基于特征生成的轴承不均衡数据故障诊断

doi:10.16182/j.issn1004731x.joss.20-FZ0458

系统仿真学报 ›› 2020, Vol. 32 ›› Issue (12): 2438-2448.doi: 10.16182/j.issn1004731x.joss.20-FZ0458

• 仿真支撑平台/系统技术 • 上一篇下一篇

基于特征生成的轴承不均衡数据故障诊断

樊名鲁, 王艳, 纪志成

江南大学物联网技术应用教育部工程研究中心,江苏无锡 214122

收稿日期:2020-04-06 修回日期:2020-07-08 出版日期:2020-12-18 发布日期:2020-12-16
作者简介:樊名鲁(1996-),男,山东聊城,硕士生,研究方向为轴承故障诊断;王艳(1978-),女,江苏无锡,博士,教授,博导,研究方向为制造系统能效优化。
基金资助:
国家自然科学基金(61973138),国家重点研发计划(2018YFB1701903)

Fault Diagnosis for Bearings of Unbalanced Data Based on Feature Generation

Fan Minglu, Wang Yan, Ji Zhicheng

Engineering Research Center of Internet of Things Technology Applications Ministry of Education,Jiangnan University,Wuxi 214122,China

Received:2020-04-06 Revised:2020-07-08 Online:2020-12-18 Published:2020-12-16

摘要/Abstract

摘要： 针对实际生产中难以获得足量的故障样本数据导致训练中样本不均衡、样本不足等问题,提出了一种基于特征聚类的过采样算法,并将其与卷积神经网络相结合的滚动轴承故障诊断模型。该模型将频域信号作为模型的输入,通过卷积神经网络进行特征提取,再通过过采样技术生成新的特征数据实现数据的均衡化,将新生成的特征数据和原有特征一同输入到支持向量机(Support Vector Machine,SVM)分类器中完成样本的分类,实现滚动轴承的故障诊断。通过对比实验,结果表明该方法可以有效解决数据不均衡的问题。

关键词: 滚动轴承, 故障诊断, 特征生成, 卷积神经网络

Abstract: Focus on the sample imbalance and insufficiency caused by the difficulty to obtain a sufficient number of fault samples in actual production.A model for rolling bearings by combining Convolutional Neural Networks and Synthetic Oversampling is presented.The frequency domain signals is used as the input of the model,and the features are extracted by the Convolutional Neural Network.The new features are generated by Synthetic Oversampling and the data equalization is realized.The model completes the classification by putting all of the features into the Support Vector Machine,and the fault diagnosis of the rolling bearings is carried out.The comparison experiments results show that the method can effectively solve the problem of data imbalance.

Key words: rolling bearing, fault diagnosis, feature generation, convolutional neural network

中图分类号:

TP391.9

樊名鲁, 王艳, 纪志成. 基于特征生成的轴承不均衡数据故障诊断[J]. 系统仿真学报, 2020, 32(12): 2438-2448.

Fan Minglu, Wang Yan, Ji Zhicheng. Fault Diagnosis for Bearings of Unbalanced Data Based on Feature Generation[J]. Journal of System Simulation, 2020, 32(12): 2438-2448.

