基于非平衡数据的车辆轮对状态集成分类方法

doi:10.3969/j.issn.0258-2724.2017.05.003

基金项目:

广东省科技厅科技项目（2013498A）

详细信息

作者简介:
敖银辉(1973-),男,教授,博士,研究方向为机电设备检测和故障诊断,电话:13543407579,E-mail:aoyinhui@gdut.edu.cn

计量
- 文章访问数:596
- HTML全文浏览量:122
- PDF下载量:71
- 被引次数:0
出版历程
- 收稿日期:2016-08-24
- 刊出日期:2017-10-25

Integrated Classification Method for Vehicle Wheel-set Condition Based on Imbalanced Datasets

摘要

摘要:针对地铁车辆轮轨振动信号信噪比低、非线性、非平稳等特点，为实现平轮故障的不解体检测诊断，提出了一种基于非平衡数据的集成分类器模型.以踏面正常、踏面擦伤、踏面剥离和圆周磨耗四种典型的平轮故障为研究对象，对采集的轮轨振动信号进行变分模态分解与模糊熵特征提取，构造故障特征数据集；通过偏置支持向量机筛选训练集中的支持向量样本并进行SMOTE（synthetic minority oversampling technique）过采样，对非支持向量进行分层组合并构造集成分类器，采用有向无环图的方式对测试集进行平轮故障识别；最后，通过查全率和查准率对比分析，给出多类非平衡数据集的分类性能评价.论文在车辆段轨旁进行了空载分类试验，实验结果表明，所提出的方法对4种定性模式障的识别准确率超过96%，可被有效应用于地铁车辆的平轮故障诊断.
- 平轮故障/
- 变分模态分解/
- 特征提取/
- 支持向量机/
- 故障诊断
Abstract:The wheel-rail vibration signal of a metro vehicle has the characteristics of being non-linear, non-stationary, and a low value of signal-to-noise ratio. The paper proposes an integrated classifier model based on the imbalanced datasets to achieve the disassembly detection and fault diagnosis of wheel flats. Four typical wheel flat faults, namely tread normal, tread scratch, tread peeling, and circumference wear were studied in the research. Feature extraction of signals was performed by incorporating the variational mode decomposition and fuzzy entropy. Fault datasets were constructed and support vector samples were filtered by employing the bias support vector machines. SMOTE (synthetic minority oversampling technique) oversampling was applied and non-support vector samples were combined. An integrated classifier was then built by incorporating the directed acyclic graph for the fault identification. Finally, the study analyzed the precision and recall ratios to evaluate the classification performance of an integrated classifier the. Experiments were conducted at a depot under no load running test. The experimental results show that the proposed method can achieve over 96% of accuracy for the given 4 fault models, which can be effectively employed in the wheel flat faults diagnosis for the metro vehicles.
- wheel flat fault/
- variational mode decomposition/
- feature extraction/
- support vector machines/
- fault diagnosis

HTML全文

参考文献 (13)

李奕璠,林建辉,刘建新,等. 车轮踏面擦伤识别方法[J]. 振动与冲击,2013,32(22):21-27. LI Yifan, LIN Jianhui, LIU Jianxin, et al. Edentification method of wheel tread flat[J]. Journal of Vibration and Shock, 2013, 32(22):21-27.

孙永奎,余志斌,金炜东. 基于多重分形与SVM的高速列车运行状态识别方法[J]. 江南娱乐网页版入口官网下载安装学报,2015,50(1):7-12. SUN Yongkui, YU Zhibin, JIN Weidong. Recognizing running state of high-speed trains based on multifractal theory and SVM[J]. Journal of Southwest Jiaotong Vniversity, 2015, 50(1):7-12

王雪,付振波. 采用小波分析与支持向量机的车轮踏面擦伤识别方法[J]. 中国机械工程,2004,15(18):45-47. WANG Xue, FU Zhenbo. A new method of wavelet and suport vector machine for detection of the train wheel bruise[J]. China Mechanical Engineering, 2004, 15(18):45-47.

KUBAT M, MATWIN S. Addressing the curse of imbalanced training sets:one-sided selection[C]//Proceedings of the Fourteenth International Conference on Machine Learning. Nashville:[s.n.], 1997:179-186.

CHAWLA N V, BOWYER K W, HALL L O, et al. SMOTE:synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research, 2011, 16(1):321-357.

LIU Y, YU X, HUANG J X, et al. Combining integrated sampling with SVM ensembles for learning from imbalanced datasets[J]. Information Processing & Management, 2011, 47(4):617-631.

VEROPOULOS K, CAMPBELL C, CRISTIANINI N. Controlling the sensitivity of support vector machines[C]//Proceedings of the International Joint Conference on Artificial Intelligence. Bristol:[s.n.], 1999:55-60.

WANG Y, MARKERT R, XIANG J, et al. Research on variational mode decomposition and its application in detecting rub-impact fault of the rotor system[J]. Mechanical Systems & Signal Processing, 2015, 60:243-251.

CHEN W, ZHUANG J W, WANG Z. Measuring complexity using FuzzyEn, ApEn, and SampEn.[J]. Medical Engineering & Physics, 2009, 31(1):61-68.

石敏,李影,王冰,等. 基于变分模态分解的齿轮箱故障诊断[J]. 电力科学与工程,2016,32(1):23-26. SHI Min, LI Ying, WANG Bing, et al. Gearbox fault diagnosis based on variational mode decomposition.[J]. Electric Power Science and Engineering, 2016, 32(1):23-26.

季艳. 基于DEMD时频分析的旋转机械故障特征提取方法研究[D]. 秦皇岛:燕山大学,2015.

丁福利,孙立民. 基于支持向量机的不平衡样本分类研究[J]. 科学技术与工程,2014,14(3):81-85. DING Fuli, SUN Limin. Unbalanced sample set classification based on support vector machine[J]. Science Technology and Engineering, 2014, 14(3):81-85.

NAIWALA P C, KAZUNARI N, AKIRA I. Driving skill classification in curve driving scenes using machine learning[J]. Journal of Modern Transportation, 2016, 9(24):196-206.

施引文献

附加材料 (0)

访问统计

点击查看大图

计量

文章访问数:596
HTML全文浏览量:122
PDF下载量:71
被引次数:0