In recent years, 3D laser scanning technology has been applied to tunnel engineering. Although more intelligent than traditional measurement technology, it is still challenging to estimate the real-time deformation of NATM tunnel excavation from laser detection and ranging point clouds. To further improve the measurement accuracy of 3D laser scanning technology in the tunnel construction process, this paper proposes an improved Kriging filtering algorithm. Considering the spatial correlation of the described object, the optimization method of point cloud grid filtering is studied. By analyzing the full-space deformation field of the tunnel lining, the deformation information of the measuring points on the surface of the tunnel lining is extracted. Based on the actual project, through the on-site monitoring comparison test, the three-dimensional laser point cloud data are grid processed and analyzed, and the deformation data obtained from the test are compared with the data measured by traditional methods. The experimental results show that the Kriging filtering algorithm can not only efficiently identify and extract the tunnel profile visualization data but also efficiently and accurately obtain the tunnel deformation. The measurement results obtained by using the proposed technology are in good agreement with those obtained by using traditional monitoring methods. Therefore, tunnel deformation monitoring based on 3D laser scanning technology can better reflect the evolution of the tunnel full-space deformation field under certain environmental conditions and can provide an effective safety warning for tunnel construction.

To provide theoretical support for the safety control of rectangular pipe jacking tunnels crossing an existing expressway, a method for predicting the surface settlement of a rectangular pipe jacking tunnel is proposed in this study. Therefore, based on the high approximation of the BP neural network to any function under the multiparameter input, the PSO-BP mixed prediction model of the ground subsidence of the ultrashallow buried large section rectangular pipe jacking tunnel is established by taking into account the adaptive mutation method, adopting the improved particle swarm optimization (IPSO) algorithm with adaptive inertia weight and mutation particles in the later stage to determine the optimal hyperparameters of the prediction model. Through the case study of an ultrashallow large cross-section rectangular pipe jacking tunnel, this algorithm is compared with the traditional algorithm and combined with field monitoring data for analysis and prediction. The prediction results show that compared with the traditional BP neural network prediction model, AWPSO-BP model and PWPSO-BP model, the improved PSO-BP mixed prediction model shows a more stable prediction effect when the change in surface subsidence is gentle and the concavity and convexity are large. The predicted subsidence value is close to the actual value, and the accuracy and robustness of the prediction are significantly improved.