A novel combined intelligent algorithm prediction model for the tunnel surface settlement

Study on deformation of tunnel pile foundation based on discrete element method and finite difference method

The deformation of pile caused by tunnel excavation will weaken the bearing capacity of the foundation. In order to investigate the deformation response of pile induced by the construction of three-hole small spacing tunnel, the DEM-FDM (discrete element method and finite difference method) coupling numerical simulation method were used to simulate the deformation process of pile during tunnel excavation. This paper probed into the deformation response of pile by three factors: the length of pile, the pile-tunnel spacing, and the three-hole tunnel construction. The results showed that, as the pile-tunnel spacing decreases, the incremental horizontal displacement of the pile top became more significant when the three-hole tunnel was excavated. The excavation resulting in four zones of horizontal displacement concentration. The prominent locations were mainly concentrated on both sides of the tunnel and the ground directly above the tunnel. The research findings of this study can provide insights and references for the design and construction of shield tunneling under passing piles.

Multi-step real-time prediction of hard-rock TBM penetration rate combining temporal convolutional network and squeeze-and-excitation block

Accurate penetration rate prediction enhances rock-breaking efficiency and reduces disc cutter damage in tunnel boring machine (TBM) construction. However, this process faces significant challenges such as the high uncertainty of ground conditions and the complexity of maintaining optimal TBM operation in long and large tunnels. To address these challenges, we propose TCN-SENet++, a novel hybrid multistep real-time penetration rate prediction model that combines a temporal convolutional network (TCN) and a squeeze-and-excitation (SENet) block for aided tunneling. This study aims to demonstrate the application of TCN-SENet++, as well as other models such as RNN, LSTM, GRU, and TCN, for TBM penetration rate prediction. The model was developed using actual datasets collected from the Yin-Song diversion project. We employ a 30-s time step to predict the future time steps of the penetration rate (1st, 3rd, 5th, 7th, and 9th). The features that influence the penetration rate, such as the cutterhead torque, thrust, and cutterhead power, were considered. A comparative analysis using the mean absolute error and mean squared error revealed that the TCN-SENet++ model outperformed the other models, including RNN, LSTM, GRU, TCN, and TCN-SENet+. In comparison, TCN-SENet++ achieved average MSE reductions of 18%, 6%, 3%, 1%, and 2%, respectively. The TCN-SENet++ model demonstrated fewer errors in the new project, validating its effectiveness and suitability for real-time penetration rate prediction in TBM construction.

Prediction method of longitudinal surface settlement caused by double shield tunnelling based on deep learning

The deep learning method faces the challenges of small sample data and high dimensional shield operational parameters in predicting the longitudinal surface settlement caused by shield excavation. In this study, various optimization algorithms were compared, and the slime mould algorithm (SMA) was optimally chosen to optimize the hyperparameters of random forest (RF), and SMA-RF was used for dimensionality reduction and feature contribution analysis. A double-input deep neural network (D-DNN) framework was proposed for the prediction of surface settlement, which considers the influence of twin tunnels and effectively increases the high-fidelity data in the database. The results show that SMA performs best among various optimization algorithms; employing features that have a cumulative contribution value exceeding 90% as input can result in high prediction accuracy; there is significant uncertainty in the feature contribution analysis for small sample data; the reduced shield running parameters show a strong nonlinear relationship with surface settlement; compared with S-DNN, D-DNN takes into account the excavation of twin tunnels and expands the database capacity by more than 1.5 times, with an average increase of 27.85% in the R2 and an average decrease of 53.2% in the MAE.

Artificial Intelligence Methods for the Construction and Management of Buildings

Artificial intelligence covers a variety of methods and disciplines including vision, perception, speech and dialogue, decision making and planning, problem solving, robotics and other applications in which self-learning is possible. The aim of this work was to study the possibilities of using AI algorithms at various stages of construction to ensure the safety of the process. The objects of this research were scientific publications about the use of artificial intelligence in construction and ways to optimize this process. To search for information, Scopus and Web of Science databases were used for the period from the early 1990s (the appearance of the first publication on the topic) until the end of 2022. Generalization was the main method. It has been established that artificial intelligence is a set of technologies and methods used to complement traditional human qualities, such as intelligence as well as analytical and other abilities. The use of 3D modeling for the design of buildings, machine learning for the conceptualization of design in 3D, computer vision, planning for the effective use of construction equipment, artificial intelligence and artificial superintelligence have been studied. It is proven that automatic programming for natural language processing, knowledge-based systems, robots, building maintenance, adaptive strategies, adaptive programming, genetic algorithms and the use of unmanned aircraft systems allow an evaluation of the use of artificial intelligence in construction. The prospects of using AI in construction are shown.