Abstract: In order to solve the problem of inaccurate prediction of the attitude during shield construction, a prediction method of EMDGRU (empirical mode decompositiongated recurrent unit) shield vertical posture based on optimal combination weighted EMDGRU is proposed. First, the acquired vertical attitude data (pitch angle) are preprocessed; Second, in order to improve the prediction accuracy of the model, the original data set is divided into several relatively stable subsequences based on EMD; Third, based on GRU neural network, the prediction model for each subsequence is established respectively; Finally, the prediction results of each subsequence are merged based on the optimal combination weighting method to get the final prediction results of the model. In order to verify the reliability of the established EMDGRU prediction model, it is applied to shield construction project of Kunming metro line 5, and the results are compared with the prediction results of GRU, SVR, and BP models. The results show that the EMDGRU prediction model has high prediction accuracy and generalization ability, which provides a new idea for accurate prediction of shield attitude.

Key words: metro tunnel, shield construction, vertical attitude prediction, empirical mode decomposition(EMD), gated recurrent unit(GRU)