Ediction of railway settlement deformation based on improved GM-AR model

In view of the randomness and fluctuation characteristics of railway settlement deformation, an unbiased grey model based on Markov optimization was established to predict railway settlement deformation.On the basis of unbiased optimization of the grey model, Markov correction is carried out to improve the prediction accuracy.Through the measured data of the settlement deformation of a high-speed railway, the prediction results of the model presented in this paper are compared with those of the grey model and the regression model, and the model presented in this paper has higher prediction accuracy and stability.