Abstract：Research purposes:In order to eliminate low frequency and high cost factors in traditional tunnel monitoring and maintenance, a new tunnel deformation online monitoring system based on multi-agent is proposed. It can adapt to the new requirements for real-time monitoring maintenance.Research conclusions:(1) Based on the hierarchical component structure design idea, this paper presents a general agent model. The model consisted of three layers, which were customer perception layer, intelligent service layer and service effect layer, respectively. The internal structure of the agent was descripted separately in coarse-grained and fine-grained. (2) According to the characteristics of tunnel deformation monitoring and the general agent, a tunnel deformation monitoring system has been set up using acquaintance cooperation communication mechanism, with six-layer composite structure. Additionally, this system could realize the loosely coupled ability and low load structure. (3) The performance of prediction agent module has been validated with Shanghai metro deformation monitoring data. The experimental results showed that the system had strong autonomy, cooperation and a certain practical value, and may give references to the construction of the tunnel monitoring system.
[1] 赵锡宏,姜洪伟,袁聚云,等. 上海软土各向异性弹塑性模型[J]. 岩土力学, 2003(3): 322-330. Zhao Xihong, Jiang Hongwei, Yuan Juyun, etc. Anisotropically Elastoplastic Model of Shanghai Soft Soils[J]. Rock and Soil Mechanics,2003(3):322-330. [2] 范思遐,周奇才,熊肖磊,等. 基于多核模式的隧道沉降预测[J]. 岩土力学, 2013(Z2):291-298. Fan Sixia, Zhao Qicai, Xiong Xiaolei,etc. Settlement Prediction of Tunnel Based on Multiple Kernels Learning Mode[J]. Rock and Soil Mechanics,2013(Z2):291-298. [3] MIMOSA OSA-CBM 3.3.1[OL], (2010-8-20)[2010-8-20].http://www.mimosa.org. [4] D.Vallejo, J.Albusac, C. Glez-Morcillo, J. J. Castro-Schez , L. Jiménez. A multi-agent Approach to Intelligent Monitoring in Smart Grids[J]. International Journal of Systems Science,2014(4): 1-22. [5] Bratman M.E. Intentions Plans and Practical Reason[M]. Cambridge:Harvard University Press,1987. [6] VAPNIK V N. The Nature of Statistical Learning Theory[M]. New York: Springer-Verlag, 1995: 37-60. [7] 范思遐,周奇才,熊肖磊,等. 基于自适应粒子群与支持向量机的隧道变形预测模型[J]. 计算机工程与应用,2014(5): 6-10. Fan Sixia, Zhao Qicai, Xiong Xiaolei, etc. A Tunnel Deformation Prediction Model Based on Support Vector Machine with Particle Swarm Optimization Algorithm[J]. Computer Engineering and Applications,2014(5): 6-10. [8] 汪波,何川,吴德兴. 隧道结构健康监测系统理念及其技术应用[J]. 铁道工程学报,2012(1):67-72. Wang Bo,He Chuan,Wu Dexing. Ideas of Tunnel Structure Health Monitoring System and Its Technology Application[J]. Journal of Railway Engineering Society, 2012(1):67-72.
2014, Vol. 31 
版权所有 © 2014 《铁道工程学报》编辑部