A Study of Prediction of Ground Settlement of Shield Tunnel Based on EEMD-BO-GRU Algorithm

Abstract Because the finite element method cannot meet the needs of shield tunnel engineering, multiple linear regression and traditional machine learning algorithms are difficult to effectively solve the shield tunnel’s nonlinear and non-stationary ground surface settlement data. Based on the Gated Recurrent Unit (GRU) algorithm of Ensemble empirical mode decomposition (EEMD) and Bayesian optimization (BO), this paper puts forward a prediction method of ground surface settlement during shield tunneling. Taking the shield tunnel construction of Zhijiang Road in Hangzhou as an example, by comparing with the traditional machine learning algorithm, the results show that RMSE, MAE, and MAPE of this algorithm are increased by 1.9313 mm, 1.7526 mm, and 4.9553%. It can be explained that this method has higher prediction accuracy and a more stable prediction effect, and the EEMD algorithm can effectively improve the generalization ability of the algorithm.