本文基于XJTU-SY全寿命周期轴承振动数据设计了信号切割与采样方法，构建了包含保持架损坏、内圈损坏和外圈损坏的数据集3类故障状态。并使用变分模态分解（VMD）方法作为信号处理模块，构建了输入序列。最后将序列输入到Transformer模型进行特征提取，再使用MLP分类器对3类故障进行诊断分析，对比了不同模态提取数下模型性能与分类效果。研究结果表明，使用VMD+Transformer的故障诊断模型在识别滚动轴承故障任务方面的准确率最高可达到90.7％。研究验证了Transformer模型在轴承故障信号处理与特征提取应用方面的可能性，可为船舶机械轴承健康管理提供技术支持。
The article designed a signal cutting and sampling method based on XJTU-SY full life cycle bearing vibration data and constructed a dataset containing three types of fault states, i.e. cage damage, inner ring damage, and outer ring damage. The Variable Modal Decomposition (Variational Mode Decomposition, VMD) method was used as the signal processing module to construct the input sequence. Finally, the sequences were input to the Transformer model for feature extraction, and then the three types of faults were diagnosed and analyzed using the MLP classifier. The experiments compare the model performance and classification effect under different modal extraction numbers. The results show that the fault diagnosis model using VMD+Transformer can reach up to 90.7% accuracy in the task of recognizing rolling bearing faults. The possibility of application of Transformer model in bearing faule signal processing and feature extraction is verified,which can provide technical support for the health management of Maring machinery bearings.
2026,48(2): 179-185 收稿日期：2025-3-12
DOI：10.3404/j.issn.1672-7649.2026.02.028
分类号：U644.21
作者简介：周博(1999-),男,硕士,助理工程师,研究方向为振动分析、旋转机械故障诊断
参考文献：
[1] 朱拥勇, 李宗吉, 王世哲. 基于HHT时频分析的水声信号特性提取与建模[J]. 舰船科学技术, 2023, 45(23): 122-126
ZHU Y , LI Z , WANG S. Underwater acoustic signal characteristic extraction and modeling based on HHT time-frequency analysis[J]. Ship Science and Technology, 2023, 45(23): 122-126
[2] 胡以怀, 蒋佳炜, 方云虎, 等. 船舶机舱旋转机械的振动测试与分析[J]. 船舶与海洋工程, 2020, 36(2): 36-40.
HU Y H, JANG J W, FANG Y H, et al. Vibration test and analysis of rotating machinery in Marine engine room[J]. Naval Architecture and Ocean Engineering, 2020, 36(2): 36-40.
[3] 李恒, 张氢, 秦仙蓉, 等. 基于短时傅里叶变换和卷积神经网络的轴承故障诊断方法[J]. 振动与冲击, 2018, 37(19): 124-131.
LI H, ZHANG Q, QIN X R, et al. Research about fault diagnosis of bearing based on FFT and convolutional neural network[J]. Journal of Vibration and Shock, 2018, 37(19): 124-131.
[4] 刘俊锋, 董宝营, 俞翔, 等. 基于FSC-MPE与BP神经网络的滚动轴承故障诊断方法[J]. 中国舰船研究, 2021, 16(6): 183-190.
LIU J F, DONG B Y, YU X, et al. Rolling bearing fault diagnosis method based on FSC-MPE and BP neural network[J]. Chinese Journal of Ship Research, 2021, 16(6): 183-190.
[5] 闫文源. 基于变分模态分解和SVM的滚动轴承故障诊断[D]. 焦作: 河南理工大学, 2018.
[6] 崔桂艳, 钟倩文, 郑树彬, 等. 基于VMD灰度图像编码和CNN的多传感融合轴承故障诊断[J]. 振动与冲击, 2023, 42(21): 316-326
CUI G Y, ZHONG Q Y, ZHENG S B, et al. Multi sensor fusion bearing fault diagnosis based on VMD gray image coding and CNN[J]. Journal of Vibration and Shock, 2023, 42(21): 316-326
[7] 程明. 基于声振信号滚动轴承故障诊断方法研究[D]. 合肥: 合肥工业大学, 2023.
[8] 向玲, 唐贵基, 胡爱军. 旋转机械非平稳振动信号的时频分析比较[J]. 振动与冲击, 2010(2): 4.
XIANG L, TANG G J, HU A J. Vibration signal's time-frequency analysis and comparison for a rotating machinery[J]. Journal of Vibration and Shock, 2010(2): 4.
[9] DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544
[10] 杨大春. 基于集合经验模态分解的滚动轴承振动信号希尔伯特谱分析方法[J]. 机械制造, 2019, 57(8): 29-32+79.
YANG D C. Hilbert spectrum analysis method of rolling bearing vibration signal based on set empirical mode decomposition[J]. Machinery, 2019, 57(8): 29-32+79.
[11] 何洋洋, 王馨怡, 董晶. 基于经验小波变换与谱峭度的船舶轴系故障特征提取方法[J]. 中国舰船研究, 2020, 15(S1): 98-106.
HE Y Y, WANG X Y, DONG J. Fault feature extraction method for marine shafting based on empirical wavelet transform-spectral kurtosis[J]. Chinese Journal of Ship Research, 2020, 15(S1): 98-106.
[12] 唐贵基, 王晓龙. 变分模态分解方法及其在滚动轴承早期故障诊断中的应用[J]. 振动工程学报, 2016, 29(4): 638-648.
TANG G J, WANG X L. Variational mode decomposition method and its application on incipient fault diagnosisof rolling bearing[J]. Journal of Vibration Engineering, 2016, 29(4): 638-648.
[13] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems, 2017: 5998-6008.
[14] 雷亚国, 韩天宇, 王彪, 等. XJTU-SY滚动轴承加速寿命试验数据集解读[J]. 机械工程学报, 2019, 55(16): 1-6.
