Abstract：The big data of bearing obtained by online monitoring is mainly composed of a large amount of data without labels and a small amount of data with labels. Successful applications of many popular intelligent fault diagnosis methods rely on the supervised learning of large scale of labeled data. To solve this problem, an improved semi-supervised learning-based generative adversarial network (ISSL-GAN) is proposed in this paper. In This method, the classifier is given more powerful classification capability through the adversarial learning mode between the generator and classifier. Furthermore, the enhanced feature matching is proposed to extract deep features from the intermediate layers of the whole network and join the loss function to speed up the convergence of the training process. Meanwhile, the semi-supervised learning makes full use of few labeled data to improve the learning efficiency of the classifier. After training with plenty of unlabeled data and few labeled data, the obtained classifier can accurately discriminate the classes of analyzed data. The proposed network is applied to four experiments, each of which is to transfer from one bearing to another one for different bearings, working conditions, fault generation methods, and damage levels, and then is compared with other deep networks. The results indicate that the proposed ISSL-GAN has much higher accuracy on bearing fault diagnosis and has faster convergence speed during the training.
Key words: Deep learning; transfer learning; fault diagnosis; semi-supervised learning; unlabeled data; bearing
邢晓松，郭伟. 基于改进半监督生成对抗网络的少量标签轴承智能诊断方法[J]. 振动与冲击, 2022, 41(22): 184-192.
XING Xiaosong,GUO Wei. Intelligent diagnosis method for bearings with few labelled samples based on an improved semi-supervised learning-based generative adversarial network. JOURNAL OF VIBRATION AND SHOCK, 2022, 41(22): 184-192.
[1] Nandi S, Toliyat H A, Li X D. Condition monitoring and fault diagnosis of electrical motors - a review [J]. IEEE Transactions Energy Convers, 2005, 20(4): 719-729.
[2] Han Y and Song Y H. Condition monitoring techniques for electrical equipment-a literature survey [J]. IEEE Transactions Power Delivery, 2003, 18(1): 4-13.
[3] 雷亚国, 贾峰, 孔德同, 林京, 邢赛博. 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 Y G, Jia F, Kong D T, et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era [J]. Journal of Mechanical Engineering, 2018, 54(5): 94-104.
[4] Fu Y X, Jia L M, Qin Y, et al. Product function correntropy and its application in rolling bearing fault identification [J]. Measurement, 2017, 97: 88-99.
[5] Wang D, Tsui K L. Theoretical investigation of the upper and lower bounds of a generalized dimensionless bearing health indicator [J]. Mechanical Systems and Signal Processing, 2018, 98: 890-901.
[6] Cui L L, Gong X Y, Zhang J Y, et al. Double-dictionary matching pursuit for fault extent evaluation of rolling bearing based on the Lempel-Ziv complexity[J]. Journal of Sound and Vibration, 2016, 385: 372-388.
[7] 雷亚国, 贾峰, 周昕, 等. 基于深度学习理论的机械装备大数据健康监测方法[J]. 机械工程学报, 2015, 51(21): 49-56.
Lei Y G, Jia F, ZHOU Xin, et al. A deep learning-based method for machinery health monitoring with big data [J]. Journal of Mechanical Engineering, 2015, 51(21): 49-56.
[8] 陈仁祥, 杨星, 胡小林, 等. 深度置信网络迁移学习的行星齿轮箱故障诊断方法[J]. 振动与冲击, 2021, 40(01): 127-133+150.
CHEN Renxiang, YANG Xing, HU Xiaolin, et al. Planetary gearbox fault diagnosis method based on deep belief network transfer learning[J]. Journal of Vibration and Shock, 2021, 40(01): 127-133+150.
[9] Shao S Y, Mcaleer S, Yan R Q, et al. Highly accurate machine fault diagnosis using deep transfer learning [J]. IEEE Transactions on Industrial Informatics, 2018, 15(4): 2446-2455.
[10] Wen L, Gao L, Li X Y, et al. A new deep transfer learning based on sparse auto-encoder for fault diagnosis[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2019, 49(1): 136-144.
[11] 王肖雨, 童靳于, 郑近德, 等. 基于流形嵌入分布对齐的滚动轴承迁移故障诊断方法[J]. 振动与冲击, 2021, 40(08): 110-116.
