• ISSN 0258-2724
  • CN 51-1277/U
  • EI Compendex
  • Scopus 收录
  • 全国中文核心期刊
  • 中国科技论文统计源期刊
  • 中国科学引文数据库来源期刊

基于改进SBELM的耦合故障诊断方法

叶青,  刘长华,  潘昊

downloadPDF
文章导航 > 西南交通大学学报  > 2016 >  29(4): 792-799.
叶青, 刘长华, 潘昊. 基于改进SBELM的耦合故障诊断方法[J]. 西南交通大学学报, 2016, 29(4): 792-799. doi: 10.3969/j.issn.0258-2724.2016.04.026
引用本文: 叶青, 刘长华, 潘昊. 基于改进SBELM的耦合故障诊断方法[J]. 西南交通大学学报, 2016, 29(4): 792-799. doi: 10.3969/j.issn.0258-2724.2016.04.026
shu
YE Qing, LIU Changhua, PAN Hao. Simultaneous Fault Diagnosis Method Based on Improved Sparse Bayesian Extreme Learning Machine[J]. Journal of Southwest Jiaotong University, 2016, 29(4): 792-799. doi: 10.3969/j.issn.0258-2724.2016.04.026
Citation: YE Qing, LIU Changhua, PAN Hao. Simultaneous Fault Diagnosis Method Based on Improved Sparse Bayesian Extreme Learning Machine[J]. Journal of Southwest Jiaotong University, 2016, 29(4): 792-799. doi: 10.3969/j.issn.0258-2724.2016.04.026
shu

基于改进SBELM的耦合故障诊断方法

doi: 10.3969/j.issn.0258-2724.2016.04.026
基金项目: 

国家自然科学基金资助项目(70701013)

广西省科学研究与技术开发计划资助项目(2013F020202)

详细信息
    作者简介:

    叶青(1983-),女,讲师,博士,研究方向为智能方法,E-mail:yq0712@163.com

Simultaneous Fault Diagnosis Method Based on Improved Sparse Bayesian Extreme Learning Machine

    摘要
  • 摘要: 为了对主减速器的耦合故障进行识别,通过对振动信号经过集成经验模态分解(ensemble empirical mode decomposition, EEMD)所获得的高频分量采用自适应阈值降噪和对低频分量采用区间阈值降噪,有效去除了信号噪声,创建了配对多标签分类策略(paired multi-label classification,PMLC).基于PMLC和稀疏贝叶斯极限学习机(sparse Bayesian extreme learning machine, SBELM)用单故障样本构造概率分类器集,再采用网格搜索方法生成最优决策阈值,将分类器集的概率输出转换为耦合故障模式,提出了基于自适应区间阈值降噪和SBELM的耦合故障诊断方法,并用主减速器的实际样本集验证了该方法的性能.研究结果表明:该方法的诊断精确度达到96.1%,比基于PNN(probability neural networks)和SVM(support vector machine)的诊断方法提高了5%;该方法的训练时间和执行时间为131.4和61.3 ms,比基于SVM的诊断方法减少了70%.

     

    Abstract: In order to identify simultaneous faults of the main reducer, an adaptive threshold denoising was adopted for intrinsic mode functions (IMFs) with high frequency and an interval threshold denoising was adopted for IMFs with low frequency, which are obtained from ensemble empirical mode decomposition (EEMD) of vibration signal, to eliminate noises. Then, a paired multi-label classification (PMLC) strategy was established, and probability classifiers based on PMLC and sparse Bayesian extreme learning machine (SBELM) were constructed with single fault samples; an optimal decision threshold was generated by using the grid searching method to convert the probability output obtained from classifiers into final simultaneous fault modes. On this basis, a simultaneous fault diagnosis (SFD) method based on adaptive threshold de-noising and SBELM was proposed. Its performance was verified using real samples of the main reducer. The experiment results show that the diagnostic accuracy of the method is 96.1%, which is 5% higher than that of methods based on probabilistic neural network (PNN) and support vector machine (SVM); its training time and execution time are 131.4 and 61.3ms, respectively, approximately 70% shorter than those of the method based on SVM.

