时变转速下基于双阈值注意力生成对抗网络和小样本的转子-轴承系统故障诊断

doi:10.3901/JME.2023.12.215

机械工程学报 ›› 2023, Vol. 59 ›› Issue (12): 215-224.doi: 10.3901/JME.2023.12.215

• 特邀专栏：制造大数据分析与决策 • 上一篇下一篇

扫码分享

时变转速下基于双阈值注意力生成对抗网络和小样本的转子-轴承系统故障诊断

邵海东¹, 李伟¹, 刘翊², 杨斌³

1. 湖南大学机械与运载工程学院长沙 410082;
2. 国家先进轨道交通装备创新中心株洲 412000;
3. 株洲中车时代电气股份有限公司株洲 412001

收稿日期:2022-08-10 修回日期:2023-02-15 出版日期:2023-06-20 发布日期:2023-08-15
通讯作者: 邵海东(通信作者),男,1990年出生,博士,副教授,博士研究生导师。主要研究方向为故障诊断与寿命预测,数据挖掘与信息融合。E-mail:hdshao@hnu.edu.cn
基金资助:
国家自然科学基金(51905160)、湖南省自然科学基金优秀青年科学基金(2021JJ20017)和国家重点研发计划(2020YFB1712100)资助项目。

Fault Diagnosis of Rotor-bearing System under Time-varying Speeds by Using Dual-threshold Attention-embedded GAN and Small Samples

HAO Haidong¹, LI Wei¹, LIU Yi², YANG Bin³

1. College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082;
2. National Rail Transit Advanced Equipment Innovation Center, Zhuzhou 412000;
3. Zhuzhou CRRC Times Electric Co., Ltd., Zhuzhou 412001

Received:2022-08-10 Revised:2023-02-15 Online:2023-06-20 Published:2023-08-15

摘要/Abstract

摘要： 可用故障数据的匮乏给时变转速下转子-轴承系统的端到端故障诊断带来严重挑战，生成对抗网络为解决小样本故障诊断问题提供新思路，但其仍存在梯度消失、全局关联特征学习能力较弱和训练效率较低等缺点。因此，提出一种双阈值注意力生成对抗网络，用于生成高质量的红外热成像图片，以解决时变转速下转子-轴承系统的小样本故障诊断难题。首先，结合Wasserstein距离和梯度惩罚设计新型对抗损失函数，避免训练过程中的梯度消失。其次，构建注意力嵌入的生成对抗网络以指导学习红外热成像图片的全局热力关联特征。最后，开发双阈值训练机制进一步提高生成样本质量和训练效率。将所提方法用于分析转子-轴承系统的实测红外热成像图片，结果表明，所提方法能辅助准确诊断时变转速及小样本下的不同故障模式，性能优于目前常用的生成对抗网络方法。

关键词: 双阈值注意力生成对抗网络, 故障诊断, 时变转速, 小样本红外热成像, 转子-轴承系统

Abstract: End-to-end fault diagnosis of rotor-bearing system under time-varying speeds using a few samples is challenging. Despite generative adversarial network (GAN) provides a way to solve the problem of small-sample fault diagnosis, it still has some limitations, such as gradient vanishing, weak extraction of global correlation features, and low training efficiency. Therefore, a dual-threshold attention-embedded GAN is proposed for generating high-quality infrared thermal (IRT) images to solve small-sample fault diagnosis of rotor-bearing system under time-varying speeds. First, Wasserstein distance and gradient penalty are combined to design the new adversarial loss function to avoid gradient vanishing. Second, attention-embedded GAN is constructed to guide learn global thermal-correlation features of the IRT images. Finally, dual-threshold training mechanism is developed to further improve the generation quality and training efficiency. The proposed method is used to analyze the collected small IRT images of a rotor-bearing system, and the results show that the proposed method can accurately diagnosis different fault modes using small samples under time-varying speeds, which is superior to other popular GANs.

