Deep domain adaptation and its application in fault diagnosis across working conditions

PDF(1474 KB)

Journal of Vibration and Shock ›› 2020, Vol. 39 ›› Issue (12) : 281-288.

YUAN Zhuang1,2, DONG Rui2, ZHANG Laibin1, DUAN Lixiang1

Author information +

History +

Abstract

In the real-world production, variable working conditions lead to the distribution discrepancy in the monitoring data, which undermines the basis of classification models and consequently deteriorates the diagnosis accuracy. Therefore, a deep learning-based domain adaptation method is proposed for rolling bearing fault diagnosis across working conditions. In this method, two deep networks are constructed in a cascaded way. The first one is applied to process vibration signals and automatically mine fault-sensitive features. The second one maps sample features from different working conditions onto a deep hidden layer (the common feature space) to reduce the distribution discrepancy caused by fluctuant working conditions, generate working-condition-independent features, and realize domain adaptation. Moreover, this deep projection network is adaptively established by parameter optimization for the best cross-domain diagnosis performance. The experiments show that, compared with peer approaches and related literatures, deep domain adaptation has a higher accuracy in fault recognition across working conditions.

Key words

deep learning / domain adaptation / variable working condition / fault diagnosis

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

YUAN Zhuang1,2, DONG Rui2, ZHANG Laibin1, DUAN Lixiang1. Deep domain adaptation and its application in fault diagnosis across working conditions[J]. Journal of Vibration and Shock, 2020, 39(12): 281-288

