| With the rapid development of the national economy,more and more tunnels and underground engineering buildings serve the people’s lives.However,the safety of tunnel construction and smooth operation directly affect the production of the national economy,especially in the excavation stage will cause dramatic changes in the force field around should lead to surrounding soil deformation,causing subsidence,displacement,uplift deformation of tunnel structure,eventually threaten the security of tunnel.Due to the influence of geological conditions and other factors,it is difficult to establish an effective prediction model to predict the deformation trend of the tunnelTo predict accurately on the traditional forecasting model of nonlinear deformation monitoring data of tunnel subsidence trend and fluctuation characteristics,this paper uses the method of self-Memorization Principle and grey model combining dynamic system,construct the grey self-memory model,and then established the reverse derivation self-memory model using the double difference method to;By comparing with the grey model and the Markov model,the both of memory models can be used to predict the nonlinear and volatility data accurately;On the basis of the above analysis,a multi steps rolling prediction method is proposed,the results show that the method can improve the prediction accuracy The self-memory model in order to determine the order of backtracking,using redundancy theorem of forgetting factor and variable weight combination screening method based on backtracking through comparison with the trial order,legal order method,show that the method can quickly and accurately obtain the back order value,so as to simplify the modeling process memory model.Finally validated memory model in the tunnel settlement applicability analysis,at the same time a new method also provides for the tunnel safety prediction. |
