 The rock mass conditions are very sensitive to tunnel boring machine, TBM, tunneling, therefore, establishing a surrounding rock excavatability, SR, classification system applicable to TBM tunnels is necessary. Accurate and intelligent identification of SR-E grades can also facilitate efficient TBM tunneling and intelligent construction. Specific excavation and penetration rates were used to evaluate SR-E. Their correlations with geological and tunneling parameters were explored using the field data from two water-conveyance tunnels in China with different lithologies. A high-precision empirical SR-E classification system was constructed using Topseus for multi-objective decision-making, and it was verified using engineering cases. An intelligent identification model for SR-E grades in the stable phase of a TBM excavation cycle was established using 12,382 TBM rock-breaking datasets and deep-forest models. Ten characteristic parameters, including total thrust, were selected as model input features. Hyperparameter optimization was achieved using the grid search method. Deep-forest was compared with decision tree, random forest, support vector classifier, and deep neural network. The This article was authored by Jian Mingzhuang, Kabin Shure, Haidlibiq Majidi, and others. We are article.tv, links in the description below.