     

    • HTML全文
    • 参考文献(13)
  • ZHANG Xiaoyuan, ZHOU Jianzhong. Multi-fault diagnosis for rolling element bearings based on ensemble empirical mode decomposition and optimized support vector machines[J]. Mechanical Systems and Signal Process, 2013, 41(1):127-140.
    HUANG Guangbin, ZHU Qinyu, SIEW C K. Extreme learning machine:theory and applications[J]. Neurocomputing, 2006, 70(1/2/3):489-501.
    EMILIO S O, JUAN G S. BELM:Bayesian extreme learning machine[J]. IEEE Transactions on Neural Networks, 2011, 22(3):505-509.
    LUO Jiahua, VONG C M, WONG P K. Sparse Bayesian extreme learning machine for multi-classification[J]. IEEE Transactions on Neural Networks and Learning Systems, 2014, 25(4):1202-1217.
    PLATT J, CRISTIANINI N. Large margin DAGs for multiclass classification[C]//Advances in Neural Information Processing Systems A Solla. Cambridge:The MIT Press. 2000,12:547-553.
    KOPSINIS Y, STEPHEN M L. Development of EMD-based denoising methods inspired by wavelet thresholding[J]. IEEE Transactions on Signal Processing, 2009, 57:1351-62.
    韩刚,张建文,褚鑫. 基于EEMD自适应阈值去噪的电能质量扰动检测与定位研究[J]. 电测与仪表,2014,51(2):45-57.HAN Gang, ZHANG Jianwen, ZHU Xin. Research on denoising of power quality disturbance detection and location based on EEMD adaptive thresholding[J]. Electrical Measurement and Instrumentation, 2014, 51(2):45-57.
    WU T F, LIN C J, WENG R C. Probability estimates for multi-class classification by pairwise coupling[J]. Journal of Machine Learning Research, 2004, 5:975-1005.
    SCHWENKER F. Hierarchical support vector machines for multi-class mode recognition[C]//Procedings of the 4th International Conference on Knowledge-Based Intelligent Engineering System and Allied Techologies. Los Alamitos:IEEE Computer Society Press, 2000:561-565.
    VONG C M, WONG P K, IP W F. A new framework of simultaneous-fault diagnosis using pairwise probabilistic multi-label classification for time-dependent modes[J]. IEEE Transaction on Industrial Electronics, 2013, 60(8):3372-3385.
    HUANG Guangbin, ZHOU Hongming, DING Xiaojian, et al. Extreme learning machine for regression and multiclass classification[J]. IEEE Transactions on Systems, Man, and Cybernetics, 2012, 42(2):513-529.
    KONAR P, CHATTOPADHYAY P. Bearing fault detection of induction motor using wavelet and support vector machines (SVMs)[J]. Applied Soft Computing, 2011, 11(1):4203-4211.
    YATES R B, NETO B R. Modern information retrieval[M]. Bergen Conuty:Pearson Education Inc., 1999:544.
    • 相关文章
    • 施引文献
  • 附加材料(0)
  • 加载中
WeChat 点击查看大图
计量
  • 文章访问数:  582
  • HTML全文浏览量:  73
  • PDF下载量:  216
  • 被引次数: 0
出版历程
  • 收稿日期:  2015-01-13
  • 刊出日期:  2016-08-25

目录

    /

    返回文章
    返回

    Copyright © 2009 西南交通大学学报

    地址：四川省成都市郫都区犀安路999号西南交通大学犀浦校区《西南交通大学学报》编辑部

    电话：028-66367562传真：028-66366552Email：xbz@home.swjtu.edu.cn

    本系统由 北京仁和汇智信息技术有限公司 开发 技术支持： info@rhhz.net