参考文献 18

[1]	阳建宏,黎敏,丁福焰.滚动轴承诊断现场实用技术[M].北京:机械工业出版社,2015.Yang Jianhong,Li Min,Ding Fuyan.Field Practical Technology of Rolling Bearing Diagnosis[M].Beijing:China Machine Press,2015.
[2]	Razavi-Far R,Farajzadeh-Zanjani M,Saif M.An Integrated Class-imbalanced Learning Scheme for Diagnosing Bearing Defects in Induction Motors[J].IEEE Transactions on Industrial Informatics,2017,13(6):2758-2769.
[3]	文成林,吕菲亚,包哲静,等.基于数据驱动的微小故障诊断方法综述[J].自动化学报,2016,42(9):1285-1299.Wen Chenglin,LüFeiya,Bao Zhejing,et al.A Review of Data Driven-based Incipient Fault Diagnosis[J].Acta Automatica Sinica,2016,42(9):1285-1299.
[4]	徐继亚,王艳,纪志成.基于鲸鱼算法优化WKELM的滚动轴承故障诊断[J].系统仿真学报,2017,29(9):2189-2197.Xu Jiya,Wang Yan,Ji Zhicheng.Fault Diagnosis Method of Rolling Bearing Based on WKELM Optimized by Whale Optimization Algorithm[J].Journal of System Simulation,2017,29(9):2189-2197.
[5]	王田田,王艳,纪志成.基于改进极限学习机的滚动轴承故障诊断[J].系统仿真学报,2018,30(11):4413-4420.Wang Tiantian,Wang Yan,Ji Zhicheng.Fault Diagnosis of Rolling Bearing Based on Improved Extreme Learning Machine[J].Journal of Vibration and Shock,2018,30(11):4413-4420.
[6]	任浩,屈剑锋,柴毅.深度学习在故障诊断领域中的研究现状与挑战[J].控制与决策,2017,32(8):1345-1358.Ren Hao,Qu Jinfeng,Chai Yi.Deep Learning for Fault Diagnosis:The State of the Art and Challenge[J].Control and Decision,2017,32(8):1345-1358.
[7]	Wen L,Li X,Gao L,et al.A New Convolutional Neural Network Based Data Driven Fault Diagnosis Method[J].IEEE Transactions on Industrial Electronics (S 1557-9948),2018,65(7):5990-5998.
[8]	Sun J,Yan C,Wen J.Intelligent Bearing Fault Diagnosis Method Combining Compressed Data Acquisition and Deep Learning[J].IEEE Transactions on Instrumentation and Measurement (S1557-9662),2018,67(1):185-195.
[9]	Guo L,Lei Y,Xing S,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 (S 1557-9948),2019,66(9):7316-7325.
[10]	王硕,王培良.基于一维卷积自编码器—高斯混合模型的间歇过程故障检测[J].信息与控制,2019,48(3):285-292.Wang Shuo,Wang Peiliang.Fault Detection Method for a Batch Process Based on a One dimensional Convolution Autoencoder and Gaussian Mixture Model[J].Information and Control,2019,48(3):285-292.
[11]	曲星宇,曾鹏,徐承成,等.基于DropOut降噪自编码的磨矿系统故障诊断[J].控制与决策,2018,33(9):1662-1666.Qu Xingyu,Zeng Peng,Xu Chengcheng,et al.DropOut Denoising Autoencoder-based Fault Diagnosis for Grinding System[J].Control and Decision,2018,33(9):1662-1666.
[12]	Oh H,Jung J H,Jeon B C,et al.Scalable and Unsupervised Feature Engineering using Vibration- imaging and Deep Learning for Rotor System Diagnosis[J].IEEE Transactions on Industrial Electronics (S1557-9948),2018,65(4):3539-3549.
[13]	Jiao W,Lin S.Overall-improved Fault Diagnosis Approach Based on Support Vector Machine[J].Chinese Journal of Scientific Instrument (S0254-3087),2015,36(8):1861-1870.
[14]	Zhang Y Y,Li X Y,Gao L,et al.Imbalanced Data Fault Diagnosis of Rotating Machinery using Synthetic Oversampling and Feature Learning[J].Journal of Manufacturing Systems (S0278-6125),2018,48(4):34-50.
[15]	Hang Q,Yang J,Xing L.Diagnosis of Rolling Bearing Based on Classification for High Dimensional Unbalanced Data[J].IEEE Access (S2169-3536),2019,7(9):79159-79172.
[16]	Hassani H,Zarei J,Arefi M M,et al.Zslices-based General Type-2 Fuzzy Fusion of Support Vector Machines with Application to Bearing Fault Detection[J].IEEE Transactions on Industrial Electronics (S1557-9948),2017,64(9):7210-7217.
[17]	LeCun Y,Bengio Y,Hinton G.Deep learning[J].Nature (S1476-4687),2015,521(7553):436-444.
[18]	Chawla N V,Bowyer K W,Hall L O,et al.SMOTE:Synthetic Minority Over-sampling Technique[J].Journal of Artificial Intelligence Research (S1076-9757),2002,16(1):321-357.

基于特征生成的轴承不均衡数据故障诊断

Fault Diagnosis for Bearings of Unbalanced Data Based on Feature Generation

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 18

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张立峰, 王会忍. 基于卷积神经网络及有限元仿真的电容层析成像图像重建[J]. 系统仿真学报, 2022, 34(4): 712-718.
[2]	敖邦乾, 杨莎, 令狐金卿, 叶振环. 基于级联神经网络疲劳驾驶检测系统设计[J]. 系统仿真学报, 2022, 34(2): 323-333.
[3]	祝志超, 吴定会, 岳远昌. 基于监督核熵成分分析的发动机磨损故障诊断[J]. 系统仿真学报, 2022, 34(1): 45-52.
[4]	李元, 耿泽伟. 基于LLE与K均值聚类算法的工业过程故障诊断[J]. 系统仿真学报, 2021, 33(9): 2066-2073.
[5]	王印松, 孙天舒. 基于二分类NMF网络的执行器故障状态评估[J]. 系统仿真学报, 2021, 33(8): 1882-1891.
[6]	位晶晶, 刘勤明, 叶春明, 李冠林. 基于GA-SVR的小样本数据缺失下的设备故障诊断[J]. 系统仿真学报, 2021, 33(6): 1342-1349.
[7]	赵瑛, 陆耀, 张健, 梁启弟, 龙炜. 基于深度神经网络的多视角人体动作识别[J]. 系统仿真学报, 2021, 33(5): 1019-1030.
[8]	吴定会, 祝志超, 韩欣宏. 基于BO-SDAE多源信号的风电机组轴承故障诊断[J]. 系统仿真学报, 2021, 33(5): 1148-1156.
[9]	仝卫国, 庞雪纯, 朱赓宏. 基于卷积神经网络的气液两相流流型识别方法[J]. 系统仿真学报, 2021, 33(4): 883-891.
[10]	马榕, 陈秋瑞, 张晗, 梅铮, 王锐, 魏伟. 基于单目深度估计的低功耗视觉里程计[J]. 系统仿真学报, 2021, 33(12): 3001-3011.
[11]	黄欣, 方钰, 顾梦丹. 基于卷积神经网络的X线胸片疾病分类研究[J]. 系统仿真学报, 2020, 32(6): 1188-1194.
[12]	李炜, 周丙相, 蒋栋年. 基于深度学习序贯检验的电源车故障诊断方法[J]. 系统仿真学报, 2020, 32(4): 638-648.
[13]	王红军, 黎邹邹, 邹湘军. 基于Adaboost与CNN的木材表面缺陷检测[J]. 系统仿真学报, 2019, 31(8): 1636-1645.
[14]	李炜, 葛振福, 申富媛, 龚建兴. 基于FDRE的3D威亚编码器故障检测与容错控制[J]. 系统仿真学报, 2019, 31(4): 740-749.
[15]	卢裕秋, 孙金玉, 马世伟. 基于深度卷积神经网络的运动目标检测方法[J]. 系统仿真学报, 2019, 31(11): 2275-2280.