Study On Groundwater Disaster Prevention And Evaluation System Of Tunnel Engineering

With the development of our national economy, tunnel construction has acquired quite great improvenment in china, according to the statistical data of ministry of communications and ministry of railway, by the end of 2006, there were 5924 railway operation tunnels, about 3,740,000 meters, which seven extra long tunnels more than 10,000meters, there were 2,889 road operation tunnels, 1,520,000 meters, which 43 extra long tunnels, about 165,900 meters,because some reasons ,for example geology, design, construction rank, cost, tunnel operation maintenance and managenment, and so on, tunnel leakage disasters becomes more and more outstanding, and some tunnel disasters have influenced tunnels'normal use. Even jeopardizes the traffic safety, there are many disasters in the process of tunnel construction and tunnel operation, such as gushing water disasters , rock burst, gas explosion, leakage disasters, tunnel lining structure crack, basement damage disease, however, among these disasters, tunenl water disasters become more proninent and serious.This paper through collection and site measurement the data of tunnel hydrogeology of extra-long tunnel in Shi-Tai passenger dedicated railway, this paper established hydrogeology conceptual model of tunnel surrounding rock, and through investigation and analysis of information from 95 railway operation tunnels, the evaluation index system of tunnel leakage is established.Based on prediction results of tunnel gushing water, hydrogeology conditions of tunnel area and other factors, waterproof and drainage engineering measures were put forward, then by substitution engineering measures as constraints into the initial mathematical model, through computer program calculation, according to data results and graphical results analyse validity of engineering measurements.Through consult domestic and foreign literature and analyse the data of 95 typical tunnel of north and south, Based on the principle of Mahalanobis distance discriminant analysis(DDA), a distance discriminant analysis model to predict the possibility and classification of tunnel leakage is established, eight main control factors of tunnel leakage are chosen in the analysis , such as ,the depth of tunnel, the situation of vegetation covering of tunnel area, annual average rainfall of tunnel area, the situation of surface water of tunnel area, groundwater corrosion, design, construction. Some surveying data of tunnel leakage are taken as the training and testing samples, and the ration of mistake distinguish is considerably low zero. the results show that the DDA model can be used to predict the possibility and classification of tunnel leakage. The method offers a new way in classification of disaster of tunnel leakage.To leakage disease evaluation of operation tunnel ,this paper select 16 sub-factors including burial depth of tunnel, the height difference between groundwater level and tunnel bottom floor, rainfall of tunnel area, vegetation of tunnel area, construction of three joints, pipeline erosion, choking ,and so on, this paper establish the evaluating indicator system and hierarchy analytical model of tunnel leakage disasters from some aspects, that is tunnel construction factor, the engineering measure of prevent-drainage water, Bedrock and groundwater factor, physical geography factor. Tunnel leakage disaster are classified according to different criteria, that is lining leaking water amount and status of tunnel leakage, positions of leakage and forms of leakage, severity of tunnel,s disaster, ascertain five rank standards of sixteen sub-factors, foundation membership function of all quantitative indexes and quantify indexes, in the end, fuzzy comprehensive assessment and BP neural network (Considering easy operability of BP neural network, this paper simplified 16 sub-factors to 10 sub-factors) are used to assess rank of tunnel leakage disaster, at the same time, visualization procedure is established with VB, these could offer a theoretical basis for design entities to prevent tunnel leakage disaster.Taking the Dazhai tunnel and Weihuang tunnel as examples, this paper use DDA predict tunnel leakage situation, and use fuzzy synthesis assessment and BP neural network evaluate runnel leakage disease rank, prediction and evaluation results accord with statistical results of situ measurement, these were benefical to study reasonable prevention meastures of tunnel water diseases.