School of Mechanical Engineering,North University of China,Taiyuan 030051,China
Show less
文章历史+
Received
Published
2025-04-14
2025-10-31
Issue Date
2025-11-27
PDF (2567K)
摘要
针对实际工程中轴承数据包含噪声, 且难以获取标签数据, 导致难以进行故障识别的问题, 提出了一种基于小波包一维卷积神经网络与复合域适应损失函数的迁移学习故障识别方法。所提出的小波包分支注意力卷积神经网络(Wavelet Packet Branch Attention Convolutional Neural Network, WPBA-CNN)综合小波包方法与注意力机制对数据特征进行提取, 并针对多尺度分支结构特点提出了分支最大均值差异(Branch Maximum Mean Discrepancy, BMMD)损失函数, 结合交叉熵损失函数与快速批量核范数最大化(Fast Batch Nuclear-norm Maximization, FBNM)方法, 构建了一种新颖的域适应复合损失函数(Domain Adaptation Compound Loss, DACL)进行迁移学习故障识别。结果表明, 在4 dB噪声数据集实验中, WPBA-CNN-DACL的准确率较具有训练干扰的卷积神经网络(Convolution Neural Networks with Training Interference, TICNN)提升了16百分点, 其BMMD组件的准确率较传统MMD提高了3.3百分点, 20组迁移任务的平均准确率达98.24%。这些实验结果验证了本文方法在噪声抑制与跨域适应中的协同优势, 该方法可以作为无标签轴承故障诊断的有效解决方案。
Abstract
To address challenges in practical engineering where bearing data contains noise and labeled data is scarce, this study proposed a transfer learning method for fault identification using a wavelet packet 1D-CNN and compound domain adaptation loss. The developed wavelet packet branch attention CNN (WPBA-CNN) integrated wavelet packet analysis and attention mechanisms for noise-resistant feature extraction. A branch maximum mean discrepancy (BMMD) loss was designed for multi-scale branches, and combined cross-entropy loss with fast batch nuclear-norm maximization (FBNM) method to form the domain adaptation compound loss (DACL). Experimental results demonstrate that the accuracy of the WPBA-CNN-DACL method increases by 16 percentage points compared to the TICNN method,and the accuracy of the BMMD component increases by 3.3 percentage points compared to the traditional MMD. The average accuracy rate of the 20 migration tasks reaches 98.24%. These experimental results validate the synergistic advantages of our method in noise suppression and cross domain adaptation, and this method can serve as an effective solution for unlabeled bearing fault diagnosis.
LIJ, LUOW, BAIM. Review of research on signal decomposition and fault diagnosis of rolling bearing based on vibration signal[J]. Measurement Science and Technology, 2024, 35 (9): 092001.
[2]
WUG G, YANT Y, YANGG L, et al. A review on rolling bearing fault signal detection methods based on different sensors[J]. Sensors, 2022, 22(21): 8330-8330.
CHENShiqian, PENGZhike, ZHOUPeng. Review of signal decomposition theory and its applications in machine fault diagnosis[J]. Journal of Mechanical Engineering,2020, 56(17): 91-107. (in Chinese)
[5]
HUANGN E, SHENZ, LONGS R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London Series A: Mathematical, Physical and Engineering Sciences, 1998, 454(1971): 903-995.
[6]
ALTHUBAITIA, ELASHAF, TEIXEIRAJ A. Fault diagnosis and health management of bearings in rotating equipment based on vibration analysis-a review[J]. Journal of Vibroengineering, 2022, 24 (1): 46-74.
[7]
LEIY G, JIAF, KONGD T, et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era[J].Journal of Mechanical Engineering,2018, 54(5): 94-104.
SIWeiwei, CENJian, WUYinbo, et al. Review of research on bearing fault diagnosis with small samples[J]. Computer Engineering and Applications, 2023, 59(6): 45-56. (in Chinese)
[10]
LIX, MAZ, YUANZ, et al. A review on convolutional neural network in rolling bearing fault diagnosis [J]. Measurement Science and Technology, 2024, 35 (7): 072002.
[11]
ZHANGW, LIC H, PENGG L, et al. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load[J]. Mechanical Systems and Signal Processing, 2018, 100: 439-453.
[12]
ZHENGB, HUANGJ H, MAX, et al. An unsupervised transfer learning method based on SOCNN and FBNN and its application on bearing fault diagnosis[J]. Mechanical Systems and Signal Processing, 2024, 208: 111047.
MISBAHI, LEEC K M, KEUNGK L. Fault diagnosis in rotating machines based on transfer learning: Literature review[J]. Knowledge-Based Systems, 2024, 283: 111158.
[15]
ZHANGS Y, SUL, GUJ F,et al. Rotating machinery fault detection and diagnosis based on deep domain adaptation: A survey[J]. Chinese Journal of Aeronautics, 2023, 36 (1): 45-74.
[16]
LIX Y, YUANP, SUK Y, et al. Innovative integration of multi-scale residual networks and MK-MMD for enhanced feature representation in fault diagnosis[J]. Measurement Science and Technology, 2024, 35 (8): 086108.
[17]
CUIS H, WANGS H, ZHUOJ B, et al. Towards discriminability and diversity: batch nuclear-norm maximization under label insufficient situations[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020: 3940-3949.
[18]
郑旭 .基于离散小波变换的特征提取和故障分类方法研究[D].北京: 北京化工大学, 2017.
[19]
LIJ M, MAOW L, YANGB X, et al. RUL prediction of rolling bearings across working conditions based on multi-scale convolutional parallel memory domain adaptation network[J]. Reliability Engineering and System Safety, 2024, 243: 109854.
[20]
LESSMEIERC, KIMOTHOJ K, ZIMMERD, et al. 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[J]. PHM Society European Conference, 2016: 3(1): 1577.