Extension prediction model of soft rock tunnel deformation grade based on entropy weight method and rough set

When the tunnel passes through the soft rock area, the deformation problem is unavoidable, which affects the construction of the tunnel. In this paper, a method is proposed to predict the deformation grade of soft rock tunnel. Six influencing factors of soft rock tunnel deformation are selected as evaluation indexes, including tunnel depth, excavation method, support closure time, groundwater condition, angle of bedding, and uniaxial compressive strength of rock. Vault subsidence and clearance convergence are selected as actual grading indexes, and the deformation grade was divided into four grades. The entropy weight method is used to calculate the weight of the actual grading index, and the excavation section deformation is graded based on extension theory. Then the weight of influencing factors is calculated based on rough set theory, and the main factors controlling deformation are highlighted. Finally, an extension prediction model of soft rock tunnel deformation grade is established and applied to the prediction of deformation grade of the Huangjiagou tunnel of the Zhengwan high-speed railway. The prediction model is in good agreement with the field observation results, and the accuracy rate reaches 90%, which provides a new idea for the prediction of deformation grade of soft rock tunnel.