Risk Identification Expert System for Metro Construction Based on BIM

Abstract

This paper presents a BIM-based Risk Identification Expert System (B-RIES) for metro construction, composed of three main built-in subsystems: BIM extraction, knowledge base management, and risk identification subsystems. The engineering parameter information related to risk factors is extracted from the BIM of a specific project where the IFC standard plays a bridge role between the BIM data and metro construction safety risks. An integrated knowledge base, consisting of fact base, rule base and case base, is established to systematize the fragmented explicit and tacit knowledge. A hybrid inference approach, with case-based reasoning and rule-based reasoning included, is developed to improve the flexibility and comprehensiveness of the system reasoning capacity. During the safety risk identification process, B-RIES is able to improve the inefficiencies in engineering information extraction, reduce the dependence on domain experts, and facilitate knowledge sharing and communication among dispersed clients and domain experts. A typical safety hazard identification in the Mingdu station, located in the Wuhan Metro Line Two, is presented in a case study. The results demonstrate the feasibility of B-RIES, and its application potential. B-RIES can be used as a decision support tool to provide guidelines for safety management in metro construction, and thus increase the likelihood of a successful project in a complex environment.

Information Technology Applications in Construction Safety Assurance

“…Information technology has been applied in a wide array of applications to provide solutions to construction safety problems. Efforts made by researchers to assess the occupational safety (Dėjus, Antuchevičienė 2013), monitor performance of workers, equipment and construction environment, to replace human operations with robots and to collaborate among themselves are vital in creating a safe-working environment and in reducing casualties (Shin et al 2014;Moon et al 2014a;Ma et al 2014;Kim et al 2014;Han et al 2014;Guo et al 2014;Fung et al 2014;Choe et al 2014;Zhu et al 2013;Zhang et al 2013a;Ye et al 2013;Wu et al 2013a;Wang 2013;Sparer, Dennerlein 2013;Sepasgozar, Bernold 2013;Schikora et al 2013;Rubio-Romero et al 2013;Qin 2013;Melzner et al 2013;Marzouk, Ali 2013;Luo et al 2013;Li et al 2013;Kivrak et al 2013;Kim, Park 2013;Kasirossafar, Shahbodaghlou 2013a;Hinze et al 2013;Hammad et al 2013;Ding et al 2013aDing et al , 2013cZhou et al 2012;Zhao, Ye 2012;Yang et al 2012;Ren et al 2012;Li, Hua 2012;Li et al 2012a;Huang 2012;Hamidi et al 2012;…”