Research On Prediction Of Tunnel Water Inflow Based On Wavelet Analysis

With the development of society and economy, tunnel engineering has become one of the most important construction projects in China and even in the world, In the process of tunnel construction, verious problems may come out. Nowadays engineering has begun to pay much attention to the problems of water gushing which can bring serious impact to the construction. Water gushing of tunnel not only threatens the safety of staff and equipment,but also has a negative impact on the local environment, Therefore, the prediction of tunnel water inflow has become an urgent problem to be solved. This article study on the prediction of water flow into huama tunnel, based on wavelet analysis and grey system theory.Focusing on two aspects of research work.(1) Analyze the change of tunnel water gushing on time scale. Multi time scale is an important characteristic of tunnel water gushing, In this paper, the Morlet continuous complex wavelet transform is used to analyze the multi time scale characteristics of water gushing time series, the wavelet variance diagram and the wavelet coefficient modulus contour map are drawn. It is concluded that the first main period of water inflow in the huama tunnel is 24 months, and the characteristic time scale of the second main period is about 9 months, which provides some guidance for the prediction of water inflow.(2) Predict the water inflow of huama tunnel. This paper analyzes the possibility of combining grey system theory with wavelet analysis, and then, a single grey GM (1, 1)model and GM (1,1) model based on wavelet denoising are used to predict the water inflow.Next,compare and analyze the results.The results show that the combined model can improve the limitation of single model and improve the accuracy of prediction.This method can provide a new way for tunnel water inflow prediction, in order to provide theoretical basis for the safety of the tunnel construction.