Abstract
Rock squeezing has a large influence on tunnel construction safety; thus, when designing and constructing tunnels it is highly important to use a reliable method for predicting tunnel squeezing from incomplete data. In this study, a combination SVM-BP (support vector machine-back-propagation) model is proposed to classify the deformation caused by surrounding rock squeezing. We design different characteristic parameters and three types of classifiers (a SVM model, a BP model, and the proposed SVM-BP model) for the tunnel-squeezing prediction experiments and analyse the accuracy of predictions by different models and the influences of characteristic parameters on the prediction results. In contrast to other prediction methods, the proposed SVM-BP model is verified to be reliable. The results show that four characteristics: tunnel diameter (D), tunnel buried depth (H), rock quality index (Q) and support stiffness (K) reflect the effect of rock squeezing sufficiently for classification. The SVM-BP model combines the advantages of both an SVM and a BP neural network. It possesses flexible nonlinear modelling ability and the ability to perform parallel processing of large-scale information. Therefore, the SVM-BP model achieves better classification performance than do the SVM or BP models separately. Moreover, coupling D, H, and K has a significant impact on the predicted results of tunnel squeezing.
Highlights
Tunnel-surrounding rock squeezing is a deformation based on a space-time relationship that usually occurs in soft rock surrounding tunnels at large buried depths
In this paper, predicting tunnel-surrounding rock squeezing is a nonlinear separable case that lies in the main purview of an support vector machine (SVM): that is, the samples cannot be classified by their linear relationship in a low dimensional space
The innovation of this study is to present a combined model based on both an SVM and a BP model and applied to classify tunnel-surrounding rock squeezing
Summary
Tunnel-surrounding rock squeezing is a deformation based on a space-time relationship that usually occurs in soft rock surrounding tunnels at large buried depths. The main machine learning methods for predicting tunnel-surrounding rock squeezing include regression analysis (Jimenez and Recio, 2011; Ghasemi and Gholizadeh, 2018), neural networks (Zhou, et al 2018), decision trees (Chen, et al 2020), naive Bayes (Feng and Jimenez, 2015), and support vector machines (Sun, et al 2018; Shafiei, et al 2012). Among many machine learning methods, SVMs have strong generalization abilities and flexible nonlinear modelling ability, applying to solving small sample, high dimensional and nonlinear problems. The goals of this study are to develop a combined model of SVM and BP for large-scale tunnel-squeezing prediction and to verify the robustness of the combined model by comparing it with other machine learning methods. The conclusion and discussion section concludes the study and discusses the applicability of the three models for rock-squeezing prediction
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
