基于中心损失-改进卷积自编码器的滚动轴承半监督故障诊断

摘要
图/表
参考文献(21)
相关文章 (15)

全文: PDF (3723 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要当前基于深度学习的旋转机械故障诊断技术，凭借其强大的逐层加工和内置特征变换功能受到广泛关注，然而传统用于故障诊断的深度网络需要大量标签数据，且诊断结果依赖于标签的数量和准确性。为此，提出一种基于中心损失-改进卷积自编码器（CL-ICAE）的半监督故障诊断方法。该方法首先利用连续小波变换将故障信号转换为时频图，细化故障特征表征；之后构建改进的卷积自编码器网络结构，并引入批量归一化(BN)和Dropout，在特征提取阶段防止过拟合；之后在分类阶段，通过将中心损失(center loss)引入Softmax损失函数，构建联合损失函数，使故障特征实现类内距离更小，特征差异更大，进一步提高分类精度。最后，将所提方法通过凯斯西储大学轴承数据集和轴承故障实验平台进行验证，结果表明在少量标签样本情况下，均可实现有效的故障诊断，提升诊断准确率。

	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
	齐咏生1
	2
	巩育瑞1
	2
	高胜利3
	刘利强1
	2
	李永亭1
	2

关键词 ：滚动轴承, 卷积自编码器, 半监督, 批量归一化, 中心损失

Abstract：At present, the fault diagnosis technology of rotating machinery based on deep learning has attracted wide attention because of its powerful layer-by-layer processing and built-in feature transformation function. However, the traditional depth network for fault diagnosis requires a lot of label data, and the diagnosis results depend on the number and accuracy of labels. For this reason, a semi-supervised fault diagnosis method based on center loss-improved convolutional autoencoder is proposed. Firstly, the fault signal is converted into time-frequency graph by continuous wavelet transform to refine the fault feature representation. Then an improved convolutional autoencoder network structure is constructed, and batch normalization(BN) and Dropout are introduced to prevent over-fitting in the feature extraction stage. Then in the classification stage, the center loss is introduced into the Softmax loss function to build a joint loss function to make the fault features achieve smaller intra-class distance and greater feature differences, and further improve the classification accuracy. Finally, the proposed method is verified by Case Western Reserve University bearing data set and bearing fault experimental platform. The results show that in the case of a small number of label samples, effective fault diagnosis can be achieved and the diagnosis accuracy can be improved.

Key words： rolling bearing convolutional autoencoder semi-supervised batch normalization center loss

收稿日期: 2021-12-14 出版日期: 2023-04-15

引用本文:

齐咏生1,2，巩育瑞1,2，高胜利3，刘利强1,2，李永亭1,2. 基于中心损失-改进卷积自编码器的滚动轴承半监督故障诊断[J]. 振动与冲击, 2023, 42(7): 301-311.
QI Yongsheng1,2, GONG Yurui1,2, GAO Shengli3, LIU Liqiang1,2, LI Yongting1,2. Semi-supervised fault diagnosis of rolling bearing based on CL-ICAE. JOURNAL OF VIBRATION AND SHOCK, 2023, 42(7): 301-311.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2023/V42/I7/301

