Prediction of Surrounding Rock Classification of Highway Tunnel Based on PSO-SVM

Abstract

With the active development of highway construction projects across the country, the construction of tunnels has also increased. During the construction period of the tunnel, various complex engineering geological environments will be encountered, and construction safety is often required. This paper establishes a highway tunnel classification model based on the Support Vector Machine theory of Particle Swarm Optimization. Six indexes including intactness index of rock mass, water inflow, rock quality designation, rock uniaxial compressive strength, longitudinal wave velocity of rock and volume joint count were selected as the SVM model evaluation index, and the surrounding rock mass of the tunnel was divided into five grades. The model is trained according to the tunnel grading standard, and the trained model is used in the classification of five actual highway tunnels. The results show that the grading results are consistent with the actual results, which indicates the feasibility and reliability of the PSO-SVM model in tunnel grading, and proposes a new idea for tunnel surrounding rock grading.