A New Advance Classification Method for Surrounding Rock in Tunnels Based on the Set-Pair Analysis and Tunnel Seismic Prediction System

An advance optimized classification method is proposed to accurately predict the surrounding rock classification based on set pair analysis (SPA) and tunnel seismic prediction (TSP). Several factors that greatly affect rock mass classification are selected as evaluation indices of SPA based on analysis of TSP data. Evaluation indices are divided into five grades according to its response characteristics of seismic wave field, and their membership functions are proposed by using frequency statistical method. Entropy weight method is adopted to determine the weights of evaluation indices, and a SPA model is established for optimized classification of surrounding rock. Engineering application of Shimenya Tunnel of Yi-Ba Highway is taken as a case study, and proved that the evaluation indices are easy to obtain and the evaluation results are accurate and reliable. The SPA–TSP method can be further used for other tunnel engineering.