[1]雷文平,吴小龙,陈超宇,等.基于自动编码器和SVM的轴承故障诊断方法[J].郑州大学学报(工学版),2018,39(05):68-72.[doi:10.13705/j.issn.1671-6833.2018.05.013]
 Lei Wenping,Wu Xiaolong,Chen Chaoyu,et al.The Application of SVM Based on Auto-encoder in Bearing Fault Diagnosis[J].Journal of Zhengzhou University (Engineering Science),2018,39(05):68-72.[doi:10.13705/j.issn.1671-6833.2018.05.013]
点击复制

基于自动编码器和SVM的轴承故障诊断方法()
分享到:

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
39卷
期数:
2018年05期
页码:
68-72
栏目:
出版日期:
2018-08-21

文章信息/Info

Title:
The Application of SVM Based on Auto-encoder in Bearing Fault Diagnosis
作者:
雷文平 吴小龙陈超宇林辉翼
郑州大学机械工程学院振动工程研究所,河南郑州,450001
Author(s):
Lei Wenping Wu Xiaolong Chen Chaoyu Lin Huiyi
Institute of Vibration Engineering, School of Mechanical Engineering, Zhengzhou University, Zhengzhou, Henan 450001
关键词:
支持向量机自动编码器无监督特征提取经验模态分解信息熵故障诊断
Keywords:
Support Vector Machine Autoencoder Unsupervised Feature Extraction Empirical Mode Decomposition Information Entropy Fault Diagnosis
DOI:
10.13705/j.issn.1671-6833.2018.05.013
文献标志码:
A
摘要:
支持向量机(Support Vector Machine, SVM)应用于轴承故障诊断前,首先要提取轴承的特征信号。在以往的特征信号提取中,往往是依据已有的知识模型进行特征筛选。随着近年来深度神经网络(Deep Neural Network, DNN)的应用与推广,自动编码器(Auto-encoder, AE)在特征提取方面的优势尤为突出。作为一种无监督的学习方式,AE能够基于数据驱动地提取信号的特征值,使得特征提取不再依赖于先验知识,从而让整个故障诊断过程更具智能化。本文运用改进的AE、去噪自动编码器(denoising autoencoder,DAE),进行轴承信号特征提取,并用SVM进行故障诊断。最终与基于经验模态分解(empirical mode decomposition, EMD)能量熵的SVM对比,反应具有无监督学习方式的DAE-SVM在轴承故障诊断方面的优越性,诊断准确率接近100%。
Abstract:
The fault feature should be extracted before the SVM was applied to the bearing fault diagnosis. In the previous feature signal extraction, it was often based on the existing knowledge model. With the application and promotion of DNN in recent years, AE had a special advantage in feature extraction. As an unsupervised learning method, AE could extract the features of the signal based on data driven, making the feature extraction no longer depends on prior knowledge, and the whole fault diagnosis processed more intelligent. In this paper, the improved AE、DAE,were used to extract the features of the bearing signals, and the fault diagnosis was carried out by SVM. Finally, by compared with the SVM based on EMD energy entropy feature extraction, the superiority of DAE-SVM with unsupervised learning method was reflected in beraing fault diagnosis, and its diagnostic accuracy was neraly 100% 

相似文献/References:

[1]李蒙蒙,尚志刚,李志辉.结合投影与近邻操作的支持向量快速筛选方法[J].郑州大学学报(工学版),2017,38(03):49.[doi:10.13705/j.issn.1671-6833.2016.06.003]
 Li Mengmeng,Shang Zhigang,Li Zhihui.Fast Method to Filter Support Vectors Combined with Operation of Projection and Nearest Neighbors’ Selection[J].Journal of Zhengzhou University (Engineering Science),2017,38(05):49.[doi:10.13705/j.issn.1671-6833.2016.06.003]
[2]耿亚南,邓计才.基于人工鱼群优化SVM的声磁标签信号检测研究[J].郑州大学学报(工学版),2017,38(04):35.[doi:10.13705/j.issn.1671-6833.2017.04.001]
 Deng Jicai,Geng Yanan.Improved AFSA Optimization of SVM in The Application of Magnetic EAS Acoustic Signal Detection[J].Journal of Zhengzhou University (Engineering Science),2017,38(05):35.[doi:10.13705/j.issn.1671-6833.2017.04.001]
[3]曾庆山,宋庆祥,范明莉.基于光流共生矩阵的人群行为异常检测[J].郑州大学学报(工学版),2018,39(03):29.[doi:10.13705/j.issn.1671-6833.2017.06.032]
 Zeng Qingshan,Song Qingxiang,Fan Mingli.Detection of Human Behavior Anomaly Based on the Optical Flow Co-occurrence Matrix[J].Journal of Zhengzhou University (Engineering Science),2018,39(05):29.[doi:10.13705/j.issn.1671-6833.2017.06.032]
[4]王杰,姜念,张毅..SVM算法的区间自适应PSO优化及其应用[J].郑州大学学报(工学版),2011,32(01):75.[doi:10.3969/j.issn.1671-6833.2011.01.019]
[5]徐敏,袁建洲,刘四新,等.基于改进粒子群优化算法的短期风电功率预测[J].郑州大学学报(工学版),2012,33(06):32.[doi:10.3969/j.issn.1671-6833.2012.06.008]
[6]王杰,陈锴鹏..基于决策函数及PSO优化的SVM预测控制应用研究[J].郑州大学学报(工学版),2013,34(02):53.[doi:10.3969/j.issn.1671-6833.2013.02.014]

更新日期/Last Update: 2018-08-22