Research on Multi-condition Bearing Fault Diagnosis Based on Improved Semi-supervised Deep Belief Network

doi:10.3901/JME.2021.15.080

Abstract

Abstract: With the development of industrial automation, the processes in the production of rotating systems are becoming more and more sophisticated and complex. When multiple processes are executed, the internal bearing speed and load are constantly changing. For this type of multi-working conditions, the original fault diagnosis method trained in a single working condition is no longer applicable. Therefore, a bearing fault diagnosis method for bearings under multiple operating conditions is proposed. This method is based on a semi-supervised deep belief network (Semi-supervised deep belief network, SSDBN). Using a small amount of labelled data to conduct the fault classification and judgment, and it can improve the accuracy of fault diagnosis under varying working conditions. First, set the source and target domains to the same load, different speed and damage size data set, and process the source and target domain signals by wavelet packet decomposition. Then the maximum mean discrepancy algorithm ((Maximum mean discrepancy, MMD) is used as the evaluation indicator of the difference between the distribution of data features in the source and target domains, and the smaller distribution difference is selected. Feature sample data, make the model easier to compare features, improve the classification accuracy of the target domain data. Use the improved semi-supervised deep belief network to train less labelled data and a large number of unlabelled data, improve the classification accuracy of the data to be tested. Take the bearing data set of Western Reserve University as an example to verify the diagnostic accuracy of the model under the same load at different speeds and damage size conditions, as well as the diagnostic accuracy of the model under different load, speed and damage size conditions. The results show that the method can improve the accuracy of the fault diagnosis of the bearing under the constraints of multiple operating conditions, reduce the false alarm rate of the fault diagnosis, and reduce the gradient disappearance during the training model, and increase the probability of successful failure classification. In addition, the proposed method does not need to be considered the sensitivity of various features does not need to rely on expert knowledge and experience. It has strong universality and compatibility, which is helpful to find and replace damaged bearings in time and ensure the safe and reliable operation of machinery and equipment.

Key words: bearing, semi-supervised deep belief network, maximum mean difference algorithm, fault diagnosis

CLC Number:

TH133
TN911

YE Nan, CHANG Peize, ZHANG Luyu, WANG Jia. Research on Multi-condition Bearing Fault Diagnosis Based on Improved Semi-supervised Deep Belief Network[J]. Journal of Mechanical Engineering, 2021, 57(15): 80-90.

