Research on Prediction of Metro Surface Deformation Based on Ensemble Kalman Filter

Abstract

In order to improve the prediction ability of the statistical model of the subway surface deformation, the equal-dimensional innovation grey system theory model and Kalman filter model are used to predict the surface deformation of the subway. The ensemble Kalman filter (EnKF) algorithm is used to assimilate the two groups of prediction data to improve the accuracy of the prediction data. The absolute difference and the root mean square error between the EnKF assimilation prediction data, the Kalman filter prediction data, and the equal-dimensional and innovation grey model prediction data and the measured data are compared and analysed. The results show that the accuracy of EnKF assimilation prediction data is greatly improved compared with the prediction data of grey system theory model and Kalman filter model, and the short-term prediction effect is better.