列车定位单元ODO故障分析及HMM的应用研究

臧钰; 上官伟; 张军政; 蔡伯根; 王化深

doi:10.3969/j.issn.0258-2724.2017.06.026

列车定位单元ODO故障分析及HMM的应用研究

doi: 10.3969/j.issn.0258-2724.2017.06.026

臧钰¹,
上官伟^1,2,3, ,,
张军政¹,
蔡伯根^1,2,3,
王化深¹

基金项目:

国家重点研发计划资助项目（2016YFB120010）

国家自然科学基金"重大"项目（61490705）

国家自然科学基金面上项目（61773049）

北京市自然科学基金资助项目（4172049）

详细信息

作者简介:
臧钰(1994-),女,博士,研究方向为交通信息工程及控制,电话:15201317134,E-mail:15111004@bjtu.edu.cn

通讯作者:
上官伟(1979-),男,教授,博士,研究方向为交通信息工程及控制、智能交通技术,E-mail:wshg@bjtu.edu.cn

计量
- 文章访问数: 539
- HTML全文浏览量: 78
- PDF下载量: 57
- 被引次数: 0
出版历程
- 收稿日期: 2016-09-20
- 刊出日期: 2017-12-25

Application of Hidden Markov Model for Fault Analysis of ODO in Train Location Unit

摘要

摘要: 列车运行过程中车轮会出现打滑抱死等现象，导致ODO（odometers）呈现功能故障状态，针对这一问题，进行了列车定位单元ODO故障分析及HMM（hidden Markov models）的应用研究.首先利用神经网络方法对ODO故障状态进行诊断；然后，引入基于HMM的故障诊断方法，从模式识别角度出发，建立ODO隐藏的故障状态模型，通过输入观测序列与分类器中的HMM匹配，得出ODO的故障诊断结果；最后，通过遗传算法对HMM中的参数训练部分进行改进.实例分析结果表明：利用神经网络进行故障诊断的故障识别率为33.3%，基于HMM的故障诊断方法对于正常和故障状态的诊断精度可达100%，总体诊断精度可达95%，利用遗传算法进行参数改进后经仿真对比表明：在训练速度上遗传算法可以较快到达稳态，训练精度提高了86%；在高噪声背景下用神经网络方法实现故障诊断具有明显缺陷，利用遗传算法可以改进B-W（Baum-Welch）算法易陷入局部最优的缺陷，基于HMM的故障诊断方法相较于神经网络方法有更高的准确性.
- 列控系统 /
- 故障诊断 /
- 里程计 /
- 神经网络 /
- 隐马尔科夫模型 /
- 遗传算法
Abstract: During the running of a train, the lock-and-slip state of a wheel may occur and hence, an Odometers (ODO) will temporarily display the state of functional failure. To address this issue, fault analysis of ODO based on the application of hidden Markov model (HMM) has been carried out. Firstly, an algorithm based on neural networks (NNs) was applied for the fault diagnosis of ODO. A fault diagnosis method based on HMM was then studied from the perspective of pattern recognition. The observation of the quantization coding sequence was introduced into the HMM classifier for establishing the hidden fault states of the ODO model with the aid of training data. By entering the observation sequence matching with the HMM classifier, the effective state of ODO was obtained. Finally, genetic algorithms (GAs) were employed for obtaining the parameters of HMM, rather than employing the Baum-Welch (B-W) algorithm. The obtained case study results show that the fault identification accuracy based on NN is 33.3%, the diagnos-tic accuracy based on HMM can reach up to 100% between normal and fault conditions, and the overall diagnostic accuracy is 95%. The training speed of GA can help in reaching the steady state quickly and the training accuracy can be improved by 86%. Furthermore, the obtained results show that the classification ability of NN is comparatively weak and cannot meet the required needs of classification when there is high noise in the data. The GA can improve on the drawbacks of the B-W algorithm that in turn can easily fall into the local optimum. The fault diagnosis method based on HMM has higher accuracy when compared with the NN-based method.
- train operation control system /
- fault diagnosis /
- odometer /
- neural network /
- hidden Markov model /
- genetic algorithm

HTML全文

参考文献(14)

DHAHBI S, ABBAS-TURKI A, HAYAT S, et al. Study of the high-speed trains positioning system:European signaling system ERTMS/ETCS[J]. Ratio Working Papers, 2011, 11(9):468-473.

涂继亮,罗艳芬,董德存. 一种基于粗集理论的车地无线通信设备故障诊断方法[J]. 计算机应用研究,2010,27(9):3372-3374. TU Jiliang, LUO Yanfen, DONG Decun. Fault diagnosis method for train-ground wireless communication unit based on rough sets theory[J]. Application Research of Computers, 2010, 27(9):3372-3374.

KORBICZJ, KOSCIELNY J M, KOWALCZUK Z, et al. Fault diagnosis-models, artificial intelligence and application[M]. Berlin:Springer, 2004:52-73.

ZHOU Yongyong, ZHOU Quan, LIU Jiabin, et al. Rough set theory based approach for fault diagnosis rule extraction of distribution system[J]. High Voltage Engineering, 2008(12):2713-2718.

姚鑫骅,徐月同,傅建中. 基于粗糙集理论的数控机床智能故障诊断研究[J]. 浙江大学学报:工学版,2008,42(10):1719-1724. YAO Xinhua, XU Yuetong, FU Jianzhong. Intelligent fault diagnosis of CNC machine tools based on rough set theory[J]. Journal of Zhejiang University:Engineering Science, 2008, 42(10):1719-1724.

刘江,蔡伯根,王剑,等. 基于灰色理论的列车组合定位轮径校准方法研究[J]. 铁道学报,2011,33(5):54-59. LIU Jiang, CAI Baigen, WANG Jian, et al. Study on wheel diameter calibration method in integrated train positioning based on gray theory[J].Journal of the China Railway Society, 2011, 33(5):54-59.

乔超,唐慧佳. 列车里程计定位方法的研究[J]. 兰州交通大学学报,2003,22(3):116-119. QIAO Chao, TANG Huijia. Research on the positioning method of train odometer[J]. Journal of LANZHOU Railway University:Nature Sciences, 2003, 22(3):116-119.

周达天. 基于多传感器信息融合的列车定位方法研究[D]. 北京:北京交通大学,2007.

MAIER W, SCHMIDIT F, SCHWAB S G, et al. A HMM-based model to geolocate pelagic fish from high-resolution individual temperature and depth histories:European sea bass as a case study[J]. Biological Psychiatry, 2016, 37(5):344-7.

MCLEOD A, STEEDMAN M. HMM-based voice separation of MIDI performance[J]. Journal of New Music Research, 2016, 45(1):1-10.

TOTH B, NEMETH G. Optimizing HMM speech synthesis for low-resource devices[J]. Journal of Advanced Computational Intelligence&Intelligent Informatics, 2016, 16(2):327-334.

XU Xianghua, ZHU Jie, Guo Qiang. Speaker independent speech recognition based on HMM state-restructuring method[J]. Journal of Southeast University:English Edition:2004, 20(4):427-430.

王剑,张辉,蔡伯根. 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. WANG Jian, LIU Hui, CAI Baigen,. The algorithm of automatic track occupying identification based on HMM[J]. Journal of The China Railway Society, 2009, 31(3):54-58.

WINGER L L. Linearly constrained generalized Lloyd algorithm for reduced codebook vector quantization[J]. IEEE Transactions on Signal Processing, 2001, 49(7):1501-1509.

施引文献

附加材料(0)

访问统计