基于多标签零样本学习的滚动轴承故障诊断

PDF(3215 KB)

振动与冲击 ›› 2022, Vol. 41 ›› Issue (11) : 55-64.

论文

基于多标签零样本学习的滚动轴承故障诊断

张永宏1，邵凡1，赵晓平2,3，王丽华1，吕凯扬2，张中洋1

作者信息 +

Rolling bearing fault diagnosis based on multi-label zero-shot learning

ZHANG Yonghong1, SHAO Fan1, ZHAO Xiaoping2,3, WANG Lihua1, L Kaiyang2, ZHANG Zhongyang1

Author information +

文章历史 +

摘要

近年来，数据驱动的方法在滚动轴承故障诊断领域发展迅速，但面对工程实际中没有历史记录的故障类型，仍存在故障特征学习不充分、误诊率高等不足。针对上述问题，本文提出了多标签零样本学习（Multi-label Zero-shot learning，MLZSL）故障诊断方法。首先，使用短时傅里叶变换（Short-time fourier transform，STFT）对可见类和未见类样本进行预处理，将得到的时频图像输入残差深度可分离卷积神经网络（Residual depthwise separable convolutional neural network，RDSCNN）进行特征提取，再使用可见类故障特征训练属性学习网络，依靠属性学习网络预测未见类故障样本的属性向量，最终实现对未见类故障的诊断。本文设计了零样本条件下的故障诊断实验，结果表明MLZSL能将可见类故障属性迁移到未见类，并有效诊断未见类故障。

Abstract

Recent years have seen the rapid development of data-driven methods in the field of rolling bearing fault diagnosis. However, there are no target fault samples available for training. This paper proposes the use of multi-label zero-shot learning (MLZSL) fault diagnosis method for solving this problem. MLZSL utilises the short-time Fourier transform (STFT) to pre-process both seen and unseen samples, and inputs the obtained time-frequency images into the residual depthwise separable convolutional neural network (RDSCNN) to perform feature extraction. It then uses the seen fault features for training the attribute learner, and ultimately uses the attribute learner for learning high-dimensional information about unseen faults in order to realise the diagnosis of unseen faults. This paper proposes a fault diagnosis experiment under the conditions of zero samples. The results demonstrate that MLZSL is able to transfer the attributes of seen faults to unseen faults and can then diagnose unseen faults effectively.

导出引用

张永宏1，邵凡1，赵晓平2,3，王丽华1，吕凯扬2，张中洋1. 基于多标签零样本学习的滚动轴承故障诊断[J]. 振动与冲击, 2022, 41(11): 55-64

ZHANG Yonghong1, SHAO Fan1, ZHAO Xiaoping2,3, WANG Lihua1, L Kaiyang2, ZHANG Zhongyang1. Rolling bearing fault diagnosis based on multi-label zero-shot learning[J]. Journal of Vibration and Shock, 2022, 41(11): 55-64

