Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/34483
Title: Safety risk identification system for metro construction on the basis of construction drawings
Authors: Ding, LY
Yu, HL
Li, H 
Zhou, C
Wu, XG
Yu, MH
Keywords: Metro project
Construction safety
Automatic risk identification
Drawing recognition
Issue Date: 2012
Publisher: Elsevier
Source: Automation in construction, 2012, v. 27, p. 120-137 How to cite?
Journal: Automation in construction
Abstract: Risk identification is a critical task in the risk management of metro and underground construction. This paper presents the safety risk identification system (SRIS) for metro construction based on construction drawings, which can be applied to the pre-construction risk assessment process to identify potential safety hazards, identify risks automatically and provide a basis for dynamic risk early warning and control. This paper summarizes the safety risks and risk factors of the metro construction, interprets the acquisition process of risk identification rules, and the production of rule-extensions and the storage of rule structures, on which the knowledge database of risk identification is based. It also develops the overall risk identification process and a group-retrieval matching algorithm based on meta-rules and certainty factors. Four recognition algorithms for typical graphic elements are proposed as a result of considering the features of metro construction drawings. The unique characteristic of SRIS is that, with the automatic identification of construction drawings by computer, the engineering parameters and relations between the construction drawings and the risk identification knowledge database can be quickly obtained. As a result, safety risks in metro construction can be automatically identified from the knowledge database.
URI: http://hdl.handle.net/10397/34483
ISSN: 0926-5805
DOI: 10.1016/j.autcon.2012.05.010
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

WEB OF SCIENCETM
Citations

13
Last Week
0
Last month
Citations as of Jan 14, 2017

Page view(s)

46
Last Week
0
Last month
Checked on Jan 15, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.