基于多重分形与SVM的高速列车运行状态识别方法

孙永奎; 余志斌; 金炜东

doi:10.3969/j.issn.0258-2724.2015.01.002

基于多重分形与SVM的高速列车运行状态识别方法

doi: 10.3969/j.issn.0258-2724.2015.01.002

基金项目:

国家自然科学基金资助项目(61134002)

中央高校基本科研业务费专项资金资助项目(2682014CX029,SWJTU09BR056)

详细信息

作者简介:
孙永奎(1972-), 男, 讲师, 博士, 研究方向为智能信息处理、模式识别, E-mail: yksun@swjtu.edu.cn

计量
- 文章访问数: 1176
- HTML全文浏览量: 113
- PDF下载量: 623
- 被引次数: 34
出版历程
- 收稿日期: 2013-06-18
- 刊出日期: 2015-02-25

Recognizing Running State of High-Speed Trains Based on Multifractal Theory and SVM

摘要

摘要: 为了评估高速列车服役性态问题,提出基于多重分形与支持向量机(SVM)的高速列车状态识别新方法.该方法计算了高速列车振动信号的多重分形谱,分析了多重分形谱参数与列车状态之间的关联关系,提取了多重分形谱宽度、分形维数差和谱偏斜度作为高速列车状态的特征,使用支持向量机来对高速列车状态进行识别.获取了某型列车的正常状态、抗蛇行减震器失效、空簧失效3种典型的多重分形特征,训练了不同速度下的SVM和单一速度为160 km/h的SVM,并进行了工况识别实验.所提方法对高速列车的状态识别率大于88.8%,表明了该方法的有效性.
- 高速列车 /
- 状态识别 /
- 多重分形谱 /
- 支持向量机
Abstract: In order to evaluate in-service performances of high-speed trains, a novel approach to recognize the running state of high-speed trains was proposed using the multifractal theory and the support vector machine (SVM). The relationship between the multifractal spectrum parameters and the train running states was analyzed after the multifractal spectrum of the vibration signal was calculated by multifractal theory. Then, high-speed train running states were identified by SVM, using the characteristics of the multifractal spectrum width, the fractal dimension difference, and the spectrum skewness. In addition, a recognition experiment was carried out for three typical conditions of a certain type train, including the normal condition, the anti-hunting damper malfunction, and the air spring damper malfunction, after the SVM with different velocities and the SVM with a velocity (160 km/h) were trained using their multifratal characteristics. As a result, a state recognition accuracy of more than 88.8% was obtained, which verified the effectiveness of the proposed method.
- high-speed train /
- state recognition /
- multifractal spectrum /
- support vector machine

HTML全文

参考文献(38)

张卫华,王伯铭. 中国高速列车的创新发展

[J]. 机车电传动,2010,1(1): 8-12,69. ZHANG Weihua, WANG Boming. Innovation and development of high-speed railway in China

[J]. Electric Drive for Locomotives, 2010, 1(1): 8-12, 69.

金学松,郭俊,肖新标, 等. 高速列车安全运行研究的关键科学问题

[J]. 工程力学,2009,26(增刊Ⅱ): 8-22,105. JIN Xuesong, GUO Jun, XIAO Xinbiao, Key scientific problems in the study on running safety of high speed trains

[J]. Engineering Mechanics, 2009, 26(Sup. Ⅱ): 8-22, 105.

罗仁,曾京,戴焕云,等. 高速列车车轮磨耗预测仿真

[J]. 摩擦学学报,2009,29(6): 551-558. LUO Ren, ZENG Jing, DAI Huanyun, et al. Simulation on wheel wear prediction of high-speed train

[J]. Tribology, 2009, 29(6): 551-558.

黄照伟,崔大宾,杜星,等. 车轮偏磨对高速列车直线运行性能的影响

[J]. 铁道学报,2013,35(2): 14-20. HUANG Zhaowei, CUI Dabin, DU Xing, et al. Influence of deviated wear of wheel on performance of high-speed train running on straight tracks

[J]. Journal of the China Rail Way Society, 2013, 35(2): 14-20.

罗仁,曾京. 列车系统蛇行运动稳定性分析及其与单车模型的比较

[J]. 机械工程学报,2008,25(4): 184-188. LUO Ren, ZENG Jing. Hunting stability analysis of train system and comparison with single vehicle model

[J]. Chinese Journal of Mechanical Engineering, 2008, 25(4): 184-188.

史红梅,余祖俊,周佳亮. 不同线路条件及运行速度下高速列车振动性能分析

[J]. 北京交通大学学报,2012,36(1): 112-116. SHI Hongmei, YU Zujun, ZHOU Jialiang. Vibration analysis of high-speed vehicles under the conditions of various speed and lines

[J]. Journal of Beijing Jiaotong University, 2012, 36(1): 112-116.

陆啸秋,赵红卫,黄志平,等. 高速列车运行安全监控技术

[J]. 铁道机车车辆,2011,31(2): 34-37,81. LU Xiaoqiu, ZHAO Hongwei, HUANG Zhiping, et al. High-speed train running safety monitoring technology

[J]. Railway Locomotive Car, 2011, 31(2): 34-37, 81.