[1] Hoang D T, Kang H J. Rolling element bearing fault diagnosis using convolutional neural network and vibration image[J].Cognitive Systems Research，2018, 53(3):42-50.
[2] Gong W F, Chen H, Zhang Z H, et al. A Novel Deep Learning Method for Intelligent Fault Diagnosis of Rotating Machinery Based on Improved CNN-SVM and Multichannel Data Fusion[J]. Sensors, 2019, 19(7):1693.
[3] Zou F Q, Zhang H F, Sang S T, et al. An anti-noise one-dimension convolutional neural learning model applying on bearing fault diagnosis[J].Measurement,2021, 186:110236.
[4] Yu J , Zhou X . One-Dimensional Residual Convolutional Autoencoder Based Feature Learning for Gearbox Fault Diagnosis[J]. IEEE Transactions on Industrial Informatics, 2020, 16(10):6347-6358.
[5] Cui M L, Wang Y Q, Lin X S, et al. Fault Diagnosis of Rolling Bearings Based on an Improved Stack Autoencoder and Support Vector Machine[J]. IEEE Sensors Journal, 2020,21(4):4927-4937.
[6] 童靳于，罗金，郑近德. 基于增强深度自编码网络的滚动轴承故障诊断方法[J]. 中国机械工程,2021,32(21):2617-2624.
TONG Jinyu, Luo Jin, Zheng Jinde. Fault diagnosis method for rolling bearing based on enhanced deep auto-encoder network[J]. China Mechanical Engineering, 2021,32(21):2617-2624.
[7] Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on Machine Learning. Lille, France: JMLR.org, 2015:448-456.
[8] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: A simple way to prevent neural networks from overfitting[J]. The Journal of Machine Learning Research, 2014, 15(1): 1929-1958.
[9] Zhu Y X, Yang Z, Li W, et al. Hetero-Center loss for cross-modality person Re-identification[J]. Neurocomputing, 2020, 386:97-109.
[10] Smith W A, Randall R B. Rolling element bearing diagnostics using the Case Western Reserve University data: a benchmark study[J]. Mechanical Systems and Signal Processing, 2015, 64/65: 100-131.
[11] 张西宁，向宙，唐春华. 一种深度卷积自编码网络及其在滚动轴承故障诊断中的应用[J]. 西安交通大学学报,2018, 52(07):60-67.
ZHANG Xining, XIANG Zhou, TANG Chunhua. A deep auto-encoding neural network and its application in bearing fault diagnosis[J]. Journal of Xi’an Jiao Tong University[J],2018,52(07):60-67.
[12] 万齐杨，熊邦书，李新民，等. 基于DCAE-CNN的自动倾斜器滚动轴承故障诊断[J]. 振动与冲击,2020,39(11):273-279.
WAN Qiyang, XIONG Bangshu, LI Xinmin, et al. Fault diagnosis for rolling bearing of swashplate based on DCAE-CNN[J]. Journal of Vibration and Shock,2020,39(11):273-279.
[13] 吴晨芳，杨世锡，黄海舟，等. 一种基于改进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.
[14] 冯浩楠，付胜，胥永刚. 基于BN-1DCNN的旋转机械故障诊断研究[J]. 振动与冲击,2021,40(19):302-308.
FENG Haonan, FU Sheng, XU Yonggang. Fault diagnosis of rotating machinery based on BN-1DCNN model[J].Journal of Vibration and Shock,2021,40(19):302-308.
[15] 袁建虎，韩涛，唐建，等. 基于小波时频图和CNN的滚动轴承智能故障诊断方法[J]. 机械设计与研究, 2017,33(2):93-97.
YUAN Jianhu, HAN Tao, TANG Jian, et al. An approach to intelligent fault diagnosis of rolling bearing using wavelet time-frequency representations and CNN[J]. Machine Design and Research,2017,33(2):93-97.
[16] Liu R N, Yang B Y, Zio E , et al. Artificial intelligence for fault diagnosis of rotating machinery: A review[J]. Mechanical Systems & Signal Processing, 2018, 108:33-47.
[17] 李涛，段礼祥，张东宁，等. 自适应卷积神经网络在旋转机械故障诊断中的应用[J]. 振动与冲击, 2020,39(16):275-288.
LI Tao, DUAN Lixiang, ZHANG Dongning, et al. Application of adaptive convolutional neural network in rotating machinery fault diagnosis[J]. Journal of Vibration and Shock,2020,39(16):275-288.
[18] Guo L , Lei Y , Xing S , et al. Deep Convolutional Transfer Learning Network: A New Method for Intelligent Fault Diagnosis of Machines With Unlabeled Data[J]. IEEE Transactions on Industrial Electronics, 2019,66(9):7316-7325.
[19] 来杰，王晓丹，向前，等.自编码器及其应用综述[J]. 通信学报, 2021, 42(09):218-230.
LAI Jie, WANG Xiaodan, XIANG Qian, et al. Review on autoencoder and its application[J]. Journal on Communications,2021,42(09):218-230.
[20] Rui Z , Yan R , Chen Z , et al. Deep learning and its applications to machine health monitoring[J]. Mechanical Systems and Signal Processing, 2019, 115:213-237.
[21] 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):132-139.
LI Heng, ZHANG Qing, QIN Xianrong, et al. Fault diagnosis method for rolling bearings based on short-time Fourier transform and convolutional neural network[J]. Journal of Vibration and Shock,2018,37(19):132-139.