基于约束式AE-GAN的滚动轴承故障诊断方法

摘要
图/表
参考文献(20)
相关文章 (15)

全文: PDF (2053 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要由于滚动轴承故障样本获取困难，导致训练样本分布往往呈现极强的不平衡性，严重影响轴承智能故障诊断的准确率。针对滚动轴承训练样本不平衡的问题，提出一种基于约束式自编码器-生成对抗网络（Constrained AutoEncoder-Generative Adversarial Network，CAE-GAN）的故障诊断方法，通过增强故障样本特征以提高诊断模型的精度。首先结合自编码器和生成对抗网络，构建一种基于编码-解码-判别结构的网络模型，以提高生成器捕捉真实样本分布的能力。为进一步提高生成样本的质量，提出一种基于距离约束的方法以限制不同类别样本之间的距离，从而避免生成样本全部来自同一类型。最后通过滚动轴承故障诊断实验证明了本文方法能有效提高生成样本的质量，解决样本不平衡问题，轴承故障诊断准确率较其他方法有明显提高。

	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
	李可1
	何坚光1
	宿磊1
	顾杰斐1
	包灵昊1
	薛志钢2

关键词 ：滚动轴承, 故障诊断, 样本不平衡, 自编码器, 生成对抗网络, 距离约束

Abstract：It is difficult to obtain rolling bearing fault samples so that training samples appear imbalanced distribution, which seriously affects the accuracy of the bearing intelligent fault diagnosis. Aiming at the problem of imbalanced distribution, a fault diagnosis method based on Constrained AutoEncoder-Generative Adversarial Network (CAE-GAN) is proposed, which is used to enhance the feature of fault samples to improve the accuracy of fault diagnosis. Firstly, CAE-GAN combines autoencoder and generative adversarial network to construct a coding-decoding-discriminating network so that the generator can better capture the distribution of real samples. To improve the quality of the generated samples, a method of distance constraint is proposed to constrain the distance between the different generated samples to avoid all the generated samples of the same type. Finally, the rolling bearing fault diagnosis experiments indicate that the proposed method can effectively improve the quality of the generated samples, solve the problem of imbalanced distribution and is better than other models.

Key words： rolling bearing fault diagnosis imbalanced samples autoencoder generative adversarial network distance constraint

收稿日期: 2022-10-18 出版日期: 2023-12-15

引用本文:

李可1，何坚光1，宿磊1，顾杰斐1，包灵昊1，薛志钢2. 基于约束式AE-GAN的滚动轴承故障诊断方法[J]. 振动与冲击, 2023, 42(23): 65-70.
LI Ke1,HE Jianguang1,SU Lei1,GU Jiefei1,BAO Linghao1,XUE Zhigang2. Fault diagnosis method for rolling bearing based on CAE-GAN. JOURNAL OF VIBRATION AND SHOCK, 2023, 42(23): 65-70.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2023/V42/I23/65

[1] Shao H D, Jiang H K, Zhang H Z, et al. Rolling bearing fault feature learning using improved convolutional deep belief network with compressed sensing [J]. Mechanical Systems and Signal Processing, 2018, 100: 743-765.
[2] Zhang S Y, Su L, Gu J F, et al. Rotating machinery fault detection and diagnosis based on deep domain adaptation: A survey. Chinese Journal of Aeronautics, 2023, 36(1): 45-74.
[3] 雷春丽，夏奔锋，薛林林，等. 基于MTF-CNN的滚动轴承故障诊断方法 [J]. 振动与冲击，2022, 41(9): 151-158.
LEI Chunli, XIA Benfeng, XUE Linlin, et al. Rolling bearing fault diagnosis method based on MTF-CNN [J]. Journal of Vibration and Shock, 2022, 41(9): 151-158.
[4] 杨宇，罗鹏，甘磊，等. SADBN及其在滚动轴承故障分类识别中的应用 [J]. 振动与冲击，2019, 38(5): 11-16.
YANG Yu, LUO Peng, GAN Lei, et al. SADBN and its application in rolling bearing fault identification and classification [J]. Journal of Vibration and Shock, 2019, 38(5): 11-16.
[5] Shi P M, Guo X C, Han D Y, et al. A sparse auto-encoder method based on compressed sensing and wavelet packet energy entropy for rolling bearing intelligent fault diagnosis [J]. Journal of Mechanical Science and Technology, 2020, 34(4): 1445-1458.
[6] 雷亚国，贾峰，孔德同，等. 大数据下机械智能故障诊断的机遇与挑战 [J]. 机械工程学报，2018, 54(5): 94-104.
LEI Yaguo, JIA Feng, KONG Detong, et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era [J]. Journal of Mechanical Engineering, 2018, 54(5): 94-104.
[7] Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative Adversarial Networks [J]. Advances in Neural Information Processing Systems, 2014, 3: 2672-2680.
[8] Fiore U, Santis A, Perla F, et al. Using Generative Adversarial Networks for Improving Classification Effectiveness in Credit Card Fraud Detection [J]. Information Sciences, 2019, 479: 448-455.
[9] Liu S W, Jiang H K, Wu Z H, et al. Data synthesis using deep feature enhanced generative adversarial networks for rolling bearing imbalanced fault diagnosis [J]. Mechanical Systems and Signal Processing, 2022, 163(15): 108139.
[10] Liu J, Zhang C H, Jiang X X. Imbalanced fault diagnosis of rolling bearing using improved MsR-GAN and feature enhancement-driven CapsNet [J]. Mechanical Systems and Signal Processing, 2022, 168(1): 108664.
[11] Mao X, Li Q, Xie H, et al. Least squares generative adversarial networks [C]. IEEE International Conference on Computer Vision (ICCV), 2017, 2813-2821.
[12] Park N, Anand A, Moniz J, et al. MMGAN: Manifold Matching Generative Adversarial Network [J]. Proceedings - International Conference on Pattern Recognition, 2018, 1343-1348.
[13] Tran N, Bui T, Cheung N. Dist-GAN: An Improved GAN using Distance Constraints[J]. In ECCV, 2018, 11218: 0302-9743.
[14] Rumelhart D, Hinton G, Williams R. Learning representations by back-propagating errors [J]. Nature, 1986, 323(6088): 533-536.
[15] Meng Z, Zhan X Y, Li J, et al. An enhancement denoising autoencoder for rolling bearing fault diagnosis [J]. Measurement, 2018, 130: 448-454.
[16] Wang Y M, Han M H, Liu W. Rolling Bearing Fault Diagnosis Method Based on Stacked Denoising Autoencoder and Convolutional Neural Network [C]. 2019 International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering (QR2MSE), 2019.
[17] Makhzani A, Shlens J, Jaitly N, et al. Adversarial Autoencoders [J]. arXiv: 1511.05644, 2015.
[18] Wu E S, Cui H Y, E.Welsch R. Dual Autoencoders Generative Adversarial Network for Imbalanced Classification Problem [J]. IEEE Access, 2020, 91265-91275.
[19] Zhang J Y, Dang H, Lee H K, et al. Flipped-Adversarial AutoEncoders [J]. arXiv: 1802.04504, 2018.
[20] Xu Q T, Huang G, Yuan Y, et al. An empirical study on evaluation metrics of generative adversarial networks [J]. arXiv: 1806.07755, 2018.