基于改进支持向量域描述的道岔转辙机运行状态异常检测

王君臣; 徐田华; 陈聪

基于改进支持向量域描述的道岔转辙机运行状态异常检测

北京交通大学轨道交通控制与安全国家重点实验室, 北京 100044

基金项目:

北京市教委项目(I17H100010)

详细信息

作者简介:
王君臣,在读硕士研究生;徐田华,教授。

中图分类号: U284.72;TP39
计量
- 文章访问数: 70
- HTML全文浏览量: 0
- PDF下载量: 19
出版历程
- 收稿日期: 2018-09-02

Abnormal detection of switch machine operation state based on improved support vector domain description

State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing 100044, China

摘要

摘要: 针对铁路道岔转辙机缺乏大量异常样本来实施其运行状态异常检测的问题,提出了基于改进的支持向量数据域描述方法的异常检测模型。以ZYJ7型液压道岔转辙机为研究对象,利用既有微机监测系统采集道岔功率数据。用聚类的方法对数据进行清洗,接着对功率数据在时间序列上进行解锁、转换和锁闭分解,分别提取其统计特征值,采用主成分分析(PCA)法对特征值进行降维处理,将经过处理后的数据输入到异常检测分类器进行模型训练和模型测试。实验结果表明,改进的支持向量域描述(SVDD)分类器对道岔运行状态的异常检测有较强的识别能力。
- 液压转辙机 /
- 改进SVDD算法 /
- 异常检测 /
- 主成分分析
Abstract: In view of the problem that railway turnout switch machines lack a large number of abnormal samples to implement abnormal detection of their operation state, this paper proposed an improved model of abnormal detection based on improved support vector domain description. Taking ZYJ7 hydraulic turnout switch machine as the research object, the power data of turnout were collected by using the existing computer monitoring system. Clustering method was used to clean the power data, then unlock, transform and decompose the power data in time series. Statistical eigenvalues were extracted. Principal component analysis (PCA) method was used to reduce the dimension of the eigenvalues. The processed data were input to the abnormal detection classifier for model training and model testing. The experimental results show that the improved Support Vector Domain Description (SVDD) classifier has a strong recognition ability for abnormal detection of turnout operation state.
- hydraulic switch machine /
- improved support vector domain description(SVDD) algorithm /
- abnormal detection /
- principal component analysis

HTML全文

参考文献(13)

[1]	中华人民共和国铁道部. 铁路行车事故案例选编[M]. 北京:中国铁道出版社, 1999.
[2]	郭进. 铁路信号基础[M]. 北京:中国铁道出版社, 2010.
[3]	中华人民共和国铁道部. 铁路技术管理规程[M]. 北京:中国铁道出版社, 2006.
[4]	赵林海,陆桥. 基于灰关联的道岔故障诊断方法[J]. 铁道学报, 2014(2):69-74.
[5]	朱绪昌. 基于灰关联的道岔信号控制系统故障诊断方法及其实现研究[D]. 兰州:兰州交通大学, 2016.
[6]	Atamuradov V, Camci F, Baskan S, et al. Failure diagnostics for railway point machines using ex-pert systems[C]//IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives. IEEE, 2009:1-5.
[7]	杨阳. 神经网络和专家系统在道岔故障诊断中的应用研究[D]. 兰州:兰州交通大学, 2013.
[8]	薛艳青. 道岔设备故障诊断专家系统实现方法研究[D]. 北京:北京交通大学, 2012.
[9]	Kim H, Sa J, Chung Y, et al. Fault diagnosis of railway point machines using dynamic time warp-ing[J]. Electronics Letters, 2016, 52(10):818-819.
[10]	Lee J, Choi H, Park D, et al. Fault Detection and Diagnosis of Railway Point Machines by So-und Analysis[J]. Sensors, 2016, 16(4):549.
[11]	钟志旺,陈建译,唐涛,等. 基于SVD-D的道岔故障检测和健康评估方法研究[J]. 西南交通大学学报, 2018, 53(4):42-50.
[12]	Tax DMJ, Duin RPW. Support vector domain description[J]. Pattern Recognit Lett, 1999, 20(11-13):1191-1199.
[13]	范昕炜. 支持向量机算法的研究及其应用[D]. 杭州:浙江大学, 2003.