基于二阶隐马尔可夫模型的桥梁健康状况分析与评定
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Analysis and Assessment of Bridge Health Status Based on the Second-Order Hidden Markov Model
  • 作者:叶飞 ; 盛昭瀚 ; 徐峰
  • 英文作者:YE Fei;SHENG Zhaohan1a;XU Feng1a;School of Management Science and Engineering Nanjing University;Computational Experiment Center for Social Science, Nanjing University;Institute of Information Technology and Engineering Management, Tongling University;
  • 关键词:桥梁健康状况 ; 测量误差 ; 累积性病害 ; 二阶隐马尔可夫模型 ; Viterbi算法 ; 计算实验
  • 英文关键词:bridge health status;;measurement error;;accumulated diseases;;second-order hidden Markov model;;Viterbi algorithm;;computational experiment
  • 中文刊名:XTGL
  • 英文刊名:Journal of Systems & Management
  • 机构:南京大学工程管理学院;南京大学社会科学计算实验中心;铜陵学院信息技术与工程管理研究所;
  • 出版日期:2018-08-09 11:57
  • 出版单位:系统管理学报
  • 年:2018
  • 期:v.27
  • 基金:交通运输部建设科技项目(201331822310);; 国家自然科学基金资助项目(71390521,71101067,71471083,71471077);; 中国博士后科学基金资助项目(2014M551565);; 安徽省高校优秀青年人才支持计划资助项目
  • 语种:中文;
  • 页:XTGL201804011
  • 页数:10
  • CN:04
  • ISSN:31-1977/N
  • 分类号:97-106
摘要
在桥梁的养护管理中,桥梁健康状况的等级分析评定一般是依据桥梁定期的监测数据而进行的。由于系统误差和随机误差的影响,管理者常常只能得到具有噪声的监测数据。针对桥梁监测数据的测量误差和桥梁累积性病害的影响,运用二阶隐马尔可夫模型和Viterbi算法,提出了一种桥梁健康状况分析与评定方法。计算实验表明,该方法可以有效地揭示桥梁的健康状况,降低测量误差的影响,提高健康状况等级评定的准确度,从而为进一步的桥梁养护管理提供更可靠的依据。
        In bridge maintenance management, the analysis and assessment of bridge health status is usually based on the regular monitoring data of bridge. Due to the influence of system error and random error, managers often only get the monitoring data with noises. Based on the measurement error and the accumulated diseases, this paper proposes a method for the analysis and assessment of bridge health status using the second-order hidden Markov model and the Viterbi algorithm. The experimental results show that the method can effectively reveal the real condition of bridge health, reduce the effects of measurement error, enhance the accuracy of the assessment of bridge health, and thus provide a more reliable basis for bridge maintenance management in the next step.
引文
[1] 刘玉民, 陈惟珍, 杨修志. 桥梁养护技术与管理[M]. 北京: 人民交通出版社, 2013.
    [2] 中华人民共和国交通运输部. 2013年交通运输行业发展统计公报[EB/OL]. (2013-05-13)[2014-12-29].http://www.moc.gov.cn/zfxxgk/bnssj/zhghs/201405/t20140513_1618277.html.
    [3] 腾格尔, 贺昌政, 蒋晓毅. 隐马尔可夫模型研究进展及其管理领域应用[J]. 软科学, 2012, 26(2): 122-126.
    [4] 陈蓉, 王慧敏, 佟金萍. 基于SPN的极端洪灾应急管理流程建模仿真[J]. 系统管理学报, 2014, 23(2): 238-246.
    [5] Farran M, Zayed T. New life-cycle costing approach for infrastructure rehabilitation[J]. Engineering, Construction and Architectural Management, 2012, 19(1): 40-60.
    [6] Madanat S, Mishalani R, Hashim W, et al. Estimation of infrastructure transition probabilities from condition rating data[J]. Journal of Infrastructure Systems, 1995, 1(2): 120-125.
    [7] Lee Y. Deterioration modeling and rehabilitation decision analysis for assessing the performance of bridge deck expansion joints[D]. West Lafayette: Purdue University, 2002.
    [8] Zayed T, Chang L, Fricker J. Life-cycle cost analysis using deterministic and stochastic methods: Conflicting results[J]. Journal of Performance of Constructed Facilities, 2002, 16 (2): 63-74.
    [9] 戴宇文, 韩大建. 桥梁管理系统中的桥梁退化模型实现[J]. 水运工程, 2005, 380: 78-82.
    [10] 卢新, 刘朔. 基于改进的有限马尔可夫链的桥梁性能退化预测系统[J]. 计算机应用研究, 2012, 29(9): 3348-3351.
    [11] 张春霞, 马少飞, 王领. 基于马尔可夫预测模型的桥梁养护时机研究[J]. 现代交通技术, 2014, 11(5): 84-87.
    [12] Golabi K, Shepard R. Pontis: A system for maintenance optimization and improvement of US bridge networks[J]. Interfaces, 1997, 27 (1): 71-88.
    [13] Kobayashi K, Kaito K, Lethanh N. A statistical deterioration forecasting method using hidden Markov model for infrastructure management[J]. Transportation Research Part B: Methodological, 2012, 46(4): 544-561.
    [14] Humplick F. Highway pavement distress evaluation modelling measurement error[J]. Transportation Research Part B, 2009, 26 (2): 135-154.
    [15] Rabinovich S G. Measurement errors and uncertainties: Theory and practice[M]. Third Edition. New Jersey: Springer, 2005.
    [16] 叶飞, 王翼飞. 高阶隐马氏模型研究进展[J]. 数学进展, 2014, 43(2): 219-231.
    [17] Yin C, Tian S, Mu S. High-order Markov kernels for intrusion detection[J]. Neurocomputing, 2008, 71(16): 3247-3252.
    [18] 荣腾中, 肖智. 高阶马尔可夫链的降阶模型及其应用[J]. 数理统计与管理, 2013, 32(1): 81-88.
    [19] 荣腾中, 肖智. 高阶马尔可夫链平稳分布的存在唯一性[J]. 系统工程理论与实践, 2013, 33(8): 2015-2020.
    [20] Ephraim Y, Merhav N. Hidden markov processes[J].IEEE Transactions on Information Theory, 2002, 48(6): 1518-1569.
    [21] Gales M, Young S. The application of hidden Markov models in speech recognition[J]. Foundations and Trends in Signal Processing, 2008, 1(3): 195-304.
    [22] Artieres T, Marukatat S, Gallinari P. Online handwritten shape recognition using segmental hidden markov models[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2007, 29(2): 205-217.
    [23] Lytynoja A, Milinkovitch M C. A hidden Markov model for progressive multiple alignment[J]. Bioinformatics, 2003, 19(12): 1505-1513.
    [24] Mari J F, Ber F L. Temporal and spatial data mining with second-order hidden Markov models[J]. Soft Computing, 2006, 10(5): 406-414.
    [25] 周顺先, 林亚平, 王耀南, 等. 基于二阶隐马尔可夫模型的文本信息抽取[J]. 电子学报, 2007, 35(11): 2226-2231.
    [26] Ye Fei, Wang Yifei. A novel method for decoding any high-order hidden Markov model[J]. Discrete Dynamics in Nature and Society, 2014(6): 1-6.
    [27] 叶飞, 王翼飞. 基于动态规划的高阶隐马氏模型推广的Viterbi算法[J]. 运筹学学报, 2013, 17(4): 43-55.
    [28] Ye Fei, Yi Na, Wang Yifei. EM algorithm for training high-order hidden Markov model with multiple observation sequences[J]. Journal of Information and Computational Science, 2011, 8(10): 1761-1777.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700