signal is decomposed into multiple intrinsic mode components (IMFs) through adaptive noise CEEMDAN, the noise dominant signal and information dominant signal in the IMF are divided on the basis of detrended fluctuation analysis, and empirical wavelet transform (EWT) is used to de-noise the noise dominant signal. Next, the BRECAN network is constructed, based on the principle of Variational Bayesian (VI-Bayesian ) using the network parameters instead of the traditional network point estimation training method, the parameters are built to simulate the interference of synthetic noise on the model training, and the network is guided by the Residual Efficient Channel Attention (RECA) module to extract the fault difference features. Finally, the effectiveness of the method is verified via a motor fault simulation experimental platform.

    Results 

    The results show that the proposed method can achieve the accurate diagnosis of ship motor faults under strong noise conditions while still maintaining a diagnostic accuracy of over 90% under signal-to-noise ratio of −12 dB.

    Conclusion 

    The results of this study can provide valuable references for the diagnosis of ship motor faults under strong noise conditions.

  • [1]
    严新平, 王树武, 马枫. 智能货运船舶研究现状与发展思考[J]. 中国舰船研究, 2021, 16(1): 1–6. doi: 10.19693/j.issn.1673-3185.01674

    YAN X P, WANG S W, MA F. Review and prospect for intelligent cargo ships[J]. Chinese Journal of Ship Research, 2021, 16(1): 1–6 (in Chinese). doi: 10.19693/j.issn.1673-3185.01674
    [2]
    郭燚, 王超, 解文祥. 用于船舶永磁推进电机驱动控制的MMC模型预测方法[J]. 中国舰船研究, 2021, 16(4): 179–189,198. doi: 10.19693/j.issn.1673-3185.02001

    GUO Y, WANG C, XIE W X. MMC model predictive control method applied to ship permanent magnet propulsion motor drive[J]. Chinese Journal of Ship Research, 2021, 16(4): 179–189,198 (in Chinese). doi: 10.19693/j.issn.1673-3185.02001
    [3]
    NIU G, DONG X, CHEN Y J. Motor fault diagnostics based on current signatures: a review[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1–19. doi: 10.1109/TIM.2023.3285999
    [4]
    吴勇, 朱建军, 邹奔. EEMD改进算法在异步电机轴承故障诊断中的应用[J]. 中国舰船研究, 2022, 17(6): 111–117. doi: 10.19693/j.issn.1673-3185.02215

    WU Y, ZHU J J, ZOU B. Application of an improved EEMD method in bearing fault diagnosis of induction motors[J]. Chinese Journal of Ship Research, 2022, 17(6): 111–117 (in Chinese). doi: 10.19693/j.issn.1673-3185.02215
    [5]
    陈起磊, 蒋亦悦, 唐瑶, 等. 基于时频图与改进图卷积神经网络的异步电机故障诊断方法[J]. 振动与冲击, 2022, 41(24): 241–248. doi: 10.13465/j.cnki.jvs.2022.24.030

    CHEN Q L, JIANG Y Y, TANG Y, et al. An induction motor fault diagnosis method based on the time-frequency image method and an improved graph convolutional network[J]. Journal of Vibration and Shock, 2022, 41(24): 241–248 (in Chinese). doi: 10.13465/j.cnki.jvs.2022.24.030
    [6]
    TOLIYAT H A, NANDI S, CHOI S, et al. Electric machines: modeling, condition monitoring, and fault diagnosis[M]. Boca Raton: CRC Press, 2017.
    [7]
    KUMAR A, PARKASH C, VASHISHTHA G, et al. State-space modeling and novel entropy-based health indicator for dynamic degradation monitoring of rolling element bearing[J]. Reliability Engineering & System Safety, 2022, 221: 108356. doi: 10.1016/j.ress.2022.108356
    [8]
    RIBEIRO JUNIOR R F, Dos SANTOS AREIAS I A, CAMPOS M M, et al. Fault detection and diagnosis in electric motors using 1d convolutional neural networks with multi-channel vibration signals[J]. Measurement, 2022, 190: 110759. doi: 10.1016/j.measurement.2022.110759
    [9]
    ALSHORMAN O, IRFAN M, ABDELRAHMAN R B, et al. Advancements in condition monitoring and fault diagnosis of rotating machinery: a comprehensive review of image-based intelligent techniques for induction motors[J]. Engineering Applications of Artificial Intelligence, 2024, 130: 107724. doi: 10.1016/j.engappai.2023.107724
    [10]
    MIAN Z B, DENG X F, DONG X H, et al. A literature review of fault diagnosis based on ensemble learning[J]. Engineering Applications of Artificial Intelligence, 2024, 127: 107357. doi: 10.1016/j.engappai.2023.107357
    [11]
    王超, 田波, 李子睿, 等. 基于自注意力子域自适应对抗网络的轴承变工况故障诊断方法[J]. 中国舰船研究, 2023, 18(5): 260–268. doi: 10.19693/j.issn.1673-3185.03092

