The structural engineering is subject to various subjective and objective factors, the deformation is usually inevitable, the deformation monitoring data usually are nonstationary and nonlinear, and the deformation prediction is a difficult problem in the field of structural monitoring. Aiming at the problems of the traditional structural deformation prediction methods, a structural deformation prediction model is proposed based on temporal convolutional networks (TCNs) in this study. The proposed model uses a one‐dimensional dilated causal convolution to reduce the model parameters, expand the receptive field, and prevent future information leakage. By obtaining the long‐term memory of time series, the internal time characteristics of structural deformation data can be effectively mined. The network hyperparameters of the TCN model are optimized by the orthogonal experiment, which determines the optimal combination of model parameters. The experimental results show that the predicted values of the proposed model are highly consistent with the actual monitored values. The average RMSE, MAPE, and MAE with the optimized model parameters reduce 44.15%, 82.03%, and 66.48%, respectively, and the average running time is reduced by 45.41% compared with the results without optimization parameters. The average RMSE, MAE, and MAPE reduce by 26.88%, 62.16%, and 40.83%, respectively, compared with WNN, DBN‐SVR, GRU, and LSTM models.

Techniques including pre‐grouting, long pipe roof, and parameter optimization were employed to ensure the safety of loess metro tunnelling under an existing glass building. Their effects were proved through monitoring the settlement of building and surface during tunnelling. Besides, division of settlement monitoring according to processes, a new method, was conducted to control settlement in time. The highest surface settlement after construction was 16 mm only, meeting the requirement. The result indicates that it is practicable to control the tunnelling settlement strictly in extremely difficult geological areas. The settlement regularities were also studied through numerical simulation; their deformation is larger compared with in situ results while their change trends coincide during most processes. Soil excavations cause settlement primarily, accounting for more than 60%. It is suggested that dual slurry pre‐grouting and process‐based measurement should be employed before each excavation in water‐rich loess areas.