基于DTW的车辆轴温监测方法

曹源; 王玉珏; 马连川; 陈磊

doi:10.19818/j.cnki.1671-1637.2015.03.009

基于DTW的车辆轴温监测方法

doi: 10.19818/j.cnki.1671-1637.2015.03.009

曹源^{1, 2,},
王玉珏²,
马连川^{1, 2},
陈磊³

1.
北京交通大学轨道交通运行控制系统国家工程研究中心，北京 100044
2.
北京交通大学电子信息工程学院，北京 100044
3.
伯明翰大学电子、电气与系统工程学院，西米德兰兹伯明翰 B15 2TT

基金项目:

国家自然科学基金项目 51305021

国家自然科学基金项目 U1334211

国家自然科学基金项目 U1234205

“十二五”国家科技支撑计划项目 2015BAG12B01

详细信息

作者简介:
曹源（1982-），男，河南开封人，北京交通大学副教授，工学博士，从事高速列控系统监测研究

中图分类号: U270.7
计量
- 文章访问数: 663
- HTML全文浏览量: 182
- PDF下载量: 882
- 被引次数: 0
出版历程
- 收稿日期: 2015-02-21
- 刊出日期: 2015-06-20

Monitoring method of vehicle axle temperature based on dynamic time warping

CAO Yuan^{1, 2
,},
WANG Yu-jue²,
MA Lian-chuan^{1, 2},
CHEN Lei³

1.
National Engineering Research Center of Rail Traffic Operation and Control System, Beijing Jiaotong University, Beijing 100044, China
2.
School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, China
3.
School of Electronic, Electrical and Systems Engineering, University of Birmingham, Birmingham B15 2TT, West Midlands, UK

More Information

Author Bio:
CAO Yuan(1982-), male, associate professor, PhD, +86-10-51686121, ycao@bjtu.edu.cn

摘要

摘要: 为了处理车辆轴温可能出现的跳变、缺失、噪声等异常数据, 有效降低误报率, 提出了基于动态时间规整算法的车辆轴温状态监测方法, 将轴温历史监测数据和历史统计数据进行指数平滑预处理, 在训练阶段将数据反复迭代得到不同轴温模式的参考样本, 计算了实时轴温和参考样本各数据帧之间的欧氏距离, 得到帧匹配距离矩阵, 运用动态规划和回溯的思想, 求出累积距离矩阵和动态规整路径, 将动态规整距离作为2个时间序列相似度的量化指标, 找出最小动态规整距离对应的轴温模式, 从而得到状态监测结果。仿真结果表明: 在MATLAB仿真中, 输入1000个时长为50~300min的轴温测试样本, 其最大响应时间小于0.4S, 共出现29次错误匹配, 误报率低于3%。通过对测试样本和参考样本的各数据帧进行指数平滑处理, 有效消除车辆轴温出现跳变的干扰, 虽然跳变值和跳变点数量不同, 但相对动态规整距离无变化, 对状态监测结果无影响。可见, 车辆轴温状态监测方法能够满足车辆轴温状态监测的实时性和准确度要求, 减少了误报率。
- 车辆工程 /
- 轴温监测 /
- 动态时间规整算法 /
- 指数平滑法
Abstract: In order to handle with the abnormal data of vehicle axle temperature, such as jump, deletion and noise, a monitoring method of vehicle axle temperature based on dynamic time warping method was put forward to reduce the false alarm rate. The historical monitoring data and historical statistical data were preprocessed by using exponential smoothing method. At the training stage, the data were iterated to get the reference samples of different axle temperature modes. The frame matching distance matrix was obtained by computing Euclidean distances of data frames between real-time axle temperatures and reference samples. With the idea of dynamic programming and backtracking, the cumulative distance matrix and dynamic time warping path were calculated. The dynamic time warping distance was taken as the quantitative similarity index of two time series to the corresponding axle temperature mode for the minimum dynamic time warping distance, thus the axle temperature condition was achieved. Simulation result shows that when 1 000 test samples of axle temperature with the time ranges of 50 min to 300 min are inputted in MATLAB, the maximum response time is less than 0.4 s, there are 29 false matches, and the false alarm rate is below 3~. The jump interferences of axle temperature are effectively eliminated by processing the data using exponential smoothing method. The values and numbers of axle temperature jumps are different, but the relative dynamic time warping distances are invariable. Obviously, the method can meet the real-time and accuracy requirements of vehicle axle temperature monitoring and reduces the false alarm rate.
- vehicle engineering /
- axle temperature monitoring /
- dynamic time warping method /
- exponential smoothing method