References

[1] YAN Xiaoan, JIA Minping, ZHANG Wan, et al. Fault diagnosis of rolling element bearing using a new optimal scale morphology analysis method[J]. Isa Transactions, 2018, 73:165-180.
[2] JIA Feng, LEI Yaguo, GUO Liang, et al. A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines[J]. Neurocomputing, 2018, 272(10):619-628.
[3] LU Siliang, HE Qingbo, ZHAO Jiwen, et al. Bearing fault diagnosis of a permanent magnet synchronous motor via a fast and online order analysis method in an embedded system[J]. Mechanical Systems and Signal Processing, 2017, 113(12):36-49.
[4] 张小龙, 张氢, 秦仙蓉, 等. 基于ITD-形态滤波和Teager能量谱的轴承故障诊断[J]. 仪器仪表学报, 2016, 37(4):788-795. ZHANG Xiaolong, ZHANG Qing, QIN Xianrong, et al. Fault diagnosis method for rolling bearing based on ITD-morphological filter and Teager energy spectrum[J]. Chinese Journal of Scientific Instrument, 2016, 37(4):788-795.
[5] 李宏坤, 杨蕊, 任远杰, 等. 利用粒子滤波与谱峭度的滚动轴承故障诊断[J]. 机械工程学报, 2017, 53(3):63-72. LI Hongkun, YANG Rui, REN Yuanjie, et al. Rolling element bearing diagnosis using particle filter and kurtogram[J]. Journal of Mechanical Engineering, 2017, 53(3):63-72.
[6] 李志农, 张芬, 何旭平. 基于小波-KCCA的非线性欠定盲分离方法研究[J]. 仪器仪表学报, 2014, 35(3):601-606. LI Zhinong, ZHANG Fen, HE Xuping. Study on underdetermined blind source separation method of nonlinear mixture based on wavelet and Kernel Canonical Correlation Analysis[J]. Chinese Journal of Scientific Instrument, 2014, 35(3):601-606.
[7] MCCULLOCH W, PITTS W. A logical calculus of the ideas immanent in nervous activity[J]. Bulletin Mathematical Biology, 1943, 5(4):115-133.
[8] SAMUEL A. Some studies in machine learning using the game of checkers. II:recent progress[J]. Ibm Journal of Research and Development, 1967, 11(6):601-617.
[9] RUMELHART D, HINTON G, WILLIAMS R, et al. Learning representations by back-propagating errors[J]. Nature, 1988, 323(6088):696-699.
[10] FISCHER A, IGEL C. An introduction to restricted Boltzmann machines[C]//Iberoamerican Congress on Pattern Recognition, 2012:14-36.
[11] LÉCUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[C]//Proc. IEEE, 1998, 86(11):2278-2324.
[12] 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(15):11-16, 26. 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(15):11-16, 26.
[13] 沈长青, 汤盛浩, 江星星, 等. 独立自适应学习率优化深度信念网络在轴承故障诊断中的应用研究[J]. 机械工程学报, 2019, 55(7):81-88. SHEN Changqing, TANG Shenghao, JIANG Xingxing, et al. Bearings fault diagnosis based on improved deep belief network by self-individual adaptive learning rate[J]. Journal of Mechanical Engineering, 2019, 55(7):81-88.
[14] 赵光权, 葛强强, 刘小勇, 等. 基于DBN的故障特征提取及诊断方法研究[J]. 仪器仪表学报, 2016, 37(9):1946-1953. ZHAO Guangquan, GE Qiangqiang, LIU Xiaoyong, et al. Fault feature extraction and diagnosis method based on deep belief network[J]. Chinese Journal of Scientific Instrument, 2016, 37(9):1946-1953.
[15] CHEN Zhiqiang, DENG Shengcai, CHEN Xudong, et al. Deep neural networks-based rolling bearing fault diagnosis[J]. Microelectronics Reliability, 2017, 75(75):327-333.
[16] SHAO Haidong, JIANG Hongkai, WANG Fuan, et al. Rolling bearing fault diagnosis using adaptive deep belief network with dual-tree complex wavelet packet[J]. Isa Transactions, 2017, 69:187-201.
[17] SHAO Haidong, JIANG Hongkai, ZHANG Haizhou, 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.
[18] 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, 55(7):1-8. LEI Yaguo, 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.
[19] ZHANG Zhongwei, CHEN Huaihai, LI Shunming, et al. A novel geodesic flow kernel based domain adaptation approach for intelligent fault diagnosis under varying working condition[J]. Neurocomputing, 2020, 376:54-64.
[20] LI Xiang, JIA Xiaodong, ZHANG Wei, et al. Intelligent cross-machine fault diagnosis approach with deep auto-encoder and domain adaptation[J]. Neurocomputing, 2020, 383:235-247.
[21] AN Zenghui, LI Shunming, WANG Jinrui, et al. Generalization of deep neural network for bearing fault diagnosis under different working conditions using multiple kernel method[J]. Neurocomputing, 2019, 352:42-53.
[22] TONG Zhe, LI Wei, ZHANG Bo, et al. Bearing fault diagnosis based on domain adaptation using transferable features under different working conditions[J]. Shock and Vibration, 2018, 2018(2018):1-12.
[23] WANG Gongming, QIAO Junfei, LI Xiaoli, et al. Improved classification with semi-supervised deep belief network[J]. IFAC-Papers on Line, 2017, 50(1):4174-4179.
[24] GRETTON A, BORGWARDT K, RASCH M, et al. A kernel method for the two-sample-problem[C]//Neural Information Processing Systems, 2006:513-520.
[25] WANG Mei, DENG Weihong. Deep face recognition with clustering based domain adaptation[J]. Neurocomputing, 2020, 393:1-14.
[26] QIN Yi, WANG Xin, ZOU Jingqiang. The optimized deep belief networks with improved logistic sigmoid units and their application in fault diagnosis for planetary gearboxes of wind turbines[J]. IEEE Transactions on Industrial Electronics, 2019, 66(5):3814-3824.
[27] 张云强, 张培林, 王怀光, 等. 基于双时域微弱故障特征增强的轴承早期故障智能识别[J]. 机械工程学报, 2016, 52(21):96-103. ZHANG Yunqiang, ZHANG Peilin, WANG Huaiguang, et al. Rolling bearing early fault intelligence recognition based on weak fault feature enhancement in time-time domain[J]. Journal of Mechanical Engineering, 2016, 52(21):96-103.
[28] LOPARO K. Bearing data center, case western reserve university[EB/OL]. 2013[2020-05-25]. http://www.eecs.case.edu/laboratory/bearing.
[29] RANZATO M, BOUREAU Y, LECUN Y, et al. Sparse feature learning for deep belief networks[C]//Neural Information Processing Systems, 2007:1185-1192.
[30] SALAKHUTDINOV R, HINTON G. Deep boltzmann machines[C]//International Conference on Artificial Intelligence and Statistics, 2009:448-455.
[31] HINTON G, SALAKHUTDINOV R. Reducing the dimensionality of data with neural networks[J]. Science 2006, 313(5786):504-507.
[32] HINTON G, OSINDERO S, TEH Y. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2014, 18(7):1527-1554.