参考文献

[1] ZHANG S, HE Q, OUYANG K, et al. Multi-bearing weak defect detection for wayside acoustic diagnosis based on a time-varying spatial filtering rearrangement[J]. Mechanical Systems and Signal Processing, 2018, 100: 224-241.
[2] Han K, Wang Y, Tian Q, et al. Ghostnet: More features from cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 1580-1589.
[3] Chollet F. Xception: Deep learning with depthwise separable convolutions[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 1251-1258.
[4] Howard A G, Zhu M, Chen B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications[J]. arXiv preprint arXiv:1704.04861, 2017.
[5] 刘恒畅, 姚德臣, 杨建伟, 等. 基于多分支深度可分离卷积神经网络的滚动轴承故障诊断研究[J]. 振动与冲击, 2021, 40(10)：95-102.
LIU H, YAO D,YANG J, et al. Fault diagnosis of rolling bearings based on a multi branch depth separable convolutional neural network[J]. Journal of Vibration and Shock, 2021, 40(10)：95-102.
[6] JING L, ZHAO M, LI P, et al. A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox[J]. Measurement, 2017, 111: 1-10.
[7] SHAO H, JIANG H, ZHAO H, et al. A novel deep autoencoder feature learning method for rotating machinery fault diagnosis[J]. Mechanical Systems and Signal Processing, 2017, 95: 187-204.
[8] 周兴康, 余建波. 基于深度一维残差卷积自编码网络的齿轮箱故障诊断[J]. 机械工程学报, 2020, 56(07)：96-108.
ZHOU X, YU J. Gearbox fault diagnosis based on one-dimension residual convolutional auto-encoder[J]. Journal of Mechanical Engineering, 2020, 56(07): 96-108.
[9] 曹继平, 王赛, 岳小丹, 等. 基于自适应深度卷积神经网络的发射车滚动轴承故障诊断研究[J]. 振动与冲击, 2020, 39(05)：97-104+149.
CHAO Jiping, WANG Sai, YUE Xiaodan, et al. Rolling bearing fault diagnosis of launch vehicle based on adaptive deep CNN[J]. Journal of Vibration and Shock, 2020, 39(05)：97-104+149.
[10] ZHAO X, ZHANG Y, SHAO F. A Multifault Diagnosis Method of Gear Box Running on Edge Equipment[J]. Security and Communication Networks, 2020.
[11] CHEN Z, DENG S, CHEN X, et al. Deep neural networks-based rolling bearing fault diagnosis[J]. Microelectronics Reliability, 2017, 75: 327-333.
[12] WEN L, GAO L, LI X. A new deep transfer learning based on sparse auto-encoder for fault diagnosis[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2017, 49(1): 136-144.
[13] LEI Y, YANG B, JIANG X, et al. Applications of machine learning to machine fault diagnosis: A review and roadmap[J]. Mechanical Systems and Signal Processing, 2020, 138: 106587.
[14] 雷亚国, 杨彬, 杜兆钧, 等. 大数据下机械装备故障的深度迁移诊断方法[J]. 机械工程学报, 2019, 55(07)：1-8.
LEI Y, YANG B, DU Z, et al. Deep Transfer Diagnosis Method for Machinery in Big Data Era[J]. Journal of Mechanical Engineering, 2019, 55(07): 1-8.
[15] LU W, LIANG B, CHEN Y, et al. Deep model based domain adaptation for fault diagnosis[J]. IEEE Transactions on Industrial Electronics, 2017, 64(3): 2296-2305.
[16] LI X, ZHANG W, DING Q. Cross-domain fault diagnosis of rolling element bearings using deep generative neural networks[J]. IEEE Transactions on Industrial Electronics, 2018, 66(7): 5525-5534.
[17] LI X, ZHANG W, MA H, et al. Partial transfer learning in machinery cross-domain fault diagnostics using class-weighted adversarial networks[J]. Neural Networks, 2020, 129: 313-322.
[18] 陈超, 沈飞, 严如强. 改进LSSVM迁移学习方法的轴承故障诊断[J]. 仪器仪表学报, 2017, 38(01)：33-40.
CHEN Chao, SHEN Fei, YAN Ruqiang. Enhanced least squares support vector machine-based transfer learning strategy for bearing fault diagnosis[J]. Chinese Journal of Scientific Instrument, 2017, 38(1): 33-40.
[19] LAMPERT C H, NICKISCH H, HARMELING S. Learning to detect unseen object classes by between-class attribute transfer[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2009: 951-958.
[20] Lampert C H, Nickisch H, Harmeling S. Attribute-based classification for zero-shot visual object categorization[J]. IEEE transactions on pattern analysis and machine intelligence, 2013, 36(3): 453-465.
[21] KODIROV E, Xiang T, Gong S. Semantic autoencoder for zero-shot learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017: 3174-3183.
[22] GAO Y, GAO L, LI X, et al. A zero-shot learning method for fault diagnosis under unknown working loads[J]. Journal of Intelligent Manufacturing, 2020, 31(4): 899-909.
[23] FENG L, ZHAO C. Fault Description Based Attribute Transfer for Zero-Sample Industrial Fault Diagnosis[J]. IEEE Transactions on Industrial Informatics, 2020.
[24] 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. 2016: 770-778.
[25] HE K, ZHANG X, REN S, et al. Identity mappings in deep residual networks[C]//European conference on computer vision. Springer, Cham, 2016: 630-645.
[26] LI X, ZHANG W, DING Q, et al. Multi-layer domain adaptation method for rolling bearing fault diagnosis[J]. Signal Processing, 2019, 157: 180-197.
[27] XU G, LIU M, JIANG Z, et al. Bearing fault diagnosis method based on deep convolutional neural network and random forest ensemble learning[J]. Sensors, 2019, 19(5): 1088.
[28] The Case Western Reserve University Bearing Data Center Website[EB/OL]. Bearing Data Center Seeded Fault Test Data.http://csegroups.case.edu/bearingdatacenter/home.