铁道信号系统安全计算机状态监测方法

曹源; 马连川; 李旺

doi:10.19818/j.cnki.1671-1637.2013.03.015

铁道信号系统安全计算机状态监测方法

doi: 10.19818/j.cnki.1671-1637.2013.03.015

曹源^{1, 2,},
马连川^{1, 2},
李旺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.
山东省计算中心, 山东济南 250014

基金项目:

国家863计划项目 2012AA112001

国家863计划项目 2012AA112801

中央高校基本科研业务费专项资金项目 2012JBZ0014

高等学校博士学科点专项科研基金项目 20110092120011

高等学校博士学科点专项科研基金项目 20120009120004

国家自然科学基金项目 61101087

铁道部科技研究开发计划项 2013X013-D

详细信息

作者简介:
曹源(1982-), 男, 河南开封人, 北京交通大学讲师, 工学博士, 从事高速铁路通信信号研究

中图分类号: U283.2
计量
- 文章访问数: 520
- HTML全文浏览量: 113
- PDF下载量: 894
- 被引次数: 0
出版历程
- 收稿日期: 2012-12-18
- 刊出日期: 2013-06-25

Monitoring method of safety computer condition for railway signal system

CAO Yuan^{1, 2
,},
MA Lian-chuan^{1, 2},
LI Wang³

1.
National Engineering Research Center of Rail Transportation Operation and Control System, Beijing Jiaotong University, Beijing 100044, China
2.
School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, China
3.
Shandong Computer Science Center, Jinan 250014, Shandong, China

More Information

Author Bio:
CAO Yuan(1982-), male, lecturer, PhD, +86-10-51684971, ycao@bjtu.edu.cn

摘要

摘要: 基于隐马尔科夫模型(Hidden Markov Model, HMM)提出了状态监测和故障诊断的原理与基本流程。通过观测数据的提取与降维, 正常态模型训练与改进, 故障态模型训练等一系列措施, 实现了两模冗余安全计算机的状态监测, 对正常态与时钟偏离1%~10%等7种不同条件进行监测。监测结果表明: 对数似然概率均值从-228.98降至-1 385.60, 健康状态不断恶化。对1号处理单元(PU1)故障状态进行仿真监测时, 将PU1故障与PU1故障态、正常态、安全容错管理单元(FTSM)故障态、通信控制器(CC)故障态以及系统受扰故障态进行比较, 得到对数似然概率均值分别为-161.95、-13.72、-14.13、-40.17及-35.69, 证明了系统所发生的故障是因PU1所致。监测方法能够有效实现安全计算机健康状态的检测, 为铁道信号安全计算机监测技术提供理论支撑。
- 铁道信号 /
- 系统安全 /
- 隐马尔科夫模型 /
- 故障监测 /
- 健康管理
Abstract: The principle and primal procedure of condition monitoring and fault detection were proposed based on hidden Markov model(HMM).The condition monitoring for two-mode redundant safety computer was carried out by using a number of ways, including the extraction and dimensionality reduction of observed data, the training and improvement of normal status model, the training of fault status model and so on. 7 different conditions of normal statuses and statuses with 1%-10% clock offsets were monitored.Monitoring result shows that average logarithmic likelihood probability reduces from -228.98 to -1 385.60, which indicates the degrading of health status.When the monitoring of PU1(process unit 1) faults is conducted by simulation, the average logarithmic likelihood probabilities of fault status compared with PU1 fault, normal status, fault tolerance and safety management(FTSM) fault, communication controller(CC) fault, and system interference fault are -161.95, -13.72, -14.13, -40.17 and -35.69, respectively, which verifies that the system fault is resulted from PU1. So the proposed monitoring method is effective in safety computer monitoring, and it will give a theoretical support to the monitoring of railway signal safety computer.
- railway signal /
- system safety /
- hidden Markov model /
- fault monitoring /
- health management

HTML全文

图 1 HMM结构

Figure 1. HMM structure

下载: 全尺寸图片幻灯片

图 2 工作流程

Figure 2. Working process

下载: 全尺寸图片幻灯片

图 3 LDA处理后的一维数据

Figure 3. One-dimension data after LDA

下载: 全尺寸图片幻灯片

图 4 安全计算机的状态转移

Figure 4. State transition of safety computer

下载: 全尺寸图片幻灯片

图 5 正常态与故障态训练曲线

Figure 5. Training curves of normal and failure statuses

下载: 全尺寸图片幻灯片

图 6 正常态的对数似然概率

Figure 6. Logarithmic likelihood probabilities of normal status

下载: 全尺寸图片幻灯片

图 7 对数似然概率比较

Figure 7. Comparison of logarithmic likelihood probabilities

下载: 全尺寸图片幻灯片

参考文献(15)