Key words: dual-threshold attention-embedded GAN, fault diagnosis, time-varying speeds, small infrared thermal images, rotor-bearing system

中图分类号:

TH17

邵海东, 李伟, 刘翊, 杨斌. 时变转速下基于双阈值注意力生成对抗网络和小样本的转子-轴承系统故障诊断[J]. 机械工程学报, 2023, 59(12): 215-224.

HAO Haidong, LI Wei, LIU Yi, YANG Bin. Fault Diagnosis of Rotor-bearing System under Time-varying Speeds by Using Dual-threshold Attention-embedded GAN and Small Samples[J]. Journal of Mechanical Engineering, 2023, 59(12): 215-224.

参考文献

[1] WEN Long,LI Xinyu,GAO Liang. A new reinforcement learning based learning rate scheduler for convolutional neural network in fault classification[J]. IEEE Transactions on Industrial Electronics,2021,68(12):12890-12900.
[2] 雷亚国,许学方,蔡潇,等. 面向机械装备健康监测的数据质量保障方法研究[J]. 机械工程学报,2021,57(4):1-9. LEI Yaguo,XU Xuefang,CAI Xiao,et al. Research on data quality assurance for health condition monitoring of machinery[J]. Journal of Mechanical Engineering,2021,57(4):1-9.
[3] 陈祝云,钟琪,黄如意,等. 基于增强迁移卷积神经网络的机械智能故障诊断[J]. 机械工程学报,2021,57(21):96-105. CHEN Zhuyun,ZHONG Qi,HUANG Ruyi,et al. Intelligent fault diagnosis for machinery based on enhanced transfer convolutional neural network[J]. Journal of Mechanical Engineering,2021,57(21):96-105.
[4] XING Saibo,LEI Yaguo,WANG Shuhui,et al. Distribution-invariant deep belief network for intelligent fault diagnosis of machines under new working conditions[J]. IEEE Transactions on Industrial Electronics,2021,68(3):2617-2625.
[5] 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 Haidong,ZHANG Xiaoyang,CHENG Junsheng,et al. Intelligent fault diagnosis of bearing using enhanced deep transfer auto-encoder[J]. Journal of Mechanical Engineering,2020,56(9):84-90.
[6] GAO Yiping,GAO Liang,LI Xinyu,et al. A zero-shot learning method for fault diagnosis under unknown working loads[J]. Journal of Intelligent Manufacturing,2020,31(4):899-909.
[7] GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al. Generative adversarial networks[J]. Advances in Neural Information Processing Systems,2014,3:2672-2680.
[8] SHAO Siyu,WANG Pu,YAN Ruqiang,et al. Generative adversarial networks for data augmentation in machine fault diagnosis[J]. Computers in Industry,2019,40(9):16-26.
[9] DAI Jun,WANG Jun,HUANG Weiguo,et al. Machinery health monitoring based on unsupervised feature learning via generative adversarial networks[J]. IEEE/ASME Transactions on Mechatronics,2020,25(5):2252-2263.
[10] 肖雄,肖宇雄,张勇军,等. 基于二维灰度图的数据增强方法在电机轴承故障诊断的应用研究[J]. 中国电机工程学报,2021,41(2):738-749. XIAO Xiong,XIAO Yuxiong,ZHANG Yongjun,et al. Research on the application of the data augmentation method based on 2D gray pixel images in the fault diagnosis of motor bearing[J]. Proceedings of the CSEE,2021,41(2):738-749.
[11] WANG Rugen,ZHANG Shaohui,CHEN Zhuyun,et al. Enhanced generative adversarial network for extremely imbalanced fault diagnosis of rotating machine[J]. Measurement,2021,180:109467.
[12] LIU Shaowei,JIANG Hongkai,WU Zhenghong,et al. Data synthesis using deep feature enhanced generative adversarial networks for rolling bearing imbalanced fault diagnosis[J]. Mechanical Systems and Signal Processing,2022,163:108139.
[13] HE Zhiyi,SHAO Haidong,ZHONG Xiang,et al. An intelligent fault diagnosis method for rotor-bearing system using small labeled infrared thermal images and enhanced CNN transferred from CAE[J]. Advanced Engineering Informatics,2020,46:101150.
