计算机科学 ›› 2016, Vol. 43 ›› Issue (12): 281-286.doi: 10.11896/j.issn.1002-137X.2016.12.052

• 智能应用 • 上一篇    下一篇

基于EDBN-SVM的高速列车故障分析

郭超,杨燕,金炜东   

  1. 西南交通大学信息科学与技术学院 成都611756,西南交通大学信息科学与技术学院 成都611756,西南交通大学电气工程学院 成都611756
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家自然科学基金项目(61134002,61572407)资助

Fault Analysis of High Speed Train Based on EDBN-SVM

GUO Chao, YANG Yan and JIN Wei-dong   

  • Online:2018-12-01 Published:2018-12-01

摘要: 深度学习作为机器学习领域的新热点,为故障诊断技术领域的研究开拓了新的思路。针对高速列车进行故障分析的重要性,将深度学习和集成学习相结合,提出一种基于EDBN-SVM(EnsembleDeep Belief Network-Support Vector Machine)的故障诊断模型。首先对高速列车振动信号进行快速傅立叶变换,其次分析确定了EDBN-SVM模型的参数,然后将信号的FFT系数作为EDBN-SVM模型的可视层输入,并逐层学习高层特征,最后利用多个SVM分类器进行识别并对识别结果进行集成。为评估该方法的有效性,采用实验室数据和仿真数据进行实验测试,并与传统的几种故障分析方法进行对比。结果表明,该方法的故障识别效果优于传统的故障分析方法,同时稳定性更好。

关键词: 高速列车,故障分析,快速傅立叶变换,深度信念网络

Abstract: As a new hot spot in the field of machine learning,deep learning has opened up new ideas for the research of fault diagnosis.In view of significance of fault analysis for high speed train,combining deep learning and ensemble lear-ning,a new fault diagnosis model based on EDBN-SVM(Ensemble Deep Belief Network-Support Vector Machine)was proposed.Firstly,we preprocessed the vibration signal of high speed train by fast fourier transform (FFT).Secondly,we analyzed the parameters of the EDBN-SVM model,then we set the FFT coefficients as the input of the visible layer of EDBN-SVM model,and used the model to learn high-level features layer by layer.Finally,we utilized multiple SVM classifiers to recognize faults,and combined the recognition results.In order to evaluate the validity of this method,we selected the laboratory data and the simulation data to conduct experiments,and compared it with the traditional fault analysis methods.The results show that the fault recognition effect and the stability of this method are better than traditional methods.

Key words: High speed train,Fault analysis,Fast Fourier transform,Deep belief network

