Perceiving safety risk of buildings adjacent to tunneling excavation: An information fusion approach

摘要: Abstract This paper develops a novel hybrid information fusion approach that integrates cloud model (CM), Dempster–Shafer (D–S) evidence theory and Monte Carlo (MC) simulation technique to perceive safety risk of tunnel-induced building damage under uncertainty. The correlation measurement in the CM framework is used construct basic probability assignments (BPAs) within different states input factors. An improved combination rule incorporates Dempster' weighted mean deal with multi-source conflicts. MC simulate observation by using distribution order describe reduce underlying uncertainty during characterization A multi-layer proposed for perception, both hard data soft taken into account. Four buildings adjacent excavation one tunnel section Wuhan metro system China are utilized as case study demonstrate effectiveness applicability developed approach. Results indicate capable (i) synthesizing achieve more accurate result (ii) identifying global sensitivities factors Reliability perception results further tested scenarios bias levels factors, proves have strong robustness fault-tolerant capacity. can be practitioners industry decision tool anticipate potential risks tunneling projects.