类别标签辅助改进稠密网络的变工况轴承故障诊断

孙洁娣1,2,刘保1,温江涛3,时培明3,闫盛楠1,2,肖启阳4

振动与冲击 ›› 2022, Vol. 41 ›› Issue (17) : 204-212.

PDF(2220 KB)
PDF(2220 KB)
振动与冲击 ›› 2022, Vol. 41 ›› Issue (17) : 204-212.
论文

类别标签辅助改进稠密网络的变工况轴承故障诊断

  • 孙洁娣1,2,刘保1,温江涛3,时培明3,闫盛楠1,2,肖启阳4
作者信息 +

Fault diagnosis of variable condition bearing based on improved dense network aided by class labels

  • SUN Jiedi1,2, LIU Bao1, WEN Jiangtao3, SHI Peiming3, YAN Shengnan1,2, XIAO Qiyang4
Author information +
文章历史 +

摘要

基于数据驱动的滚动轴承智能故障诊断得到广泛研究,但多数研究中均假设训练数据与测试数据同分布,考虑到旋转机械实际运转中复杂多变的工况往往导致数据分布产生偏差,使得识别方法的通用性差、实际识别效果不佳。本文将域适应引入轴承故障诊断过程中,基于迁移学习提出了一种特征空间域和标签概率分布同步适应的迁移学习网络。该网络将一维稠密卷积网络及注意力机制融合实现复杂故障特征的自动提取;域适应处理通过联合最小化特征概率分布差异和标签概率分布差异来约束网络学习域不变特征;最终对变工况滚动轴承故障实现了高准确度的识别。实验结果表明了该方法的可行性及良好的性能。
关键词:轴承故障诊断;变工况;稠密卷积网络;注意力机制;类别标签辅助

Abstract

Intelligent fault diagnosis-based data-driven for rolling bearings has been widely studied, however, most researches assume that training data and test data are the same distribution. The complex and variable working conditions in the actual operation of rotating machinery often lead to deviations in data distribution, which result in poor versatility and low identification accuracy. This paper introduced domain adaptation and proposed a transfer diagnosis network with synchronous adaptation of feature space domain and label probability distribution. The network combines a one-dimensional dense convolutional network and attention mechanism to automatically extract complex fault features; the domain adaptation constrains the network to learn domain invariant features by jointly minimizing the difference in feature probability distribution and label probability distribution; finally rolling bearing faults under variable operating conditions can be identified with high accuracy. The experimental results show the validity and better performance of this method.
Key words: bearing fault diagnosis; variable working conditions; dense convolution network; attention mechanism; label auxiliary

关键词

轴承故障诊断 / 变工况 / 稠密卷积网络 / 注意力机制 / 类别标签辅助

Key words

bearing fault diagnosis / variable working conditions / dense convolution network / attention mechanism / label auxiliary

引用本文

导出引用
孙洁娣1,2,刘保1,温江涛3,时培明3,闫盛楠1,2,肖启阳4. 类别标签辅助改进稠密网络的变工况轴承故障诊断[J]. 振动与冲击, 2022, 41(17): 204-212
SUN Jiedi1,2, LIU Bao1, WEN Jiangtao3, SHI Peiming3, YAN Shengnan1,2, XIAO Qiyang4. Fault diagnosis of variable condition bearing based on improved dense network aided by class labels[J]. Journal of Vibration and Shock, 2022, 41(17): 204-212