    WANG C, TIAN B, LI Z R, et al. Self-attention and subdomain adaptive adversarial network for bearing fault diagnosis under varying operation conditions[J]. Chinese Journal of Ship Research, 2023, 18(5): 260–268 (in Chinese). doi: 10.19693/j.issn.1673-3185.03092
    [12]
    廖志强, 宋雪玮, 贾宝柱, 等. 基于加权峭度自适应滤波和对称差分能量谱的船舶推进轴系轴承故障诊断[J]. 广东海洋大学学报, 2022, 42(6): 130–136. doi: 10.3969/j.issn.1673-9159.2022.06.017

    LIAO Z Q, SONG X W, JIA B Z , et al. Fault diagnosis of ship propulsion shafting bearings based on weighted kurtosis adaptive filtering and symmetric differential energy spectrum[J]. Journal of Guangdong Ocean University, 2022, 42(6): 130–136. doi: 10.3969/j.issn.1673-9159.2022.06.017
    [13]
    YAO Y, GUI G, YANG S X, et al. A recursive multi-head self-attention learning for acoustic-based gear fault diagnosis in real-industrial noise condition[J]. Engineering Applications of Artificial Intelligence, 2024, 133: 108240. doi: 10.1016/j.engappai.2024.108240
    [14]
    ZHOU F T, HUANG Z H, ZHANG C H. Carbon price forecasting based on CEEMDAN and LSTM[J]. Applied Energy, 2022, 311: 118601. doi: 10.1016/j.apenergy.2022.118601
    [15]
    HU K, IVANOV P Ch, CHEN Z, et al. Effect of trends on detrended fluctuation analysis[J]. Physical Review E, 2001, 64(1): 011114. doi: 10.1103/PhysRevE.64.011114
    [16]
    SONG Q, ZHAO S F, WANG M S. On the accuracy of fault diagnosis for rolling element bearings using improved DFA and multi-sensor data fusion method[J]. Sensors, 2020, 20(22): 6465. doi: 10.3390/s20226465
    [17]
    GILLES J. Empirical wavelet transform[J]. IEEE Transactions on Signal Processing, 2013, 61(16): 3999–4010. doi: 10.1109/TSP.2013.2265222
    [18]
    CHEGINI S N, BAGHERI A, NAJAFI F. Application of a new EWT-based denoising technique in bearing fault diagnosis[J]. Measurement, 2019, 144: 275–297. doi: 10.1016/j.measurement.2019.05.049
    [19]
    NATRAS R, SOJA B, SCHMIDT M. Uncertainty quantification for machine learning-based ionosphere and space weather forecasting: ensemble, Bayesian neural network, and quantile gradient boosting[J]. Space Weather, 2023, 21(10): e2023SW003483. doi: 10.1029/2023SW003483
    [20]
    GAL Y, GHAHRAMANI Z. Bayesian convolutional neural networks with Bernoulli approximate variational inference [J/OL]. eprint arXiv. (2015-07-06)[2024-7-15]. https://arxiv.org/abs/1506.02158.
    [21]
    ARCO J E, ORTIZ A, RAMÍREZ J, et al. Uncertainty-driven ensembles of multi-scale deep architectures for image classification[J]. Information Fusion, 2023, 89: 53–65. doi: 10.1016/j.inffus.2022.08.010
    [22]
    YANG S M, YUAN A J, YU Z G. A novel model based on CEEMDAN, IWOA, and LSTM for ultra-short-term wind power forecasting[J]. Environmental Science and Pollution Research, 2022, 30(5): 11689–11705. doi: 10.1007/s11356-022-22959-0
    [23]
    王晓琪, 吴轲, 赵观辉, 等. 基于全局注意力残差收缩网络的柱塞泵故障诊断方法[J/OL]. 中国舰船研究. (2024-06-07)[2024-07-19]. https://www.ship-research.com/article/doi/10.19693/j.issn.1673-3185.03739.

    WANG X Q, WU K, ZHAO G H, et al. Fault diagnosis of piston pump based on global attention residual shrinkage network[J/OL]. Chinese Journal of Ship Research. (2024-06-07) [2024-07-19]. https://www.ship-research.com/article/doi/10.19693/j.issn.1673-3185.03739 (in Chinese).
    [24]
    HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2018: 7132−7141.
    [25]
    HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA:IEEE, 2018.
    [26]
    WANG Q L, WU B G, ZHU P F et al. ECA-net: efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, WA, USA: IEEE, 2020: 11531−11539.
    [27]
    ALKEMADE C Th J, SNELLEMAN W, BOUTILIER G D, et al. A review and tutorial discussion of noise and signal-to-noise ratios in analytical spectrometry—I. fundamental principles of signal-to-noise ratios[J]. Spectrochimica Acta Part B: Atomic Spectroscopy, 1978, 33(8): 383–399. doi: 10.1016/0584-8547(78)80049-4

Catalog

    Article views (112) PDF downloads (26) Cited by()
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return