HTML全文

图 1 状态监测流程

Figure 1. Condition monitoring process

下载: 全尺寸图片幻灯片

图 2 四个列车轴温测试样本

Figure 2. Four test samples of tra1n axle temperature

下载: 全尺寸图片幻灯片

图 3 动态规整距离

Figure 3. Dynamic time warping distances

下载: 全尺寸图片幻灯片

图 4 动态规整路径

Figure 4. Dynamic time warping paths

下载: 全尺寸图片幻灯片

图 5 匹配频数分布

Figure 5. Matching frequency distribution

下载: 全尺寸图片幻灯片

图 6 样本匹配结果

Figure 6. Matching result of samples

下载: 全尺寸图片幻灯片

表 1 参考样本

Table 1. Reference samples

表 2 测试样本与参考样本的DTW距离

Table 2. Dynamic time warping distances between test samples and reference samples

表 3 不同跳变序列的动态规整距离

Table 3. Dynamic time warping distances of different hopping seq uences

参考文献(21)

[1]	张周锁, 胥永刚, 何正嘉. 新型高速机车轴温监测系统的研究与开发[J]. 西安交通大学学报, 2001, 35(3): 280-283. doi: 10.3321/j.issn:0253-987X.2001.03.014 ZHANG Zhou-suo, XU Yong-gang, HE Zheng-jia. New monitoring system of bearing temperature in high speed locomotive[J]. Journal of Xi'an Jiaotong University, 2001, 35(3): 280-283. (in Chinese) doi: 10.3321/j.issn:0253-987X.2001.03.014
[2]	杨军, 孙文斌. CRH5型动车组轴温检测系统改进方案探讨[J]. 大连交通大学学报, 2013, 34(5): 37-41. doi: 10.3969/j.issn.1673-9590.2013.05.009 YANG Jun, SUN Wen-bin. Study on the solution for improving the hot axel detection system[J]. Journal of Dalian Jiaotong University, 2013, 34(5): 37-41. (in Chinese) doi: 10.3969/j.issn.1673-9590.2013.05.009
[3]	余祖俊, 许西宁, 史红梅. 单总线数字式机车轴温监测报警装置[J]. 电子测量与仪器学报, 2001, 15(3): 55-60. https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY200103011.htm YU Zu-jun, XU Xi-ning, SHI Hong-mei. l-wire digital device of locomotive bearing temperature detection and alerting[J]. Journal of Electronic Measurement and Instrument, 2001, 15(3): 55-60. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY200103011.htm
[4]	哈大雷, 王乾, 蒋涛, 等. 新型轴温监测系统在高速动车组上的应用[J]. 大连交通大学学报, 2013, 34(1): 89-94. doi: 10.3969/j.issn.1673-9590.2013.01.019 HA Da-1ei, WANG Qian, JIANG Tao, et al. Application of new axle temperature monitoring system on high-speed EMUs[J]. Journal of Dalian Jiaotong University, 2013, 34(1): 89-94. (in Chinese) doi: 10.3969/j.issn.1673-9590.2013.01.019
[5]	KEOGH E, RATANAMAHATANA C A. Exact indexing of dynamic time warping[J]. Knowledge and Information Systems, 2005, 7(3): 358-386. doi: 10.1007/s10115-004-0154-9
[6]	ZHEN D, WANG T, GU F, et al. Fault diagnosis of motor drives using stator current signal analysis based on dynamic time warping[J]. Mechanical Systems and Signal Processing, 2013, 34(1/2): 191-202.
[7]	BLACKBURN J, RIBEIRO E. Human motion recognition using isomap and dynamic time warping[C]∥ELGAMMAL A, ROSENHAHN B, KLETTE R. Human Motion-Understanding, Modeling, Capture and Animation. Berlin: Springer, 2007: 285-298.
[8]	GILLIAN N, KNAPP R B, O'MODHRAIN S. Recognition of multivariate temporal musical gestures using n-dimensional dynamic timewarping[C]∥JENSENIUS A R, TVEIT A, GODOY R I, et al. 11th International Conference on New Interfaces for Musical Expression. Trier: DBLP, 2011: 337-342.
[9]	孙博, 康锐, 谢劲松. 故障预测与健康管理系统研究和应用现状综述[J]. 系统工程与电子技术, 2007, 29(10): 1762-1767. doi: 10.3321/j.issn:1001-506x.2007.10.042 SUN Bo, KANG Rui, XIE Jin-song. Research and application of the prognostic and health management system[J]. Systems Engineering and Electronics, 2007, 29(10): 1762-1767. (in Chinese) doi: 10.3321/j.issn:1001-506x.2007.10.042
