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.

A simplified log creep model for describing triaxial creep of mélange rocks.

This study aims to develop a simplified log creep model (LgCM) for predicting the triaxial three-stage creep behaviors of mélange rocks. The model was deduced from the creep deformation mechanism by considering the competition of strain rate hardening and damage during the steady and accelerating creep stages and was described by two simplified fractal functions. The model was then compared with the previous creep models on the uniaxial three-stage creep data of mortar, rock salt, and sandy shale, as well as the triaxial low-stress creep data of claystone. Afterward, the triaxial creep experimental results of the mélange rock samples were introduced to illustrate the process of calibrating the model in predicting the triaxial three-stage creep behaviors of mélange rocks. It was found the developed LgCM model showed good performance in predicting both the uniaxial and triaxial three-stage creep behaviors of rocks. The investigation reveals that the trend of the parameter ß can indicate three thresholds of the hardening and damaging effects, and provide the equation to reproduce the creep behavior of the mélange rock. The work contributes to understanding the time-dependent failure of underground rock mass in mélange rock formations.