基于BiLSTM的滚动轴承故障诊断研究

赵志宏1,2,赵敬娇1,魏子洋1

振动与冲击 ›› 2021, Vol. 40 ›› Issue (1) : 95-101.

PDF(1926 KB)
PDF(1926 KB)
振动与冲击 ›› 2021, Vol. 40 ›› Issue (1) : 95-101.
论文

基于BiLSTM的滚动轴承故障诊断研究

  • 赵志宏1,2,赵敬娇1,魏子洋1
作者信息 +

Rolling bearing fault diagnosis based on BiLSM network

  • ZHAO Zhihong1,2, ZHAO Jingjiao1, WEI Ziyang1
Author information +
文章历史 +

摘要

针对滚动轴承的故障诊断,设计并实现了一种基于双向长短期记忆网络(BiLSTM)的诊断模型。将原始振动信号直接作为模型输入,自动提取滚动轴承故障特征,可以对内圈、滚动体、外圈不同故障类型及不同损伤程度的滚动轴承进行故障识别。该模型通过BiLSTM神经网络自动提取轴承振动信号的深层信息,弥补了传统故障诊断方法需要人工提取特征的不足,实现端到端的滚动轴承故障智能诊断。滚动轴承实测振动信号实验结果表明故障识别准确率可以达到99.8%以上,该方法具有一定的应用价值。

Abstract

Aiming at rolling bearing fault diagnosis, a diagnosis model based on the bidirectional long short term memory (BiLSTM) network was designed and implemented. The original vibration signal was directly used as the input of the model and rolling bearing fault features were extracted automatically to do fault recognition of rolling bearings with different fault types and damage degrees of inner race, rolling element and outer race. The deep information of bearing vibration signals was extracted with BiLSTM network to make up for the deficiency of traditional fault diagnosis methods needing to extract features manually, and thus realize the end-to-end intelligent fault diagnosis of rolling bearing. The test results of rolling bearing really measured vibration signals showed that the fault recognition correctness rate of the proposed method can reach 99.8%; the proposed method has a certain application value.

关键词

双向长短期记忆网络 / 轴承故障诊断 / 深度学习

Key words

bidirectional long short term memory (BiLSTM) network / bearing fault diagnosis / deep learning

引用本文

导出引用
赵志宏1,2,赵敬娇1,魏子洋1. 基于BiLSTM的滚动轴承故障诊断研究[J]. 振动与冲击, 2021, 40(1): 95-101
ZHAO Zhihong1,2, ZHAO Jingjiao1, WEI Ziyang1. Rolling bearing fault diagnosis based on BiLSM network[J]. Journal of Vibration and Shock, 2021, 40(1): 95-101

