• Geomechanics and Engineering
• /
• v.27 no.6
• /
• pp.551-560
• /
• 2021

Due to the low strength and high compressibility characteristics, the loess deposits tunnels are prone to large deformations and collapse. An accurate stability evaluation for loess deposits is of considerable significance in deformation control and safety work during tunnel construction. 37 groups of representative data based on real loess deposits cases were adopted to establish the stability evaluation model for the tunnel project in Yan'an, China. Physical and mechanical indices, including water content, cohesion, internal friction angle, elastic modulus, and poisson ratio are selected as index system on the stability level of loess. The data set is randomly divided into 80% as the training set and 20% as the test set. Firstly, principal component analysis (PCA) is used to convert the five index system to three linearly independent principal components X1, X2 and X3. Then, the principal components were used as input vectors for probabilistic neural network (PNN) to map the nonlinear relationship between the index system and stability level of loess. Furthermore, Leave-One-Out cross validation was applied for the training set to find the suitable smoothing factor. At last, the established model with the target smoothing factor 0.04 was applied for the test set, and a 100% prediction accuracy rate was obtained. This intelligent classification method for loess deposits can be easily conducted, which has wide potential applications in evaluating loess deposits.

• Geomechanics and Engineering
• /
• v.24 no.3
• /
• pp.253-266
• /
• 2021

The sufficient early strength of primary support is crucial for stabilizing the surroundings, especially for the tunnels constructed in soil. This paper introduces the Steel-Concrete Composite Support System (SCCS), a new support with high bearing capacity and flexible, rapid construction. The bearing characteristics and construction performance of SCCS were systematically studied using a three-dimensional numerical model. A sensitivity analysis was also performed. It was found that the stress of a π-shaped steel arch decreased with an increase in the thickness of the wall, and increased linearly with an increase in the rate of stress release. In the horizontal direction of the arch section, the nodal stresses of the crown and the shoulder gradually increased in longitudinally, and in the vertical direction, the nodal stresses gradually decreased from top to bottom. The stress distribution at the waist, however, was opposite to that at the crown and the shoulder. By analyzing the stress of the arch section under different installation gaps, the sectional stress evolution was found to have a step-growth trend at the crown and shoulder. The stress evolution at the waist is more likely to have a two-stage growth trend: a slow growth stage and a fast growth stage. The maximum tensile and compressive stresses of the secondary lining supported by SCCS were reduced on average by 38.0% and 49.0%, respectively, compared with the traditional support. The findings can provide a reference for the supporting technology in tunnels driven in loess.