改进的深度残差收缩网络轴承故障诊断方法

摘要
图/表
参考文献(22)
相关文章 (15)

全文: PDF (3790 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对深度残差收缩网络（Deep residual shrinkage network, DRSN）在降噪过程中引起的信号失真问题，提出了一种改进的深度残差收缩网络（Improved deep residual shrinkage network, IDRSN）并将其应用于滚动轴承的故障诊断中。首先，引入一种改进的半软阈值函数（Improved Semi-Soft Threshold Function, ISSTF）用于解决恒等偏差的问题并消除软阈值函数引起的信号失真。然后，设计了半软阈值模块（Semi-Soft Threshold Block, SSTB）和自适应斜率模块（Adaptive Slope Block, ASB）构建改进的残差收缩单元（Improved residual shrinkage building unit, IRSBU），用于自适应设置最优阈值并进一步修正输出。最后，将所提方法应用于两种不同工况的滚动轴承故障诊断中。研究结果表明，与现有方法相比，所提方法的分类准确率和鲁棒性更高，对于变转速工况下的故障诊断更为有效。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	唐世钰1
	童靳于1
	2
	郑近德1
	潘海洋1
	伍毅1

关键词 ：故障诊断, 滚动轴承, 深度残差收缩网络, 半软阈值函数, 自适应斜率模块

Abstract：Aiming at the signal distortion problem caused by deep residual shrinkage network (DRSN) in the noise reduction process, an improved deep residual shrinkage network (IDRSN) is proposed and applied to the fault diagnosis of rolling bearing. Firstly, an improved semi-soft threshold function (ISSTF) was introduced to solve the problem of identity deviation and eliminate the signal distortion caused by the soft threshold function. Then, a semi-soft threshold block (SSTB) and an adaptive slope block (ASB) were designed to construct an improved residual shrinkage building unit (IRSBU), which was used to adaptively set the optimal threshold value and further correct the output. Finally, the proposed method was applied to fault diagnosis of rolling bearing in two different operating conditions. The results showed that the proposed method had higher classification accuracy and robustness compared with the existing methods, and was more effective for fault diagnosis under variable speed conditions.

Key words： fault diagnosis rolling bearing deep residual shrinkage network semi-soft threshold function adaptive slope block

收稿日期: 2022-06-14 出版日期: 2023-09-28

引用本文:

唐世钰1，童靳于1,2，郑近德1，潘海洋1，伍毅1. 改进的深度残差收缩网络轴承故障诊断方法[J]. 振动与冲击, 2023, 42(18): 217-224.
TANG Shiyu1,TONG Jinyu1,2,ZHENG Jinde1,PAN Haiyang1,WU Yi1. Improved deep residual shrinkage network used for bearing fault diagnosis. JOURNAL OF VIBRATION AND SHOCK, 2023, 42(18): 217-224.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2023/V42/I18/217

[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 Yaguo, 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] ZHENG J D, PAN H Y, TONG J Y, et al. Generalized refined composite multiscale fuzzy entropy and multi-cluster feature selection based intelligent fault diagnosis of rolling bearing[J]. ISA transactions, 2022, 123: 136-151.
[3] 王新，闫文源. 基于变分模态分解和 SVM 的滚动轴承故障诊断[J]. 振动与冲击，2017，36(18)：252-256.
WANG Xin, YAN Wenyuan. Fault diagnosis of roller bearings based on the variational mode decomposition and SVM[J]. Journal of Vibration and Shock, 2017, 36(18): 252-256.
[4] MA J, XU F, HUANG K, et al. GNAR-GARCH model and its application in feature extraction for rolling bearing fault diagnosis[J]. Mechanical Systems and Signal Processing, 2017, 93: 175-203.
[5] HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.
[6] ELSISI M, TRAN M Q, MAHMOUD K, et al. Effective IoT-based deep learning platform for online fault diagnosis of power transformers against cyberattack and data uncertainties[J]. Measurement, 2022, 190: 110686.
[7] LI C, ZHANG W, PENG G, et al. Bearing fault diagnosis using fully-connected winner-take-all autoencoder[J]. IEEE Access, 2017, 6: 6103-6115.
[8] 许子非，金江涛，李春. 基于多尺度卷积神经网络的滚动轴承故障诊断方法[J]. 振动与冲击，2021，40(18)：47-52.
XU Zifei, JIN Jiangtao, LI Chun. New method for the fault diagnosis of rolling bearings based on a multiscale convolutional neural network[J]. Journal of Vibration and Shock, 2021, 40(18): 47-52.
[9] 张智禹，尹爱军，谭建. 融合注意力机制的改进 DBN 变工况齿轮箱故障诊断方法[J]. 振动与冲击，2021，40(14)：212-220.
ZHANG Zhiyu, YIN Aijun, TAN Jian. Improved DBN method with attention mechanism for the fault diagnosis of gearboxes under varying working condition[J]. Journal of Vibration and Shock, 2021, 40(14): 212-220.
[10] SHAO H D, JIANG H K, ZHANG H Z, et al. Electric locomotive bearing fault diagnosis using a novel convolutional deep belief network[J]. IEEE Transactions on Industrial Electronics, 2017, 65(3): 2727-2736.
[11] INCE T, KIRANYAZ S, EREN L, et al. Real-time motor fault detection by 1-D convolutional neural networks[J]. IEEE Transactions on Industrial Electronics, 2016, 63(11): 7067-7075.
[12] SHAO H D, JIANG H K, ZHAO K, et al. A novel tracking deep wavelet auto-encoder method for intelligent fault diagnosis of electric locomotive bearings[J]. Mechanical Systems and Signal Processing, 2018, 110: 193-209.
[13] ZELEZNIK R, FOLDYNA B, ESLAMI P, et al. Deep convolutional neural networks to predict cardiovascular risk from computed tomography[J]. Nature communications, 2021, 12(1): 1-9.
[14] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.
[15] ZHAO M H, KANG M, TANG B P, et al. Multiple wavelet coefficients fusion in deep residual networks for fault diagnosis[J]. IEEE Transactions on Industrial Electronics, 2018, 66(6): 4696-4706.
[16] ZHANG K, TANG B P, DENG L, et al. A hybrid attention improved ResNet based fault diagnosis method of wind turbines gearbox[J]. Measurement, 2021, 179: 109491.
[17] ZHAO M H, ZHONG S S, FU X Y, et al. Deep residual shrinkage networks for fault diagnosis[J]. IEEE Transactions on Industrial Informatics, 2019, 16(7): 4681-4690..
[18] ISOGAWA K, IDA T, SHIODERA T, et al. Deep shrinkage convolutional neural network for adaptive noise reduction[J]. IEEE Signal Processing Letters, 2017, 25(2): 224-228.
[19] LEI S, LU M M, LIN J Q, et al. Remote sensing image denoising based on improved semi-soft threshold[J]. Signal, Image And Video Processing, 2021, 15(1): 73-81.
[20] 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: 100-131..
[21] ZHAO D F, ZHANG H L, LIU S L, et al. Deep rational attention network with threshold strategy embedded for mechanical fault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-15.
[22] LAURENS V D M, HINTON G. Visualizing data using t-SNE[J]. Journal of machine learning research, 2008, 9(2605): 2579-2605.