Dynamic Risk Assessment in Construction Projects Using Bayesian Networks

This paper presents a systemic Bayesian network (BN) based approach for dynamic risk assessment for adjacent buildings in tunnel construction. This approach consists of four steps in detail, namely, hazard analysis, BN learning and BN-based risk analysis. In the dynamic risk analysis framework, the predictive, sensitivity and diagnostic analysis techniques in the Bayesian inference are used to conduct the feed-forward control in the preconstruction stage, intermediate control in the construction stage and back-forward control in the post-accident stage, respectively. A case relating to dynamic safety risk analysis of some existing buildings adjacent to construction of the Wuhan Yangtze Metro Tunnel in China is presented. 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, and thus increase the likelihood of a successful project in a dynamic project environment.

[1]  Miroslaw J. Skibniewski,et al.  Towards a safety management approach for adjacent buildings in tunneling environments: Case study in China , 2014 .

[2]  Chun Fai Leung,et al.  Finite element analysis of tunnel–soil–pile interaction using displacement controlled model , 2007 .

[3]  Nima Khakzad,et al.  Safety analysis in process facilities: Comparison of fault tree and Bayesian network approaches , 2011, Reliab. Eng. Syst. Saf..

[4]  Imoh Antai,et al.  A probabilistic approach to exposure risk assessment , 2008 .

[5]  Barry T. Hart,et al.  A Bayesian network approach to support environmental flow restoration decisions in the Yarra River, Australia , 2013, Stochastic Environmental Research and Risk Assessment.

[6]  Lieyun Ding,et al.  Development of web-based system for safety risk early warning in urban metro construction , 2013 .

[7]  Richard J. Finno,et al.  Evaluating Damage Potential in Buildings Affected by Excavations , 2005 .

[8]  Farnad Nasirzadeh,et al.  Dynamic risk analysis in construction projects , 2008 .

[9]  Ian Jenkinson,et al.  An Offshore Risk Analysis Method Using Fuzzy Bayesian Network , 2009 .

[10]  Benoît Iung,et al.  Overview on Bayesian networks applications for dependability, risk analysis and maintenance areas , 2012, Eng. Appl. Artif. Intell..

[11]  Faisal Khan,et al.  Dynamic risk assessment using failure assessment and Bayesian theory , 2009 .

[12]  Gregory F. Cooper,et al.  A Bayesian Method for the Induction of Probabilistic Networks from Data , 1992 .

[13]  Sung-Bae Cho,et al.  Evolutionary attribute ordering in Bayesian networks for predicting the metabolic syndrome , 2012, Expert Syst. Appl..

[14]  Marek J. Druzdzel,et al.  Learning Bayesian network parameters from small data sets: application of Noisy-OR gates , 2001, Int. J. Approx. Reason..

[15]  Fan Wang,et al.  Feedforward Analysis for Shield-Ground System , 2013 .

[16]  Steve Rowlinson,et al.  Capturing Safety Knowledge Using Design-for-Safety-Process Tool , 2004 .

[17]  Pengfei Li,et al.  Protection of buildings against damages as a result of adjacent large-span tunneling in shallowly buried soft ground , 2013 .

[18]  B. Ayyub.  Risk Analysis in Engineering and Economics , 2003 .

[19]  Debra F. Laefer,et al.  Evaluation of risk assessment procedures for buildings adjacent to tunnelling works , 2014 .

[20]  Shaoming Liao,et al.  Shield tunneling and environment protection in Shanghai soft ground , 2009 .

[21]  William H. Hsu,et al.  Genetic wrappers for feature selection in decision tree induction and variable ordering in Bayesian network structure learning , 2004, Inf. Sci..

[22]  Daniel Chi-Wing Ho,et al.  A survey of the health and safety conditions of apartment buildings in Hong Kong , 2008, Building and Environment.

[23]  Godfried Augenbroe,et al.  Multi-criteria decision making under uncertainty in building performance assessment , 2013 .