Dynamic risk analysis for adjacent buildings in tunneling environments: a Bayesian network based approach

This paper presents a systemic Bayesian network (BN) based approach for dynamic risk analysis of adjacent buildings in tunneling environments, consisting of risk/hazard identification, BN learning and BN validation. Two validation indicators are proposed to evaluate the effectiveness of the established BN model, aiming to ensure that the model predictions are not significantly different from actual observations. In the dynamic risk analysis framework, the predictive, sensitivity and diagnostic techniques are used to conduct the feed-forward control in the pre-construction stage, intermediate control in the construction stage and back-forward control in the post-accident stage, respectively. A case regarding some existing buildings adjacent to construction of the Wuhan Yangtze metro tunnel in China is presented. The results demonstrate the feasibility of the proposed approach, as well as its application potential. The proposed approach can be used by practitioners in the industry as a decision support tool to provide guidelines on the conservation of adjacent buildings against tunnel-induced damages.