References

[1] 王国彪，何正嘉，陈雪峰，等. 机械故障诊断基础研究“何去何从”[J]. 机械工程学报，2013, 49(1):63-72.
WANG Guo-biao, HE Zheng-jia, CHEN Xue-feng, et al. Basic Research on Machinery Fault Diagnosis--What is the Prescription [J]. Journal of mechanical engineering, 2013, 49(1):63-72.
[2] 李晗，萧德云. 基于数据驱动的故障诊断方法综述[J]. 控制与决策，2011, 26(1):1-9.
LI Han, XIAO De-yun. Survey on data driven fault diagnosis methods [J]. Control and Decision, 2011, 26(1):1-9.
[3] 张妮，车立志，吴小进. 基于数据驱动的故障诊断技术研究现状及展望[J]. 计算机科学，2017(S1):47-52.
ZHANG Ni, CHE Li-zhi, WU Xiao-Jin. Present Situation and Prospect of Data-driven Based Fault Diagnosis Technique [J]. Computer Science, 2017(S1):47-52.
[4] 钱林，康敏. 基于小波包与质心粒子群的齿轮箱故障诊断及应用[J]. 振动与冲击，2016, 35(11):191-195.
QIAN Lin, KANG Min, Gearbox fault diagnosis and its application based on wavelet packet and centroid particle swarm algorithm [J]. Journal of vibration and shock, 2016, 35(11):191-195.
[5] 何大伟，彭靖波，胡金海，等. 基于改进 FOA 优化的 CS-SVM 轴承故障诊断研究[J]. 振动与冲击，2018, 37(18):108-114.
HE Da-wei, PENG Jing-bo, HU Jin-hai, et al. Bearing fault diagnosis based on a modified CS-SVM model optimized by an improved FOA algorithm [J]. Journal of vibration and shock, 2018, 37(18):108-114.
[6] Wang J, Ma Y, Zhang L, et al. Deep learning for smart manufacturing: Methods and applications [J]. Journal of Manufacturing Systems, 2018, 48:144-156.
[7] 任浩，屈剑锋，柴毅，等. 深度学习在故障诊断领域中的研究现状与挑战[J]. 控制与决策，2017, 32(8):1345-1358.
REN Hao, QU Jian-feng, CHAI Yi, et al. Deep learning for fault diagnosis: The state of the art and challenge [J]. Control and Decision, 2017, 32(8):1345-1358.
[8] 吴春志，江鹏程，冯辅周，等. 基于一维卷积神经网络的齿轮箱故障诊断[J]. 振动与冲击，2018, 37(22):51-56.
WU Chun-zhi, JIANG Peng-cheng, FENG Fu-zhou, et al. Faults diagnosis method for gearboxes based on a 1-D convolutional neural network [J]. Journal of vibration and shock, 2018, 37(22):51-56.
[9] Jia F, Lei Y, Lin J, et al. Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data [J]. Mechanical Systems and Signal Processing, 2016, 72-73:303-315.
[10] 邹今春，沈玉娣. 变工况齿轮箱故障诊断方法综述[J]. 机械传动，2012, 36(08):124-127.
ZOU Jin-chun, SHEN Yu-di. Review of Gearbox Fault Diagnosis Techniques under Variable Conditions [J]. Journal of Mechanical Transmission, 2012, 36(08):124-127.
[11] Xiang L, Wei Z, Qian D. A robust intelligent fault diagnosis method for rolling element bearings based on deep distance metric learning [J]. Neurocomputing (2018), https://doi.org/10.1016/j.neucom.2018.05.021
[12] 潘海宁，张军，秦明，等. 基于能量谱特征的变速风机振动调制信号的检测方法[J]. 中国电机工程学报，2014, 20(34):166-171.
PAN Hai-ning, ZHANG Jun, QIN Ming, et al. Modulation Signal Detection of Wind Turbine’s Vibration Based on Feature Extraction of the Energy Spectrum [J]. Proceedings of the CSEE, 2014, 20(34):166-171.
[13] 秦嗣峰，冯志鹏，Ming L. Vold-Kalman滤波和高阶能量分离在时变工况行星齿轮箱故障诊断中的应用研究[J]. 振动工程学报，2015, 28(5):839-845.
QIN Si-feng, FENG Zhi-peng, Ming L. Application of Vold-Kalman filter and higher order energy separation to fault diagnosis of planetary gearbox under time-varying conditions [J]. Journal of Vibration Engineering, 2015, 28(5):839-845.
[14] Braun S. The synchronous (time domain) average revisited [J]. Mechanical Systems & Signal Processing, 2011, 25(4):1087-1102.
[15] He G, Ding K, Li W, et al. A novel order tracking method for wind turbine planetary gearbox vibration analysis based on discrete spectrum correction technique [J]. Renewable Energy, 2016, 87:364-375.
[16] Lu W, Liang B, Cheng Y, et al. Deep Model Based Domain Adaptation for Fault Diagnosis [J]. IEEE Transactions on Industrial Electronics, 2017, 64(3):2296-2305.
[17] 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, PP(99):1-9.
[18] Zhe T, Wei L, Bo Z, et al. Bearing Fault Diagnosis Based on Domain Adaptation Using Transferable Features under Different Working Conditions [J]. Shock and Vibration, 2018, 2018:1-12.
[19] 康守强，胡明武，王玉静，等. 基于特征迁移学习的变工况下滚动轴承故障诊断方法[J]. 中国电机工程学报，2018:1-9.
KANG Shou-qiang, HU Ming-wu, WANG Yu-jing, et al. Fault Diagnosis Method of a Rolling Bearing Under Variable Working Conditions based on Feature Transfer Learning [J]. Proceedings of the CSEE, 2018:1-9.
[20] Wei Z, Gaoliang P, Chuanhao L, et al. A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals [J]. Sensors, 2017, 17(425):1-21.
[21] Zhang W, Li C, Peng G, Chen Y, Zhang Z. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load [J]. Mechanical Systems and Signal Processing, 2018, 100:439–53.
[22] 谢骏遥，王金江，赵锐，等. 迁移因子分析在齿轮箱变工况故障诊断中的应用[J]. 电子测量与仪器学报，2016, 30(4):534-541.
XIE Jun-yao, WANG Jin-jiang, ZHAO Rui, et al. Application of transfer factor analysis in gearbox fault diagnosis under various working condition [J]. Journal of electronic measurement and instrumentation, 2016, 30(4):534-541.
[23] 段礼祥，谢骏遥，王凯，等. 基于不同工况下辅助数据集的齿轮箱故障诊断[J]. 振动与冲击，2017, 36(10):104-108.
DUAN Li-xiang, XIE Jun-yao, WANG Kai, et al. Gearbox diagnosis based on auxiliary monitoring datasets of different working conditions [J]. Journal of vibration and shock, 2017, 36(10):104-108.
[24] 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 Ru-qiang. 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.
[25] 沈飞，陈超，严如强. 奇异值分解与迁移学习在电机故障诊断中的应用[J]. 振动工程学报，2017, 30(1):118-126.
SHEN Fei, CHEN Chao, YAN Ru-qiang. Application of SVD and transfer learning strategy on motor fault diagnosis [J]. Journal of Vibration Engineering, 2017, 30(1):118-126.
[26] 刘正平，胡俊，张龙. 基于堆栈降噪自编码的轴承故障诊断方法[J]. 机床与液压，2018, 46(15):177-181.
LIU Zheng-ping, HU Jun, ZHANG Long. Fault Diagnosis Method of Bearing Based on Stacked Denoising Autoencoder [J]. Machine Tool & Hydraulics, 2018, 46(15):177-181.
[27] 王丽华，谢阳阳，张永宏，等. 采用深度学习的异步电机故障诊断方法[J]. 西安交通大学学报，2017, 51(10):128-134.
WANG Li-hua, XIE Yang-yang, ZHANG Yong-hong, et al. A Fault Diagnosis Method for Asynchronous Motor Using Deep Learning [J]. Journal of Xi’an Jiaotong university. 2017, 51(10):128-134.
[28] Shao H, Jiang H, Lin Y, et al. A novel method for intelligent fault diagnosis of rolling bearings using ensemble deep auto-encoders [J]. Mechanical Systems and Signal Processing, 2018, 102:278-297.
[29] Chen M, Xu Z, Weinberger K, et al. Marginalized Denoising Autoencoders for Domain Adaptation [J]. Computer Science, 2012:1-8.
[30] 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.
[31] Bernhard Schölkopf, Smola A , Klaus-Robert Müller. Kernel principal component analysis [C]. International Conference on Artificial Neural Networks. Springer, Berlin, Heidelberg, 1997:1-6.