参考文献

[1] 王焱. 经验模态分解结合神经元网络在轴承故障诊断中的研究与应用[D]. 浙江大学,2007.
WANG Yan. Bearing Malfunction DiagnosingResearch and ApplicationBased on EMD and ANN[D]. College of Electrical Engineering Zhejiang University,2007
[2] 周剑飞,刘晨. 基于LSTM的设备故障在线检测方法[J/OL]. 计算机工程与应用:1-9. http://kns.cnki.net/kcms/detail/11.2127.TP.20181225.2104.005.html. [2019-10-20]
ZHOU Jian,LIU Chen. On-line Fault Detection Method for Equipment Based on LSTM[J]. Computer Engineering and Applications:1-9.http://kns.cnki.net/kcms/detail/11.2127.TP.20181225.2104.005.html. [2019-10-20]
[3] 陈伟,陈锦雄,江永全,等. 基于RS-LSTM的滚动轴承故障识别[J]. 中国科技论文,2018,13 (10) :1134-1141.
CHEN Wei,CHEN Jinxiong,JIANG Yongquan,et al. Fault identification of rolling bearing based on RS-LSTM[J]. China Science paper,2018,13 (10) :1134-1141.
[4] 杨宇,于德介,程军圣. 基于EMD与神经网络的滚动轴承故障诊断方法[J]. 振动与冲击,2005,24 (1) :85-88.
YANG Yu,YU Dejie,CHENG Junsheng. Roller bearing fault diagnosis method based on EMD and neural network[J]. Journal of Vibration and Shock,2005,24 (1) :85-88.
[5] 朱可恒. 滚动轴承振动信号特征提取及诊断方法研究[D].大连理工大学,2013.
ZHU Keheng. Research on Vibration Signal based Rolling Element Bearing Feature Extraction and Fault Diagnosis Method[D]. Dalian University of Technology,2013.
[6] 徐涛,裴爱岭,刘勇. 基于谐波小波包和SVM的滚动轴承故障诊断方法[J].沈阳航空航天大学学报,2014,31(4):50-54.
XU Tao,PEI Ai-ling,LIU Yong. Fault diagnosis of roller bearings with harmonic wavelet package and SVM[J]. Journal of Shenyang Aerospace University,2014,31 (4) :50-54.
[7] 孟宗,闫晓丽,王亚超. 基于LMD和HMM的旋转机械故障诊断[J]. 中国机械工程,2014,25(21):2942-2946+2951.
MENG Zong ,Yan Xiaoli,Wang Yachao.Rotating. Machinery Fault Diagnosis Based on Local Mean Decomposition and Hidden Markov Model[J].China Mechanical Engineering 2014,25 (21) :2942-2946+2951.
[8] 赵志宏,杨绍普. 一种基于样本熵的轴承故障诊断方法[J]. 振动与冲击,2012,31 (6) :136-140+154.
ZHAO ZhiHong,YANG ShaoPu. Sample entropy-based roller bearing fault diagnosis method[J]. Journal of Vibration and Shock,2012,31 (6) :136-140+154.
[9] OCAK H ,LOPARO K A. HMM-Based Fault Detection and Diagnosis Scheme for Rolling Element Bearings[J]. Journal of Vibration & Acoustics,2005,127 (4) :299-306.
[10] QU J,GHANG G,Uong T. A novel intelligent method for mechanical fault diagnosis based on dual-tree complex wavclet packet transform and multiple classifier fusion[J].Ncurocomputing, 2016,171 (4) :837-853.
[11] 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. Health monitoring method oI mec;hanic;al equipment big data based on deep learning theory [J]. Journal of Mechanical Engineering,2015,51 (21) :49-56.
[12] SUN W,Shao S,GHAO R,et al. A sparse auto-encodcibased deep neural network approach for induction mofor faults classification[J]. Measurement,2016,89 (ISFA) :171-178..
[13] 赵春华,胡恒星,陈保家,等. 基于深度学习特征提取和WOA-SVM状态识别的轴承故障诊断[J]. 振动与冲击,2019,38 (10) :31-37+48.
ZHAO Chunhua,HU Hengxing,CHEN Baojia,et al. Bearing fault diagnosis based on the deep learning feature extractionand WOA SVM state recognition[J]. Journal of Vibration and Shock,2019,38(10):31-37+48.
[14] 廖宁,陶洁,杨大炼. 基于深度学习和经验模态分解的双列圆锥滚动轴承故障诊断[J]. 湖南科技大学学报(自然科学版),2017,32 (2) :70-77.
LIAO Ning,TAO Jie,YANG Dalian. Fault diagnosis for double row tapered roller bearing based on deep learning method and EMD[J]. Journal of Hunan University of Science & Technology(Natural Science Edition),2017,32(2):70-77.
[15] MA X,TAO Z,WANG Y,et al. Longshort-term meoryeural network for traffic speed prediction using remote microwave sensor data[J]. Transportation Research Part C,2015,54:187-197.
[16] 王鑫,吴际,刘超,等. 基于LSTM 循环神经网络的故障时间序列预测[J]. 北京航空航天大学学报,2018,44(4):772-784.
WANG Xin,WU Ji,LIU Chao ,et al. Exploring LSTM based recurrent neural network for failure time series prediction[J]. Journal of Beijing University of Aeronautics and Astronautics,2018,44(4):772-784.
[17] 陈伟. 深度学习在滚动轴承故障诊断中的应用研究[D]. 西南交通大学,2018.
CH Wei. Application of deep learning in rolling bearing fault diagmosis[D]. Southwest Jiaotong University,2018.
[18] GRAVES A,SCHMIDHUBER J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures[J]. Neural Networks,2005,18(5-6):602-610.
[19] ZHAO R,YAN R,WANG J,et al. Learning to Monitor Machine Health with Convolutional Bi-Directional LSTM Networks[J]. Sensors,2017,17(2):273-291.
[20] 葛瑞,王朝晖,徐鑫,等.基于多层卷积神经网络特征和双向长短时记忆单元的行为识别[J].控制理论与应用,2017,34(6):790-796.
GE Rui,WANG Zhao-hui,XU Xin,et al.[J].Action recognition with hierarchical convolutional neural networks features and bi-directional long short-term memory model[J].Control Theory & Applications,2017,34 (6) :790-796.
[21] 魏贞原. 深度学习:基于Keras的Python实践[M]. 北京:电子工业出版社,2018.
WEI ZhenYuan. Deep Learning: Python Practice Based on Keras[M].Beijing: Publishing House Electronic Industry,2018.
[22] 雷亚国,何正嘉,訾艳阳,等. 基于特征评估和神经网络的机械故障诊断模型[J]. 西安交通大学学报,2006,40 (5) :558-562.
LEI Yaguo,HE Zhengjia,ZI Yanyang,et al. Mechanical  Fault Diagnosis  Model  Based  on  Feature  Evaluation  and Neural Networks[J]. Journal of Xi'an Jiaotong University, 2006,40 (5) :558-562.
[23] GUSTAFSSON O,TIBOR T. Detection of Damage in Assembled Rolling Element Bearings[J]. A S L E Transactions,1962,5 (1) :197-209.
[24] PAN H.,HE X.,TANG S.,et al. An Improved Bearing Fault Diagnosis Method using One-Dimensional CNN and LSTM[J]. Journal of Mechanical Engineering,2018,64(7-8),443-452.

PDF(1926 KB)

Accesses

Citation

Detail

段落导航
相关文章

/