基于提升深度迁移自动编码器的轴承智能故障诊断

doi:10.3901/JME.2020.09.084

机械工程学报 ›› 2020, Vol. 56 ›› Issue (9): 84-90.doi: 10.3901/JME.2020.09.084

扫码分享

基于提升深度迁移自动编码器的轴承智能故障诊断

邵海东¹, 张笑阳², 程军圣¹, 杨宇¹

1. 湖南大学汽车车身先进设计制造国家重点实验室长沙 410082;
2. 中国航空工业集团公司西安航空计算技术研究所西安 710065

收稿日期:2019-05-29 修回日期:2020-01-08 出版日期:2020-05-05 发布日期:2020-05-29
通讯作者: 邵海东(通信作者),男,1990年出生,博士,讲师。主要研究方向为故障诊断与智能预测。E-mail:hdshao@hnu.edu.cn
作者简介:张笑阳,男,1990年出生,硕士,助理工程师。主要研究方向为设备测试性与安全性分析。E-mail:zxyang123456@126.com
基金资助:
国家自然科学基金（51905160，51875183）和中央高校基本科研业务费专项资金（531118010335）资助项目。

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

SHAO Haidong¹, ZHANG Xiaoyang², CHENG Junsheng¹, YANG Yu¹

1. State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, Hunan University, Changsha 410082;
2. Xi'an Aeronautics Computing Technique Research Institute, AVIC, Xi'an 710065

Received:2019-05-29 Revised:2020-01-08 Online:2020-05-05 Published:2020-05-29

摘要/Abstract

摘要： 实际工程中，含标注信息的轴承监测数据严重缺乏，这将导致其智能故障诊断模型难以有效构建。提出了一种基于提升深度迁移自动编码器的新方法用于不同机械设备间的轴承故障智能诊断。首先，采用可缩放指数型线性单元作为标准自动编码器的激活函数，提升原始振动数据的映射质量。然后，非负约束用于修正代价函数，进一步减少重构误差。其次，构建提升深度自动编码器并用充足可用的源域数据进行预训练，得到的参数作为目标模型的初始化参数。最后，目标域中仅有的一个训练样本用于目标模型的微调以适应剩余的测试样本。将所提方法用于分析不同轴承的试验振动数据，结果表明，所提方法能基于原始振动数据有效实现不同种机械设备间的迁移诊断。

关键词: 提升深度自动编码器, 轴承故障, 迁移诊断, 可缩放指数型线性单元, 非负约束

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

中图分类号:

TH17

邵海东, 张笑阳, 程军圣, 杨宇. 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 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.

参考文献

[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.

基于提升深度迁移自动编码器的轴承智能故障诊断

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

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

本文评价

[1]	汪煜坤, 易彩, 汪浩, 周秋阳, 冉乐, 王靖元. PSD引导的自适应频带划分方法及其在轴承故障诊断中的应用[J]. 机械工程学报, 2024, 60(17): 179-193.
[2]	邵海东, 肖一鸣, 颜深. 仿真数据驱动的改进无监督域适应轴承故障诊断[J]. 机械工程学报, 2023, 59(3): 76-85.
[3]	石颉, 李莎莎, 申海锋. 笼型感应电机故障诊断技术综述[J]. 电气工程学报, 2023, 18(1): 1-13.
[4]	周健, 郑联语, 王艺玮, 王移川. 面向旋转机械迁移诊断的分层并行网络模型自动创建方法[J]. 机械工程学报, 2022, 58(22): 115-128.
[5]	陈是扦, 彭志科, 周鹏. 信号分解及其在机械故障诊断中的应用研究综述[J]. 机械工程学报, 2020, 56(17): 91-107.
[6]	刘东东, 程卫东, 万广通. 基于故障特征趋势线模板的滚动轴承故障诊断^*[J]. 机械工程学报, 2017, 53(9): 83-91.
[7]	樊薇李双蔡改改沈长青黄伟国朱忠奎. 瞬态成分Laplace小波稀疏表示及其轴承故障特征提取应用[J]. 机械工程学报, 2015, 51(15): 110-118.
[8]	张晗杜朝辉方作为王诗彬陈雪峰. 基于稀疏分解理论的航空发动机轴承故障诊断[J]. 机械工程学报, 2015, 51(1): 97-105.
[9]	王诗彬;许佳;朱忠奎. 瞬态成分参数的最小二乘法辨识及其轴承故障特征提取应用[J]. , 2012, 48(7): 68-76.
[10]	彭富强;于德介;罗洁思;武春燕. 基于多尺度线调频基稀疏信号分解的轴承故障诊断[J]. , 2010, 46(7): 88-95.
[11]	崔玲丽;康晨晖;张建宇;李文斌;高立新. 基于时延相关及小波包系数熵阈值的增强型共振解调方法[J]. , 2010, 46(20): 53-57.