Developing a cloud evidence method for dynamic early warning of tunnel construction safety risk in undersea environment
Hong Zhou, Binwei Gao, Xianbo Zhao, Linyu Peng, S. Mamatha Bai
Abstract
Traditional methods have limitations in achieving precise predictions of risk occurrence at an exact future time and have difficulties transforming between qualitative and quantitative indicators and handling multi-source heterogeneous risk data. This study quantifies and analyzes the multi-source construction safety risks classified into the categories of man, machine, material, method and environment (4M1E), and presents a cloud evidence method that integrates wavelet de-noising algorithm, cloud model, and Dempster-Shafer (D-S) evidence theory. A real-time risk prediction and warning is provided using this method after the fusion of multi-source uncertain information and the transformation between qualitative and quantitative indicators, enabling the timely detection of potential risks for project managers. This method analyzing “uncertainty” with “certainty” is verified by an undersea tunnel construction project. The result shows that this method is effective in early warning risks two days before their actual occurrence, providing reference significance for risk early warning of the tunnel construction project.