Fuzzy comprehensive Bayesian network-based safety risk assessment for metro construction projects

Abstract

This paper presents a systemic decision-support approach to safety risk analysis for metro construction projects under uncertainty using a fuzzy comprehensive Bayesian network (FCBN), which combines the fuzzy comprehensive evaluation method (FCEM) and a Bayesian network (BN). The results of the safety risk assessment based on the FCBN are composed of three aspects: risk probability, risk loss, and risk controllability. In this assessment, two of the aspects—risk loss and risk controllability—are calculated in terms of intervals or fuzzy numbers. Through the application of the FCEM, the levels of risk loss and risk controllability are then estimated. The risk probability is calculated from the BN, in which the relationships among the dependent variables are expressed in the form of a directed graph. A comprehensive safety risk assessment allows engineers to assess potential safety hazards and provides a basis for dynamic early risk warning and control ahead of metro construction, which is acquired by combining the FCEM and the BN. A case study relating to safety risk analysis in the construction of the Dalian Metro in China is used to verify the feasibility of the approach as well as its application potential. A comparison of the results with the actual construction state shows its effectiveness in estimating the risk level of a metro construction project under uncertainty. The proposed approach provides a powerful tool with which planners and engineers can systematically assess and mitigate the inherent risks associated with metro construction.