[1]	曹源, 唐涛, 徐田华, 等. 形式化方法在列车运行控制系统中的应用[J]. 交通运输工程学报, 2010, 10(1): 112-126. http://transport.chd.edu.cn/article/id/201001020 CAO Yuan, TANG Tao, XU Tian-hua, et al. Application of formal methods in train control system[J]. Journal of Traffic and Transportation Engineering, 2010, 10(1): 112-126. (in Chinese). http://transport.chd.edu.cn/article/id/201001020
[2]	陈珊, 王太勇, 王国锋, 等. 机械设备智能诊断与预测维修系统[J]. 西南交通大学学报, 2003, 38(5): 540-543. doi: 10.3969/j.issn.0258-2724.2003.05.013 CHEN Shan, WANG Tai-yong, WANG Guo-feng, et al. Intelligent fault diagnosis, prediction and maintenance system of mechanical equipment[J]. Journal of Southwest Jiaotong University, 2003, 38(5): 540-543. (in Chinese). doi: 10.3969/j.issn.0258-2724.2003.05.013
[3]	VICHARE N M, PECHT M G. Prognostics and health management of electronics[J]. IEEE Transactions on Components and Packaging Technologies, 2006, 29(1): 222-229. doi: 10.1109/TCAPT.2006.870387
[4]	OWSLEY L M D, ATLASL E, BERNARD G D. Self-organizing feature maps and hidden Markov models formachine-tool monitoring[J]. IEEE Transactions on Signal Processing, 1997, 45(11): 2787-2798. doi: 10.1109/78.650105
[5]	SMYTH P. Hidden Markov models and neural networks for fault detection in dynamic systems[C]∥IEEE. Proceedings of Neural Networks for Signal Processing. Boise: IEEE, 1993: 582-592.
[6]	ATLAS L, OSTENDORF M, BERNARD G D. Hidden Markov models for monitoring machining tool-wear[C]∥IEEE. Proceedings of the Acoustics, Speech, and Signal Processing. Istanbul: IEEE, 2000: 3887-3890.
[7]	OCAK H, LOPARO K A. A new bearing fault detection and diagnosis scheme based on hidden Markov modeling of vibration signals[C]∥IEEE. Proceedings of the Acoustics, Speech, and Signal Processing. Salt Lake City: IEEE, 2001: 3141-3144.
[8]	ZHAO Yun-xin, ATLAS L E, ZHUANG Xin-hua. Application of the gibbs distribution to hidden Markov modeling in speaker independent isolated word recognition[J]. IEEE Transactions on Signal Processing, 1991, 39(6): 1291-1299. doi: 10.1109/78.136535
[9]	林果园, 郭山清, 黄皓, 等. 基于动态行为和特征模式的异常检测模型[J]. 计算机学报, 2006, 29(9): 1553-1560. doi: 10.3321/j.issn:0254-4164.2006.09.006 LIN Guo-yuan, GUO Shan-qing, HUANG Hao, et al. An anomaly detection model based on dynamic behavior and character patterns[J]. Chinese Journal of Computers, 2006, 29(9): 1553-1560. (in Chinese). doi: 10.3321/j.issn:0254-4164.2006.09.006
[10]	冯长建. HMM动态模式识别理论、方法以及在旋转机械故障诊断中的应用[D]. 杭州: 浙江大学, 2002. FENG Chang-jian. HMM dynamical pattern recognition the-ories, methods and applications in faults diagnosis of rotating machine[D]. Hangzhou: Zhejiang University, 2002. (in Chinese).
[11]	王剑, 张辉, 蔡伯根, 等. 基于HMM的列车轨道占用自动识别算法研究[J]. 铁道学报, 2009, 31(3): 54-58. https://www.cnki.com.cn/Article/CJFDTOTAL-TDXB200903011.htm WANG Jian, ZHANG Hui, CAI Bai-gen, et al. The algorithm of automatic track occupying identification based on HMM[J]. Journal of the China Railway Society, 2009, 31(3): 54-58. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-TDXB200903011.htm
[12]	QIAO Y, XIN X W, BIN Y, et al. Anomaly intrusion detection method based on HMM[J]. Electronics Letters, 2002, 38(13): 663-664. doi: 10.1049/el:20020467
[13]	宋雪萍, 马辉, 刘杰, 等. 基于HMM的故障诊断特征提取和聚类技术[J]. 振动、测试与诊断, 2006, 26(2): 92-96, 157. https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCS200602001.htm SONG Xue-ping, MA Hui, LIU Jie, et al. Feature extraction and clustering technique of rotating machinery fault diagnose based on HMM[J]. Journal of Vibration, Measurement and Diagnosis, 2006, 26(2): 92-96, 157. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-ZDCS200602001.htm
[14]	RABINER L R, JUANG B H. An introduction to hidden Markov models[J]. IEEE ASSP Magazine, 1986, 3(1): 4-16.
[15]	PECK R, NESS J. The use of shrinkage estimators in linear discriminant analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1982, 4(5): 530-537.