WANG Xiaoyu, TONG Jinyu, ZHENG Jinde, et al. Transfer fault diagnosis for rolling bearings based on manifold embedded distribution alignment [J]. Journal of Vibration and Shock, 2021, 40(08): 110-116.
[12] Lu W N, Liang B, Cheng Y, et al. Deep model based domain adaptation for fault diagnosis [J]. IEEE Transactions on Industrial Electronics, 2017, 63(3): 2296-2305.
[13] Zhu J, Chen N, Shen C. A new deep transfer learning method for bearing fault diagnosis under different working conditions [J]. IEEE Sensors Journal, 2020, 20(15): 8394-8402.
[14] Han T, Liu C, Yang W, et al. A novel adversarial learning framework in deep convolutional neural network for intelligent diagnosis of mechanical faults [J]. Knowledge-Based Systems, 2018, 165: 474-487.
[15] Jiao J, Zhao M, Lin J. Unsupervised adversarial adaptation network for intelligent fault diagnosis [J]. IEEE Transactions on Industrial Electronics, 2020, 67(11): 9904-9913.
[16] Chai Z, Zhao C. A fine-grained adversarial network method for cross-domain industrial fault diagnosis [J]. IEEE Transactions on Automation Science and Engineering, 2020, 17(3): 1432-1442.
[17] Goodfellow I J, Pouget-abadie J, Mirza M, et al. Generative Adversarial Nets [C]. Proceedings of the 27th International Conference on Neural Information Processing Systems, 2014, 2: 2672- 2680.
[18] Liu Q, Ma G and Cheng C. Generative adversarial network based multi-class imbalanced fault diagnosis of rolling bearing [C]. 2019 4th International Conference on System Reliability and Safety (ICSRS) Rome :IEEE, .2019,318-324.
[19] 马波, 蔡伟东, 赵大力. 基于GAN样本生成技术的智能诊断方法[J]. 振动与冲击, 2020, 39(18): 153-160.
Ma B, Cai W D, Zhao D L. Intelligent diagnosis method based on GAN sample generation technology [J]. Journal of Vibration and Shock, 2020, 39(18): 153-160.
[20] Ding Y, Ma L, Ma J, et al. A generative adversarial network-based intelligent fault diagnosis method for rotating machinery under small sample size conditions [J]. IEEE Access, 2019, 7: 149736-149749.
[21] Zhang Y C, Ren Z H, Zhou S H, et al. An intelligent fault diagnosis for rolling bearing based on adversarial semi-supervised method [J]. IEEE Access, 2020, 8: 149868-149877.
[22] Zhang X Y, Shi H C, Zhu X B, et al. Active semi-supervised learning based on self-expressive correlation with generative adversarial networks [J]. Neurocomputing, 2019, 345: 103-113.
[23] Guo L, Lei Y G, Xing S B, 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, 2018, 66(9): 7316-7325.
[24] Li X, Zhang W, Xun X, et al. Deep Learning-based machinery fault diagnostics with domain adaptation across sensors at different places [J]. IEEE Transactions on Industrial Electronics, 2019, 67(8): 6785-6794.
[25] 邵海东, 张笑阳, 程军圣, 等. 基于提升深度迁移自动编码器的轴承智能故障诊断[J]. 机械工程学报, 2020, 56(9): 84-90.
Shao H D, Zhang X Y, Cheng J S, et al. Intelligent Fault Diagnosis of Bearing Using Enhanced Deep Transfer Auto-encoder [J]. Journal of Mechanical Engineering, 2020, 56(9): 84-90.
[26] Zhuang F Z, Qi Z Y, Duan K Y, et al. A comprehensive survey on transfer learning [EB/OL]. arXiv:1911.02685, 2019.
[27] Lu J, Gong P H, Ye J P, et al. Learning from very few samples: a survey [EB/OL]. arXiv:2009.02653, 2020.
[28] Tzeng E, Hoffman J, Saenko K, et al. Adversarial discriminative domain adaptation[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
[29] 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]. European conference of the prognostics and health management society, Bilbao, Spain, July 5-8, 2016.
