Q-method optimization of tunnel surrounding rock classification by fuzzy reasoning model and support vector machine

This work aims to cope with the increasingly complex geological conditions in the process of traffic tunnel construction in China, improve the stability of tunnel construction, and reduce the probability of collapse, water gushing and other hazards in the construction process. The instability and deformation mechanism of tunnel surrounding rock is explored based on the theoretical knowledge of support vector machine (SVM), fuzzy reasoning, and Q classification method, and combined with the characteristics of tunnel surrounding rock in China. Moreover, a classification model via SVM and fuzzy reasoning is constructed for tunnel surrounding rock, followed by the outline of the shortcomings of tunnel surrounding rock classification in China. Then, the corresponding optimization method is put forward according to Q classification method. Finally, simulation experiments are conducted on arch collapse surrounding rock to evaluate the deformation stability. Experimental results demonstrate that the unstable area of tunnel surrounding rock increases with the increase in tunnel span, and the supporting treatment area required by the tunnel is also greatly enlarged. With the increase in span, the settlement value of vault increases continuously, and the increase rate varies with the hardness of surrounding rock. Moreover, the influence of the change of structural plane spacing of surrounding rock on the stability of surrounding rock gradually reduces. The influence of surrounding rock with larger hardness is more significant than that of surrounding rock with smaller hardness. Furthermore, there is a corresponding relationship between the hardness of rock and the rebound value. Besides, through the comparison between the actual surrounding rock test and the surrounding rock grade, there is no significantly corresponding relationship between the rebound value and the surrounding rock grade. Therefore, the rebound instrument can be used as an auxiliary tool for determining the surrounding rock grade. The research conclusion is that the classification optimization method of tunnel surrounding rock reported here facilitates the classification speed of tunnel surrounding rock.