基于改进胶囊网络的轴承复合故障诊断研究

摘要
图/表
参考文献(27)
相关文章 (15)

全文: PDF (1569 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要滚动轴承的工作环境复杂，各个部位经常同时发生故障并相互影响，产生复合故障。传统的方法往往将复合故障视为单独的一类，难以识别其中包含的具体故障。针对这一问题，提出了一种基于胶囊网络和多标签分类的智能复合故障诊断方法。首先，将原始振动信号作为输入，通过卷积层和挤压激励模块实现特征提取。其次，初级胶囊层将提取的特征转换为向量，通过自注意路由算法传递到高级胶囊层。最后，通过多标签分类器得到诊断结果。经实验室数据验证，该方法在不同转速数据集上的准确率分别达到了98.70%、98.04%和94.72%，有效识别了复合故障。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	袁洪芳1
	张晓宁1
	王华庆2

关键词 ：胶囊网络, 故障诊断, 滚动轴承, 深度学习

Abstract：Due to the working condition of rolling bearings being complex, various parts often break down simultaneously and influence each other, resulting in compound fault. Traditional methods often regard the compound fault as an independent category, which makes it difficult to identify specific faults contained therein. To solve this problem, an intelligent method on the basis of capsule network and multi-label classification is proposed. First, original vibration signals are taken as input, and feature extraction is achieved by convolutional layers and the squeeze-and-excitation block. Second, the extracted features are converted into vectors through the primary capsule layer and then passed to the advanced capsule layer by the self-attention routing. Finally, the diagnosis results are obtained by a multi-label classifier. Validated by laboratory data, the accuracy reached 98.70%, 98.04%, and 94.72% under different speed conditions, effectively identifying the compound fault.

Key words： capsule network fault diagnosis rolling bearings deep learning

收稿日期: 2022-08-07 出版日期: 2023-10-28

引用本文:

袁洪芳1，张晓宁1，王华庆2. 基于改进胶囊网络的轴承复合故障诊断研究[J]. 振动与冲击, 2023, 42(20): 69-76.
YUAN Hongfang1,ZHANG Xiaoning1,WANG Huaqing2. Compound fault diagnosis of bearings based on an improved capsule network. JOURNAL OF VIBRATION AND SHOCK, 2023, 42(20): 69-76.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2023/V42/I20/69