[14] LI Xin,SHAO Haidong,JIANG Hongkai,et al. Modified Gaussian convolutional deep belief network and infrared thermal imaging for intelligent fault diagnosis of rotor-bearing system under time-varying speeds[J]. Structural Health Monitoring,2022,21(2):339-353.
[15] 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. CHEN Shiqian,PENG Zhike,ZHOU Peng. Review of signal decomposition theory and its applications in machine fault diagnosis[J]. Journal of Mechanical Engineering,2020,56(17):91-107.
[16] AMIN N,AMIN T G,MAHMOUD O,et al. Intelligent fault diagnosis of cooling radiator based on deep learning analysis of infrared thermal images[J]. Applied Thermal Engineering,2019,163:114410.
[17] JANSSENS O,VAN DE WALLE R,LOCCUFIER M,et al. Deep learning for infrared thermal image based machine health monitoring[J]. IEEE-ASME Transactions on Mechatronics,2018,23(1):151-159.
[18] JIA Zhen,LIU Zhenbao,VONG ChiMan,et al. A rotating machinery fault diagnosis method based on feature learning of thermal images[J]. IEEE Access,2019,7:12348-12359.
[19] LI Yongbo,DU Xiaoqiang,WAN Fangyi,et al. Rotating machinery fault diagnosis based on convolutional neural network and infrared thermal imaging[J]. Chinese Journal of Aeronautics,2020,33(2):427-438.
[20] CHOUDHARY A,MIAN T,FATIMA S. Convolutional neural network based bearing fault diagnosis of rotating machine using thermal images[J]. Measurement,2021,176:109196.
[21] MAO Gang,ZHANG Zhongzheng,QIAO Bin,et al. Fusion domain-adaptation cnn driven by images and vibration signals for fault diagnosis of gearbox cross-working conditions[J]. Entropy,2022,24(1):119.
[22] ARJOVSKY M,BOTTOU L. Towards principled methods for training generative adversarial networks[EB/OL].[2017-01-17],https://arxiv.org/abs/1701.04862.
[23] ZHANG H,GOODFELLOW I,METAXAS D. Self-attention generative adversarial networks[EB/OL].[2018-05-21],https://arxiv.org/abs/1805.08318.
[24] ARJOVSKY M,CHINTALA S,BOTTOU L. Wasserstein GAN[EB/OL].[2017-01-26],https://arxiv.org/abs/1701.07875.
[25] GULRAJANI I,AHMED F,ARJOVSKY M,et al. Improved training of Wasserstein GANs[EB/OL].[2017-05-31],https://arxiv.org/abs/1704.00028.
[26] SUN Guangcong,DING Shifei,SUN Tongfeng,et al. SA-CapsGAN:Using capsule networks with embedded self-attention for generative adversarial network[J]. Neurocomputing,2021,423:399-406.
[27] YANG Weijun,PANG Chengxin,HUANG Jinhai,et al. Sequence-to-point learning based on temporal convolutional networks for nonintrusive load monitor-ing[J]. IEEE Transactions on Instrumentation and Measurement,2021,70:2512910.
[28] LI Wei,ZHONG Xiang,SHAO Haidong,et al. Multi-mode data augmentation and fault diagnosis of rotating machinery using modified ACGAN designed with new framework[J]. Advanced Engineering Informatics,2022,52:101552.
[29] LI Yongbo,WANG Xianzhi,SI Shubin,et al. A new intelligent fault diagnosis method of rotating machinery under varying-speed conditions using infrared thermography[J]. Complexity,2019,2019(2):2619252.
[30] YANG Bin,LEI Yaguo,JIA Feng,et al. A polynomial kernel induced distance metric to improve deep transfer learning for fault diagnosis of machines[J]. IEEE Transactions on Industrial Electronics,2020,67(11):9747-9757.
[31] 孟宗,关阳,潘作舟,等. 基于二次数据增强和深度卷积的滚动轴承故障诊断研究[J]. 机械工程学报,2021,57(23):106-115. MENG Zong,GUAN Yang,PAN Zuozhou. Fault diagnosis of rolling bearing based on secondary data enhancement and deep convolutional network[J]. Journal of Mechanical Engineering,2021,57(23):106-115.