[1] Garcia C,Lehner A,Strang T,et al.Comparison of collisionavoidance systems and applicability to rail transport[C]∥Proceedings of the 7th International Conference on Intelligent Transport Systems.France:Sophia Antipolis,2007:1-6
[2] Huang Cai-lun,Fan Xiao-ping,Chen Chun-yang,et al.Fault diag-nosis method of locomotive driven gear based on envelopment analysis of wavelet coefficients extraction and DCT[J].Journal of the China Railway Society,2008,30(2):98-102(in Chinese) 黄采伦,樊晓平,陈春阳,等.基于小波系数提取及离散余弦包络分析的机车牵引齿轮故障诊断方法[J].铁道学报,2008,30(2):98-102
[3] Lei Ya-guo,He Zheng-jia,Zi Yan-yang.Application of the EEMD method to rotor fault diagnosis of rotating machinery[J].Mechanical Systems and Signal Processing,2009,23(4):1327-1338
[4] Qin Na,Jin Wei-dong,Huang Jin,et al.High speed train bogie fault signal analysis based on wavelet entropy feature[J].Advanced Materials Research,2013,3(12):2286-2289
[5] Chen Yun-feng,Wang Hong-jun,Yang Yan.Fault diagnosis of high-speed rail based on clustering ensemble[J].Computer Scien-ce,2015,42(6):233-238(in Chinese) 陈云风,王红军,杨燕.基于聚类集成的高铁故障诊断分析[J].计算机科学,2015,42(6):233-238
[6] Li Zhi-chun.A Simple SOM neural network based fault detection model for fault diagnosis of rolling rearings[J].Applied Mechanics and Materials,2013,397:1321-1325
[7] Zhao Jing-jing,Yang Yan,Li Tian-rui,et al.Fault diagnosis of high-speed rail based on approximate entropy and empirical mode decomposition[J].Computer Science,2014,41(1):91-94(in Chinese) 赵晶晶,杨燕,李天瑞,等.基于近似熵及EMD的高铁故障诊断[J].计算机科学,2014,41(1):91-94
[8] Sun Zhi-jun,Xue Lei,Xu Yang-ming,et al.Overview of deep lea-ring[J].Application Research of Computer,2012,9(8):2806-2810(in Chinese) 孙志军,薛磊,许阳明,等.深度学习研究综述[J].计算机应用研究,2012,29(8):2806-2810
[9] Guo Li-li,Ding Shi-fei.Research progress on deep learning[J].Computer Science,2015,42(5):28-33(in Chinese) 郭丽丽,丁世飞.深度学习研究进展[J].计算机科学,2015,42(5):28-33
[10] Hinton G,Osindero S,Teh Y.A fast learning algorithm for deep belief nets[J].Neural Computation,2006,18(7):1527-1554
[11] Roux N L,Bengio Y.Representational power of restricted boltzmann machines and deep belief networks[J].Neural Computation,2008,20(6):1631-1649
[12] Mohamed A,Dahl G,Hinton G.Acoustic modeling using deep belief networks[J].IEEE Transactions on Audio,Speech,and Language Processing,2012,20(1):14-22
[13] Ranzato M,Huang F,Boureau Y,et al.Unsupervised learning of invariant feature hierarchies with applications to object recognition[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.USA:IEEE,2007:1-8
[14] Xie Ji-peng,Yang Yan,Li Tian-rui,et al.Learning features from high speed train vibration signals with deep belief networks[C]∥Proceedings of the International Joint Conference on Neural Networks (IJCNN).USA:IEEE,2014:2205-2210
[15] Lee H,Grosse R,Ranganath R,et al.Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations[C]∥Proceedings of the International Conference on Machine Learning.USA:ACM,2009:609-616
[16] Hansen L,Salamon P.Neural network ensembles[J].IEEETransactions on Pattern Analysis and Machine Intelligence.1990,12(10):993-1001
[17] Pang S,Kim D,Bang S.Fraud detection using support vectormachineensemble[C]∥Proceedings of the 8th International Conference on Neural Information Processing.Shanghai:Fudanuniversity,2001:1344-1349
[18] Dong Y,Han K.A comparison of several ensemble methods for text categorization[C]∥Proceedings of the International Con-ference on Services Computing(SCC).USA:IEEE,2004:419-422
[19] Hinton G.Training products of experts by minimizing contrastive divergence[J].Neural Computer,2002,14(8):1771-1800
[20] Carreira-Perpinan M,Hinton G.On contrastive divergence lear-ning.http://www.doc88.comIP-747820956400.html
[21] Yang Su-hong.A voting statistical method of group decision [C]∥Proceedings of the International Joint Conference on Computational Sciences and Optimization (CSO 2009).USA:IEEE,2009:873-875
[22] Tanaka M,Okutomi M.A Novel Inference of a Restricted Boltzmann Machine[C]∥Proceedings of the 22th International Conference on Pattern Recognition (ICPR).USA:IEEE,2014:1526-1531
[23] Wang Lei,Ji Guo-yi.Fault diagnosis of rotor system based on EMD fuzzy entropy and SVM[J].Noise and Vibration Control,2012,2(3):171-176(in Chinese) 王磊,纪国宜.基于EMD模糊熵和SVM的转子系统故障诊断[J].噪声与振动控制,2012,32(3):171-176

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!