Development Of Boring Parameters Optimization And Excavation Face Instability Early-warning Platform For Undersea Tunnel

In recent years,the development of track transportation and the advancement of shield construction technology have provided the basis for tunnel constuction.More and more cross-sea tunnel projects,which are completed or under construction,have been adopted the shield method in coast and inland of China.However,due to the complex geological conditions,the interaction of multiple stratum,and the existence of weak stratum of underwater tunnels,how to optimize the excavation parameters under the composite stratum,and how to select more suitable early-warning parameters and conduct real-time safety early warning for undersea tunnels during construction period,have always been the focus,difficult and hot issue in the field of tunnel construction.In this paper,the excavation parameters are optimized based on the MIV-BP model and the AIC criterion.The real-time early-warning method of the tunnel is studied using the limit support force as the early-warning parameter.Finally,the boring parameters optimization and excavation face instability early-warning platform for undersea tunnel is developed based on WebGL technology.The main research results of the paper are generalized as follows:(1)Aiming at the problems that the key boring parameters in mixed ground are more difficult to control in submarine drainage tunnels and caverns,this paper proposes a specific solution.The Mean Impact Value(MIV)algorithm is introduced to the BP neural network model and the key boring parameters that have significant impact on shield construction effect can be screened out.On this basis,with the optimum distribution fitting of boring parameters based on Akaike Information Criterion(AIC),this paper proposes an optimized scheme for boring parameters,which use the confidence intervals of 50% confidence level as the controlling intervals.The corresponding program is developed based on the open source module libraries of Scikit-Learn and SciPy of Python.(2)Based on the predecessor theory,the stability of excavation face of the slurry shield is studied.By analyzing the existing early-warning parameters of the shield tunnels,the limit support pressure is selected as the early-warning index.Beacuse the calculation of the traditional limit support force has not considered the updating geological information,this paper proposes the method of calculating the early-warning index based on the dynamic updating model.On the basis of the early-warning level,the real-time safety early warning of excavation face for undersea tunnels is realized.(3)This paper studies the key technologies of the universal wedge-shaped segments involved in modeling,information extraction and correlation,and lightweight loading methods in front-end of Web.Based on the research of the universal wedgeshaped segments assembly technology,the segment layout method is determined,and the IFC model of the submarine drainage tunnel in accordance with the engineering practice is established based on Dynamo.On the basis of this,the IFC model data extraction and information association method are proposed.Finally,through the research on the working principle of WebGL,a lightweight processing method based on re-use geometry information is proposed,which realizes the lightweight loading of segments in the WebGL visualization platform.Based on the research contents above,this paper designs the system architecture and its functions,and the boring parameters optimization and excavation face instability early-warning platform for undersea tunnel based on WebGL technology is developed.The platform has already been applied to a certain submarine drainage tunnel project nuclear power station,and its application implementation process is carried out.