时变转速下基于双阈值注意力生成对抗网络和小样本的转子-轴承系统故障诊断

Fault Diagnosis of Rotor-bearing System under Time-varying Speeds by Using Dual-threshold Attention-embedded GAN and Small Samples

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	狄子钧, 袁东风, 李东阳, 梁道君, 周晓天, 信苗苗, 曹凤, 雷腾飞. 基于多尺度-高效通道注意力网络的刀具故障诊断方法[J]. 机械工程学报, 2024, 60(6): 82-90.
[2]	严如强, 许文纲, 王志颖, 朱启翔, 周峥, 赵志斌, 孙闯, 王诗彬, 陈雪峰, 张军辉, 徐兵. 航空发动机燃油控制系统故障诊断技术研究进展与挑战[J]. 机械工程学报, 2024, 60(4): 3-31.
[3]	张军辉, 刘施镐, 徐兵, 黄伟迪, 吕飞, 黄晓琛. 轴向柱塞泵智能化关键技术研究进展及发展趋势[J]. 机械工程学报, 2024, 60(4): 32-49.
[4]	丁孺琦, 熊文杰, 程敏, 徐兵. 智能化阀口独立电液控制系统安全性能评估[J]. 机械工程学报, 2024, 60(4): 101-112.
[5]	王志颖, 李天福, 许文纲, 孙闯, 张军辉, 徐兵, 严如强. 降噪混合注意力变分自编码器及其在轴向柱塞泵故障诊断中的应用[J]. 机械工程学报, 2024, 60(4): 167-177.
[6]	邵海东, 林健, 闵志闪, 明宇航. 分布外样本干扰下基于改进半监督原型网络的齿轮箱跨域故障诊断[J]. 机械工程学报, 2024, 60(4): 212-221.
[7]	潘海洋, 徐海锋, 郑近德, 童靳于, 张飞斌. 基于双加权不平衡矩阵分类器的机械故障诊断方法[J]. 机械工程学报, 2024, 60(3): 170-180.
[8]	赵轲, 叶敏, 王瑞欣, 陆海, 刘孟孟, 邵海东. 基于模糊域自适应的源自由域旋转机械故障诊断方法[J]. 机械工程学报, 2024, 60(18): 43-52.
[9]	李志鹏, 马天雨, 刘金平, 向青松, 唐俊杰. 基于非对称性对抗训练的多源域自适应智能故障诊断方法[J]. 机械工程学报, 2024, 60(18): 76-88.
[10]	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.
[11]	刘一龙, 李心远, 陈银萍, 成玮, 陈雪峰. 基于峭度曲面极大值的电机轴承保持架故障诊断方法[J]. 机械工程学报, 2024, 60(15): 89-99.
[12]	于小洛, 杨阳, 杜明刚, 何清波, 彭志科. 机械传动系统含偏差频率分量协同检测与分解方法[J]. 机械工程学报, 2024, 60(15): 100-112.
[13]	黄包裕, 张永祥. 一种基于三步法的轴承故障诊断方法[J]. 机械工程学报, 2024, 60(14): 51-68.
[14]	陈钱, 陈康康, 董兴建, 皇甫一樊, 彭志科, 孟光. 一种面向机械设备故障诊断的可解释卷积神经网络[J]. 机械工程学报, 2024, 60(12): 65-76.
[15]	王诗彬, 王世傲, 陈雪峰, 黄海, 安波涛, 赵志斌, 刘永泉, 李应红. 可解释性智能监测诊断网络构造及航空发动机整机试车与中介轴承诊断应用[J]. 机械工程学报, 2024, 60(12): 90-106.