[10]	JUN B H. Fault detection using dynamic time warping(DTW)algorithm and discriminant analysis for swine wastewater treatment[J]. Journal of Hazardous Materials, 2011, 185(1): 262-268. doi: 10.1016/j.jhazmat.2010.09.027
[11]	徐波, 唐海龙, 李行善. 基于DTW的涡扇发动机气路故障定量诊断方法[J]. 北京航空航天大学学报, 2004, 30(6): 524-528. doi: 10.3969/j.issn.1001-5965.2004.06.009 XU Bo, TANG Hai-long, LI Xing-shan. DTW based quantitative fault diagnosis of gas path component in turbofan[J]. Journal of Beijing University of Aeronautics and Astronautics, 2004, 30(6): 524-528. (in Chinese) doi: 10.3969/j.issn.1001-5965.2004.06.009
[12]	ISLAM M S, HANNAN M A, BASRI H, et al. Solid waste bin detection and classification using dynamic time warping and MLP classifier[J]. Waste Management, 2014, 34(2): 281-290. doi: 10.1016/j.wasman.2013.10.030
[13]	RATH T M, MANMATHA R. Word image matching using dynamic time warping[C]∥IEEE. CVPR 2003. Now York: IEEE, 2003: 521-527.
[14]	TOMASI G, VAN DEN BERG F, ANDERSSON C. Correlation optimized warping and dynamic time warping as preprocessing methods for chromatographic data[J]. Journal of Chemometrics, 2004, 18(5): 231-241. doi: 10.1002/cem.859
[15]	YU Da-ren, YU Xiao, HU Qing-hua, et al. Dynamic time warping constraint learning for large margin nearest neighbor classification[J]. Information Sciences, 2011, 181(13): 2787-2796. doi: 10.1016/j.ins.2011.03.001
[16]	王振恒, 赵劲松, 李昌磊. 一种新的间歇过程故障诊断策略[J]. 化工学报, 2008, 59(11): 2837-2842. doi: 10.3321/j.issn:0438-1157.2008.11.023 WANG Zhen-heng, ZHAO Jin-song, LI Chang-lei. Novel fault diagnosis strategy for batch chemical processes[J]. Journal of Chemical Industry and Engineering, 2008, 59(11): 2837-2842. (in Chinese) doi: 10.3321/j.issn:0438-1157.2008.11.023
[17]	RAMAKER H, VAN SPRANG E N M, WESTERHUIS J A, et al. Dynamic time warping of spectroscopic BATCH data[J]. Analytica Chimica Acta, 2003, 498(1/2): 133-153.
[18]	ARICI T, CELEBI S, AYDIN A S, et al. Robust gesture recognition using feature pre-processing and weighted dynamic time warping[J]. Multimedia Tools and Applications, 2014, 72(3): 3045-3062. doi: 10.1007/s11042-013-1591-9
[19]	王君伟, 范启富, 白凌云. 基于DTW的红外乘客计数系统[J]. 测控技术, 2008, 27(6): 32-35. doi: 10.3969/j.issn.1000-8829.2008.06.010 WANG Jun-wei, FAN Qi-fu, BAI Ling-yun. DTW based automatic passenger counting system using infrared sensors[J]. Measurement and Control Technology, 2008, 27(6): 32-35. (in Chinese) doi: 10.3969/j.issn.1000-8829.2008.06.010
[20]	HELWIG N E, HONG S, HSIAO-WECKSLER E T, et al. Methods to temporally align gait cycle data[J]. Journal of Biomechanics, 2011, 44(3): 561-566. doi: 10.1016/j.jbiomech.2010.09.015
[21]	高剑, 张彩明, 孟祥旭, 等. 一种基于DDTW的三维碎片自动拼接方法[J]. 计算机学报, 2009, 32(2): 342-349. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJX200902019.htm GAO Jian, ZHANG Cai-ming, MENG Xiang-xu, et al. Automatic fragment reassembly method based on DDTW match[J]. Chinese Journal of Computers, 2009, 32(2): 342-349. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JSJX200902019.htm