张兵. 列车关键部件安全监测理论与分析研究. 成都:西南交通大学,2008.

戴津,刘峰,董孝卿,等. 基于同一转向架历史对比与同一列车横向对比的转向架状态监测

[J]. 铁道机车车辆,2010,30(2): 26-29,37. DAI Jin, LIU Feng, DONG Xiaoqing, et al. Bogie condition monitoring based on comparing historical date of one bogie and date of all bogies in one train

[J]. Railway Locomotive Car, 2010, 30(2): 26-29, 37.

SAHOO P, BARMAN T, DAVIM J P. Fractal analysis in machining

[M]. New York: Springer, 2011: 20-42.

YANG J, ZHANG Y, ZHU Y. Intelligent fault diagnosis of rolling element bearing based on SVMs and fractal dimension

[J]. Mechanical Systems and Signal Processing, 2007, 21(5): 2012-2024.

CRISTIANINI N, SHAWE-TAYLOR J. An introduction to support vector machines and other kernel-based learning mechods

[M]. 北京: 电子工业出版社,2000: 82-97.

孙霞,吴自勤,黄畇. 分形原理及其应用

[M]. 合肥:中国科学技术大学出版社,2003: 53-74.

曾京,罗仁. 考虑车体弹性效应的铁道客车系统振动分析

[J]. 铁道学报,2007,29(6): 19-25. ZENG Jing, LUO Ren. Vibration analysis of railway passenger car systems by considering flexible carbody effect

[J]. Journal of the China Railway Society, 2007, 29(6): 19-25.

CHANG C C, LIN C J. LIBSVM: a library for support vector machines

[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3): 1-27.

施引文献

期刊类型引用(15)

1.	贾宝新，翟紫薇，张晶，周志扬，苑文雅，郑克楠. 基于高阶局部最大值同步挤压变换的浅埋隧道地表高铁振动信号时频与衰减特征分析. 岩土力学. 2025(01): 337-352 . 百度学术
2.	李权福，夏惠兴，华洪斌，王志军，姚伟. 铁路货车车辆转向架无源无线振动传感与监测系统. 铁道车辆. 2023(01): 124-130 . 百度学术
3.	卢昌宏，张利斌，张恒志，牟柏源，邹益胜. 一种多通道信息融合的横向减振器性能退化阶段辨别方法. 铁道科学与工程学报. 2021(03): 737-743 . 百度学术
4.	杨欣薇，朱松青，杨柳，薛宇豪，祝子昊. 城轨门系统承载传动机构健康状态评估研究. 南京工程学院学报(自然科学版). 2021(02): 45-53 . 百度学术
5.	杨欣薇，朱松青，杨柳，高海涛，平冠群，李昌磊. 基于EMD-SVM的列车门系统承载传动机构故障诊断技术研究. 现代制造工程. 2021(09): 87-93 . 百度学术
6.	张血琴，高润明，郭裕钧，康永强，李院生，吴广宁. 基于高光谱的复合绝缘子电晕老化状态评估. 西南交通大学学报. 2020(02): 442-449 . 本站查看
7.	赵莉华，张振东，刘浩，吴晓文，黄小龙. 基于多重分形-贝叶斯融合算法的变压器绕组机械状态识别. 电测与仪表. 2020(14): 45-50+118 . 百度学术
8.	王晓东，宁静，陈春俊. 1D CNN和LSTM高速列车横向稳定性状态识别研究. 中国测试. 2020(11): 25-30 . 百度学术
9.	冉伟，宁静，陈杨，陈春俊. 基于EEMD-SVD-LTSA的高速列车蛇行演变特征提取框架. 电子测量技术. 2019(05): 1-5 . 百度学术
10.	叶运广，宁静，种传杰，崔万里，陈春俊. 高速列车转向架蛇行失稳的MEEMD-LSSVM预测模型. 铁道学报. 2018(01): 38-43 . 百度学术
11.	王星，符颖，陈游，周一鹏，呙鹏程. 基于多重分形和半监督EM的LPI雷达信号识别. 控制与决策. 2018(11): 1941-1949 . 百度学术
12.	刘棋，宁静，叶运广，陈春俊. 基于EEMD能量熵的高速列车蛇行诊断研究. 中国测试. 2017(05): 96-100 . 百度学术
13.	敖银辉，黄晓鹏，袁敏正，陈希隽，方恩权. 基于非平衡数据的车辆轮对状态集成分类方法. 西南交通大学学报. 2017(05): 852-858 . 本站查看
14.	付小利，王晓乐，吕乾勇，金炜东. 并行化的高速列车运行状态评估. 计算机工程与设计. 2016(07): 1970-1974 . 百度学术
15.	庞荣，余志斌，熊维毅，李辉. 基于深度学习的高速列车转向架故障识别. 铁道科学与工程学报. 2015(06): 1283-1288 . 百度学术