参考文献

[1] KHAN S, YAIRI T. A review on the application o deep learning in system health management [J], Mechanical Systems and Signal Processing, 2018, 107: 241-265.
[2] 温江涛,闫常弘,孙洁娣,乔艳雷.基于压缩采集与深度学轴承故障诊断方法[J].仪器仪表学报, 2018, 39(1):171-179.
WEN J T, YAN CH H, SUN J D, et al. Bearing fault diagnosis method based on compressed acquisition and deep learning [J]. Chinese Journal of Scientific Instrument, 2018, 39(1): 171-179.
[3] ZHAO R, YAN RQ, CHEN ZH, et al. Deep learning and its applications to machine health monitoring [J]. Mechanical Systems and Signal Processing, 2019, 115: 213-237.
[4] LEI YG, YANG B, JIANG XW, et al. Applications of machine learning to machine fault diagnosis: A review and roadmap [J]. Mechanical Systems and Signal Processing, 2020, 138: 106587.
[5] JING L Y, ZHAO M, LI P, et al. A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox [J]. Measurement, 2017, 111:1-10.
[6] LIANG P F, DENG CH, WU J, et al. Compound Fault Diagnosis of Gearboxes via Multi-label Convolutional Neural Network and Wavelet Transform [J]. Computers industry, 2019, 113(113): 103132.
[7] LU CH, WANG ZH Y, ZHOU B. Intelligent fault diagnosis of rolling bearing using hierarchical convolutional network based health state classification [J]. Advanced Engineering Informatics, 2017, 32(32): 139-151.
[8] 庄福振,罗平,何清,等. 迁移学习研究进展[J]. 软件学报,2015,26(1):26-39.
ZHUANG F ZH, LUO P, HE Q, et al. Survey on Transfer Learning Research [J]. Journal of Software, 2015, 26(1): 26-39.
[9] 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 YY, YANG B, DU ZH J, et al. Deep Transfer Diagnosis Method for Machinery in Big Data Era [J]. Journal Of Mechanical Engineering,  2019, 55(7): 1-8.
[10] 陈仁祥, 杨星, 胡小林, 等. 深度置信网络迁移学习的行星齿轮箱故障诊断方法[J]. 振动与冲击, 2021,40(1): 127-133+150.
CHEN R X, Yang X, HU X, et al. Planeraty gearbox fault diagnosis method based on deep belief network transfer learning [J]. Journal of Vibration and Shock, 2021, 40(1): 127-133+150.
[11] SUN M D, WANG H, LIU P, et al. A sparse stacked denoising autoencoder with optimized transfer learning applied to the fault diagnosis of rolling bearings[J]. Measurement: Journal of the International Measurement Confederation, 2019, 146(146): 305-314.
[12] HAN T, LIU CH, YANG W G, et al. Learning transferable features in deep convolutional neural networks for diagnosing unseen machine conditions [J]. ISA Transactions, 2019, 93: 341-353.
[13] 郭亮,董勋,高宏力,李长根.无标签数据下基于特征知识迁移的机械设备智能故障诊断[J].仪器仪表学报, 2019, 40(8):58-64.
 GUO L, DONG X, GAO H L, et al. Intelligent fault diagnosis of mechanical equipment based on feature knowledge transfer under unlabeled data[J].Chinese Journal of Scientific Instrument, 2019, 40(8): 58-64.
[14] YANG B, LEI Y G, JIA F, et al. An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings[J]. Mechanical Systems and Signal Processing, 2019, 122(122): 692–706.
[15] LEI Y G, GUO L, XING S B, et al. Deep Convolutional Transfer Learning Network: A New Method for Intelligent Fault Diagnosis of Machines with Unlabeled Data[J]. IEEE Transactions on Industrial Electronics, 2019, 66(9): 7316–7325.
[16] 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 Chunzhi, JIANG Pengcheng, FENG Fuzhou, et al. Gearbox fault diagnosis based on one-dimensional convolutional neural network[J], Vibration and Shock, 2018, 37(22): 51-56.
[17] 周奇才, 刘星辰, 赵炯等. 旋转机械一维深度卷积神经网络故障诊断研究[J], 振动与冲击,2018, 37(23):31-37.
ZHOU Qicai, LIU Xingchen, ZHAO Jiong, et al. Fault diagnosis of one-dimensional deep convolutional neural network for rotating machinery[J], Vibration and Shock, 2018, 37(23): 31-37.
[18] 刘立, 朱建成, 韩光洁, 等. 基于1D-CN联合特征提取的轴承健康监测与故障诊断[J], 软件学报,2021,32(8): 2379-2390.
LIU L, ZHU J C, HAN G J, et al. Bearing healgh monitroing and fault diagnosis based on joint feature extraction in 1D-CNN [J], Ruan Jian Xue Bao/Journal of Software, 2021,32(8): 2379-2390. (in Chinese)
[19] JIAO J Y, ZHAO M, LIN J, et al. A comprehensive review on convolutional neural network in machine fault diagnosis [J]. Neurocomputing, 2020, 417: 36-63.
[20] LIU CH CH, SUN X F, CHEN CH Y, et al. Multi-Scale Residual Hierarchical Dense Networks for Single Image Super-Resolution[J]. IEEE Access, 2019, 7: 60572–60583.
[21] JIAO J Y, ZHAO M, LIN J, et al. Deep Coupled Dense Convolutional Network With Complementary Data for Intelligent Fault Diagnosis[J]. IEEE Transactions on Industrial Electronics, 2019, 66(12): 9858–9867.
[22] WOO S, PARK J, LEE J Y, et al. CBAM: Convolutional block attention module[J]. Lecture Notes in Computer Science, 2018, 11211 LNCS: 3-19.
[23] LI X, ZHANG W, DING Q, et al. Multi-layer domain adaptation method for rolling beraring fault diagnosis [J], Signal Processing, 2019, 157: 180-197.
[24] AN Z H, LI SH M, WANG J R, 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.
[25] WANG X S, HUANG W W, CHENG Y H, et al. Multisource Domain Attribute Adaptation Based on Adaptive Multikernel Alignment Learning[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2020, 50(5): 1897-1908.
[26] ZHU Y CH, ZHUANG F ZH, WANG J D, et al. Deep Subdomain Adaptation Network for Image Classification[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 1: 1-10.
[27] SMITH W A, RANDALL R B. Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study [J]. Mechanical Systems and Signal Processing, 2015, 64-65(12):100-131.
[28] PAN S J, TSANG I W, KWOK J T, et al. Domain adaptation via transfer component analysis [J]. IEEE Transactions on Neural Networks, 2011, 22(2): 199-210.
[29] WANG B, LEI YG, LI NP, et al, A Hybrid Prognostics Approach for Estimating Remaining Useful Life of Rolling Element Bearings[J], IEEE Transactions on Reliability, 2018, 1: 1-12.

PDF(2220 KB)

Accesses

Citation

Detail

段落导航
相关文章

/