Abstract:

Support vector machine (SVM) based on structural risk minimization is used to predict the deformation of tunnel surrounding rocks, so as to understand the deformation trend of the surrounding rocks and to take measures to control the deformation. In the paper, the principle of support vector machine is described, the parameter optimization method based on ant colony optimization (ACO) is studied, and the ACOSVM model is established. The deformation prediction model has been applied in the construction of a highway tunnel, which shows that the model has high precision and can provide effective guidance for the tunnel construction. The paper can provide reference for similar projects in the future.

Key words: tunnel, surrounding rock, deformation, prediction, support vector machine, ant colony optimization, parameter optimization