Intelligent Fault Diagnosis of Bearing Using Enhanced Deep Transfer Auto-encoder

doi:10.3901/JME.2020.09.084

Abstract

Abstract: The collected data with labeled information of bearing is far insufficient in engineering practice, which is a great challenge for effectively training an intelligent diagnosis model. A new method called enhanced deep transfer auto-encoder is proposed for bearing fault diagnosis of different machines. First, scaled exponential linear unit is used to improve the quality of the mapped vibration data collected from bearing. Second, nonnegative constraint is adopted to modify the cost function to reduce reconstruction error. Third, an enhanced deep auto-encoder model is pre-trained with sufficient available data in the source domain and its parameters are transferred to initialize the target domain model. Finally, the enhanced deep transfer model is fine-tuned with only one training sample in the target domain to adapt to the characteristics of the remaining testing samples. Two sets of vibration data from bearings installed in the different machines are used to verify the feasibility of the proposed method. The analysis result confirms that the proposed method is able to achieve effective transfer diagnosis between different machines.

Key words: enhanced deep auto-encoder, bearing fault, transfer diagnosis, scaled exponential linear unit, nonnegative constraint

CLC Number:

TH17

SHAO Haidong, ZHANG Xiaoyang, CHENG Junsheng, YANG Yu. Intelligent Fault Diagnosis of Bearing Using Enhanced Deep Transfer Auto-encoder[J]. Journal of Mechanical Engineering, 2020, 56(9): 84-90.

References

[1] 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 Yagu, 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.
[2] SHAO Haidong, JIANG Hongkai, ZHANG Haizhou, et al. Electric locomotive bearing fault diagnosis using a novel convolutional deep belief network[J]. IEEE Transactions on Industrial Electronics, 2018, 65(3):2727-2736.
[3] 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 Yaguo, JIA Feng, ZHOU Xin, et al. A deep learningbased method for machinery health monitoring with big data[J]. Journal of Mechanical Engineering, 2015, 51(21):49-56.
[4] SHAO Haidong, JIANG Hongkai, ZHAO Huiwei, et al. A novel deep autoencoder feature learning method for rotating machinery fault diagnosis[J]. Mechanical Systems and Signal Processing, 2017, 95:187-204.
[5] SHAO Haidong, JIANG Hongkai, ZHAO Huiwei, et al. An enhancement deep feature fusion method for rotating machinery fault diagnosis[J]. Knowledge-Based Systems, 2017, 119:200-220.
[6] ZHAO Rui, YAN Ruqiang, CHEN Zhenghua, et al. Deep learning and its applications to machine health monitoring[J]. Mechanical Systems and Signal Processing, 2019, 115:213-237.
[7] 姜洪开,邵海东,李兴球. 基于深度学习的飞行器智能故障诊断方法[J]. 机械工程学报, 2019, 55(7):27-34. JIANG Hongkai, SHAO Haidong, LI Xingqiu. Deep learning theory with application in intelligent fault diagnosis of aircraft[J]. Journal of Mechanical Engineering, 2019, 55(7):27-34.
[8] 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, 5(7):1-8. LEI Yaiguo, YANG Bin, DU Zhaojun, et al. Deep transfer diagnosis method for machinery in big data era[J]. Journal of Mechanical Engineering, 2019, 55(7):1-8.
[9] PAN S J, YANG Qiang. A Survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10):1345-1359.
[10] 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(1):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.
[11] LU Weining,LIANG Bin,CHEN Yu,et al. Deep model based domain adaptation for fault diagnosis[J]. IEEE Transactions on Industrial Electronics, 2017, 64(3):2296-2305.
[12] WEN Long, GAO Liang, LI Xinyu. 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.
[13] 陈雪峰,訾艳阳.智能运维与健康管理[M]. 北京:机械工业出版社, 2018. CHEN Xuefeng, ZI Yanyang. Intelligent maintenance and health management[J]. Beijing:China Machine Press, 2018.
[14] VINOD N, HINTON G E. Rectified linear units improve restricted Boltzmann machines[C]//International Conference on Machine Learning in Haifa, Israel, June 21-June 24, 2010:807-814.
[15] LU Lu, SHIN Y, SU Yanhui, et al. Dying ReLU and initialization:Theory and numerical examples[EB/OL].[2019-03-15]. Cornell University Library 2019, http://export.arxiv.org/abs/1903.06733.
[16] KLAMBAUER G, UNTERTHINER T, MAYR A, et al. Self-normalizing neural networks[EB/OL].[2017-09-07]. Cornell University Library 2017, https://arxiv.org/abs/1706.02515v4.
[17] HOSSEINI-ASL E, ZURADA J M, NASRAOUI O. Deep learning of part-based representation of data using sparse autoencoders with nonnegativity constraints[EB/OL].[2016-01-12]. Cornell University Library 2016, https://arxiv.org/abs/1601.02733.
[18] LEI Yaguo, HE Zhengjia, ZI Yanyang. EEMD method and WNN for fault diagnosis of locomotive roller bearings[J]. Expert Systems with Applications, 2011, 38(6):7334-7341.
[19] QIAN Weiwei, LI Shunming, YI Pengxing, et al. A novel transfer learning method for robust fault diagnosis of rotating machines under variable working conditions[J]. Measurement, 2019, 138:514-525.