![]()
Abstract Time-dependent deformations of rock are important factors for the desizgn and construction of tunnels in the rock masses with time-dependent strength and deformation properties. Therefore, determining of the tunnel closure is an indispensable task in rock engineering, especially for design and construction of underground structures. However, in some types of rock masses, the tunnel closure may increase for months or years after the excavation owing to rheological behavior of the surrounding rock masses, which greatly influences the selection of the initial tunnel support system, the excavation layout, and the determination of its load-carrying capacity.
In this paper, we present a method to predict quickly the tunnel closure in time-dependent rock mass using Grey Verhulst Model (GVM). The method is validated fairly via a test for a new excavated drift of -600m level in a coal mine, Democratic People’s Republic of Korea.
1 Introduction Tunnel convergence is one of the issues that affects the performance of the tunnels both during the excavation and afterwards. The stability state of the underground structures can timely be known by monitoring the change of surrounding rock mass displacement. Therefore, the closure prediction of rock mass surrounding tunnel can be actually dealt with time series prediction problem.
Review of the literature shows that this problem has been investigated from different points of view by many researchers. Heretofore, there are a lot of methods for time series prediction of the tunnel deformation, such as traditional methods, artificial neural network (ANN) based models, grey system and support vector machine (SVM), etc., some of which are as follows.
Sulem et al. (1987) proposed a method based on analytical functions that the closure must be expressed as a function of the two parameters, distance to the face and the time-dependent properties of the ground. Also, Zhao et al. (2016) derived an analytical solution to the temporal-spatial displacement of the subsea tunnel lining from a generalized Kelvin constitutive model state equation. Meanwhile, Mahdevari & Torabi (2012) developed a method based on ANN for prediction of convergence in tunnels. At present, the Support vector machine (SVM), as a new machine learning technology, is one of the methods of tackling this problem, which is a supervised machine learning method based on the statistical learning theory (Mahdevari et al. 2013). Yao et al. (2010) & Wu et al. (2014) predicted tunnel surrounding rock mass displacement using SVM method, which has a high-accuracy prediction than ANN. Besides, Yao et al. (2012) presented a hybrid prediction model based on SVM and genetic algorithm (GA) for tunnel surrounding rock displacement. On the other hand, Huang et al. (2003) used time-series analysis termed ARMA(n, m) and GM(1,1) are used to predict the displacement at the key measuring points of the permanent shiplock in the Three Gorges Project, and Guo et al. (2014) presented the origin error reduced GM(1,1) to predict final tunnel surrounding rock displacement based on the data of early 20 days.
Site News