[1] Burriel-Valencia J, Puche-Panadero R, Martinez-Roman J, et al. Short-frequency fourier transform for fault diagnosis of induction machines working in transient regime[J]. IEEE Transactions on Instrumentation and Measurement, 2017, 66(3): 432-440.
[2] 臧怀刚,王石云,李玉奎. EMD和平滑伪Wigner-Ville谱熵的轴承故障诊断[J]. 噪声与振动控制，2014,34(5): 145-149.
ZANG Huaigang, WANG Shiyun, LI Yukui. Bearing fault diagnosis based on EMD and smoothed pseudo Wigner-Ville spectrum entropy[J]． Noise and Vibration Control，2014, 34(5): 145-149．
[3] Han C, Lu W, Wang P, et al. A recursive sparse representation strategy for bearing fault diagnosis[J]. Measurement, 2022, 187: 110360.
[4] Ren L, Lv W, Jiang S W, et al. Fault diagnosis using a joint model based on sparse representation and SVM[J]. IEEE Transactions on Instrumentation & Measurement, 2016, 65(10): 2313-2320.
[5] 钱小毅,张宇献. 基于动态特征矩阵的k近邻风电机组故障检测方法[J]. 仪器仪表学报, 2019, 40(6): 202-212.
QIAN Xiaoyi, ZHANG Yuxian. Fault detection of wind turbines using k-nearest neighbor based on dynamic feature matrix[J]. Chinese Journal of Scientific Instrument,2019, 40(6): 202-212.
[6] Meng Z, Zhan X, Li J, et al. An enhancement denoising autoencoder for rolling bearing fault diagnosis[J]. Measurement, 2018, 130: 448-454.
[7] Jiang G, He H, Yan J, et al. Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox[J]. IEEE Transactions on Industrial Electronics, 2018, 66(4): 3196-3207.
[8] Lin T, Wang H, Guo X, et al. A novel prediction network for remaining useful life of rotating machinery[J]. The International Journal of Advanced Manufacturing Technology, 2022: 1-10.
[9] Krizhevsky A, Sutskever I, Hinton G. ImageNet classification with deep convolutional neural networks[J]. Advances in neural information processing systems, 2012, 25(2): 1097-1105.
[10] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. Las Vegas, NV: IEEE ,2016: 770-778.
[11] Wang H, Xu J, Yan R, et al. A new intelligent bearing fault diagnosis method using SDP representation and SE-CNN[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 69(5): 2377-2389.
[12] 吴晨芳,杨世锡,黄海舟,等. 一种基于改进的LeNet-5模型滚动轴承故障诊断方法研究[J]. 振动与冲击, 2021, 40(12): 55-61.
WU Chenfang, YANG Shixi, HUANG Haizhou, et al. An improved fault diagnosis method of rolling bearings based on LeNet-5[J]. Journal of Vibration and Shock, 2021, 40(12): 55-61.
[13] 牛锐祥,丁华,施瑞,等. 改进密集连接卷积网络的滚动轴承故障诊断方法[J]. 振动与冲击, 2022, 41(11): 252-258.
NIU Ruixiang, DING Hua, SHI Rui, et al. Rolling bearing fault diagnosis method based on improved densely connected convolution network[J]. Journal of Vibration and Shock, 2022, 41(11): 252-258.
[14] Dibaj A, Ettefagh M M, Hassannejad R, et al. A hybrid fine-tuned VMD and CNN scheme for untrained compound fault diagnosis of rotating machinery with unequal-severity faults[J]. Expert Systems with Applications, 2020, 167: 114094.
[15] Li N, Huang W, Guo W, et al. Multiple enhanced sparse decomposition for gearbox compound fault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 69(3): 770-781.
[16] 齐咏生,刘飞,李永亭,等. 基于MK-MOMEDA和Teager能量算子的风电机组滚动轴承复合故障诊断[J].太阳能学报,2021, 42(07): 297-307.
QI Yongsheng, LIU Fei, Li Yongting, et al. Compound fault diagnosis of wind turbine rolling bearing based on MK-MOMEDA and Teager energy operator[J]. Acta Energiae Solaris Sinica, 2021, 42(07): 297-307.
[17] Huang R, Li W, Cui L. An intelligent compound fault diagnosis method using one-dimensional deep convolutional neural network with multi-label classifier[C]//2019 IEEE International Instrumentation and Measurement Technology Conference (I2MTC). IEEE, 2019: 1-6.
[18] Liang P, Deng C, Wu J, et al. Compound fault diagnosis of gearboxes via multi-label convolutional neural network and wavelet transform[J]. Computers in Industry, 2019, 113(2): 103132.
[19] Sabour S, Frosst N, Hinton G E. Dynamic routing between capsules[J]. Advances in neural information processing systems, 2017, 30.
[20] 杨平,苏燕辰,张振. 基于卷积胶囊网络的滚动轴承故障诊断研究[J].振动与冲击,2020, 39(4): 55-62+68.
YANG Ping, SU Yanchen, ZHANG Zhen. A study on rolling bearing fault diagnosis based on convolution capsule network[J]. Journal of Vibration and Shock, 2020, 39(4): 55-62+68.
[21] Li D C, Zhang M, Kang T B, et al. Fault diagnosis of rotating machinery based on dual convolutional-capsule network (DC-CN)[J]. Measurement, 2022, 187: 110258.
[22] Ke L, Liu Y, Yang Y. Compound fault diagnosis method of modular multilevel converter based on improved capsule network[J]. IEEE Access, 2022, 10: 41201-41214.
[23] Mazzia V, Salvetti F, Chiaberge M. Efficient-capsnet: capsule network with self-attention routing[J]. Scientific Reports, 2021, 11(1): 1-13.
[24] Hu J, Li S, Gang S, et al. Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. Salt Lake City, UT : IEEE ,2018: 7132–7141.
[25] Xi E, Bing S, Yang J. Capsule Network Performance on Complex Data[J]. arXiv preprint arXiv: 1712.03480, 2017.
[26] Zhang M L, Zhou Z H. A review on multi-label learning algorithms[J]. IEEE transactions on knowledge and data engineering, 2013, 26(8): 1819-1837.
[27] Lessmeier C, Kimotho J K, Zimmer D, 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[C]//PHM Society European Conference. 2016, 3(1).