A spatiotemporal deep learning method for excavation-induced wall deflections

Data-driven approaches such as neural networks are increasingly used for deep excavations due to the growing amount of available monitoring data in practical projects.However,most neural network models only use the data from a single monitoring point and neglect the spatial relationships between multiple monitoring points.Besides,most models lack flexibility in providing predictions for multiple days after monitoring activity.This study proposes a sequence-to-sequence(seq2seq)two-dimensional(2D)convolutional long short-term memory neural network(S2SCL2D)for predicting the spatiotemporal wall deflections induced by deep excavations.The model utilizes the data from all monitoring points on the entire wall and extracts spatiotemporal features from data by combining the 2D convolutional layers and long short-term memory(LSTM)layers.The S2SCL2D model achieves a long-term prediction of wall deflections through a recursive seq2seq structure.The excavation depth,which has a significant impact on wall deflections,is also considered using a feature fusion method.An excavation project in Hangzhou,China,is used to illustrate the proposed model.The results demonstrate that the S2SCL2D model has superior prediction accuracy and robustness than that of the LSTM and S2SCL1D(one-dimensional)models.The prediction model demonstrates a strong generalizability when applied to an adjacent excavation.Based on the long-term prediction results,practitioners can plan and allocate resources in advance to address the potential engineering issues.

Multi-objective optimization-based prediction of excavation-induced tunnel displacement

This paper proposes an inverse method for improving the prediction of tunnel displacements during adjacent excavation.In this framework,staged data assimilation and parameter identification are conducted using the multi-objective particle swarm optimization algorithm.Recent monitoring data are assumed to be more informative and assigned more weights in the multi-objective optimization to improve the prediction accuracy.Then,an empirical formula is applied to correct the time effect of tunnel displacement.The Kriging method is introduced to surrogate the finite element model to reduce computational cost.The proposed framework is verified using a typical staged“excavation nearing tunnel”case.The predictions using the updated parameters are in good agreement with the measurements.The identified values of underlying soil parameters are within the typical ranges for the unloading condition.The updated time effect indicates that tunnel displacements may develop excessively in the three months after the region S1-B is excavated to the bottom.The maximum vertical tunnel displacement may increase from the currently measured 12 mm to the calculated 26 mm if the later construction is suspended long enough.Subsequent constructions need to be timely conducted to restrain the time effect and control tunnel displacements.