Analysis of Early-Warning Threshold for Metro Construction Collapse Risk Based on D-S Evidence Theory and Rough Set
XIE Yi1,2, LIU Jia31. School of Traffic and Transportation, Changsha Uni-versity of Science and Technology, Changsha 410076, Hunan, China; 2. Wuhan Engineering Consulting Bureau, Wuhan 430014, Hubei, China; 3. School of Information and Safety, Zhongnan University of Economics and Law, Wuhan 430073, Hubei, China
The existing early-warning system in metro construction are generally based on traditional single-sensor data and simple analytic model, which makes it difficult to deal with the complex and comprehensive environment in metro construction. In this paper, the framework of early-warning threshold for metro construction collapse risk based on D-S evidence theory and rough set is built. By combining the primary data fusion collected based on rough set with the secondary data fusion which is based on D-S evidence theory, the integration of multiple information in metro construction is realized and the risk assessment methods are optimized. A case trial based on Hangzhou metro construction collapse accident is also carried out to exemplify the framework. The empirical analysis guarantees the completeness and independence of the prediction information, and realizes the dynamic prediction of the variation trend of metro construction collapse risk.
 Berkelaar R, Huisman L, Luijten C J L M. Deformation monitoring of the underground metro station Rotterdam CS:A case study[C]//Seventh International Symposium on Field Measurements in Geomechanics. Boston: American Society of Civil Engineers, 2007: 307-320.
 Hyun H C, Hyo N C, Seo J W. Risk assessment methodology for underground construction projects [J]. Journal of Con-struction Engineering and Management, 2004, 130(2): 258- 272.
 Yang P, Feng L,Yang Y, et al. Design and analysis on the index system of the metro shield construction monitoring [J]. Science Technology and Engineering, 2010, 10(29): 7326- 7329 (Ch).
 Hu Y J. The system of monitoring data processing and predicting and alarm of deep pit engineering [J]. Journal of Jiaozuo Institute of Technology (Natural Science), 2001, 3: 130-135(Ch).
 Chen W K, Zhang Z Y. Research on key monitoring indicators of subway construction disaster warning signs based on WBS-RBS and association rules [J]. China Safety Science Journal, 2013, 23(1):148-154 (Ch).
 Qiu D W. The Deformation Monitoring and Analysis for Existing Subway Tunnel under the Influence of Traversing Engineering [D]. Beijing: Beijing Jiaotong University, 2012 (Ch).
 Wu X G, Chen Y Q. Research on the standards for safety monitoring and forewarning management assessment in metro construction [J]. Journal of Railway Engineering Society, 2013, 5: 105-112(Ch).
 Dempster A P. Upper and lower probabilities induced by a multivalued mapping [J]. The Annals of Mathematical Sta-tistics, 1967, 38 (2): 325-339.
 Shafer G. A Mathematical Theory of Evidence [M]. Prince-ton: Princeton University Press, 1976.
 Pawlak Z. Rough sets [J]. International Journal of Computer & Information Sciences, 1982, 11 (5): 341-356.