In order to mitigate the risk of equipment damage or jamming disasters caused by overloading when a tunnel boring machine (TBM) excavates in adverse geological conditions, which can negatively affect the project schedule, data from the Tianshan Shengli Tunnel project was used to investigate TBM load prediction. First, outliers in the cyclic segment data were removed utilizing the interquartile range (IQR) criterion, and the data was subsequently normalized. Then, feature parameters with strong causal relationships to two load parameters, cutterhead torque and thrust, were selected as input features through the independent component analysis-based linear non-Gaussian acyclic model (ICA-LiNGAM) method. Finally, a gated recurrent unit (GRU) prediction model incorporating a self-attention mechanism (SAM) was constructed, and the internal decision-making mechanism of the model was analyzed utilizing the Shapley additive explanations (SHAP) method. The results show that the prediction accuracy and computational efficiency of the model can be improved through feature screening and the introduction of a self-attention mechanism. A goodness-of-fit (R2) of 0.899 1 and 0.955 9 for the TBM load cutterhead torque and thrust, respectively, is achieved by the CX-SAM-GRU prediction model, and good generalization ability is exhibited under different engineering geological conditions. It is indicated by the importance analysis that the prediction results of cutterhead torque are largely influenced by thrust and advance rate, whereas the prediction results of thrust are largely influenced by cutterhead water spray flow, cutterhead rotation speed, and propel pump pressure. The robustness of this method for multi-step prediction results of thrust is superior to that of cutterhead torque, and the cutterhead torque prediction is generally more sensitive to closer time steps. It is concluded that a theoretical reference for TBM load prediction in practical engineering can be provided, and support for safe on-site construction can be offered.
ZHOU Zhen-liang, WANG Man, YUE Yi-mei, LI Hao-kai.
TBM Load Prediction Based on CX-SAM-GRU Model[J].
Science Technology and Engineering, 2026, 26(31): 13665-13677 DOI:10.12404/j.issn.1671-1815.2600094
QianQihu, LiChaofu, FuDeming. Application status and prospects of tunnel boring machines in underground engineering in China[J]. Underground Space, 2002(1): 1-11, 93.
WangChao, QiaoShifan, LiuHongzhong. Research on force calculation model for disc cutters in TBM rock-breaking process[J]. Engineering Mechanics, 2021, 38(10): 54-63.
[7]
SheL, HuC, LiY, et al. A specific energy and penetration interaction-based method for optimizing TBM operational parameters in hard rock[J]. Tunnelling and Underground Space Technology, 2025, 161: 106585.
ZhaoSiguang, WangMingnian, TongJianjun, et al. Research on intelligent classification model of tunnel surrounding rock based on multivariate feature mining of drilling parameters[J]. Tunnel Construction, 2024, 44(12): 2469-2479.
YeMing, WuGensheng, YuHongwei, et al. Classification prediction method for surrounding rock based on TBM penetration rate grade matrix[J]. Modern Tunnelling Technology, 2024, 61(S1): 205-214.
ZhangQinglong, ZhuYanwen, MaRui, et al. Research on TBM tunneling parameters prediction based on attention-enhanced Bi-LSTM model[J]. Modern Tunnelling Technology, 2022, 59(4): 69-80.
[14]
WuZ, WeiR, ChuZ, et al. Real-time rock mass condition prediction with TBM tunneling big data using a novel rock-machine mutual feedback perception method[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2021, 13(6): 1311-1325.
ZhangWengang, TangLibin, ChenFuyong, et al. Prediction of TBM tunneling speed based on four hyperparameter optimization algorithms and random forest model[J]. Journal of Basic Science and Engineering, 2021, 29(5): 1186-1200.
HouShaokang, LiuYaoru, ZhangKai. Prediction of TBM tunneling parameters based on IPSO-BP hybrid model[J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(8): 1648-1657.
[19]
GaoB, WangR R, LinC, et al. TBM penetration rate prediction based on the long short-term memory neural network[J]. Underground Space, 2021, 6(6): 718-731.
ManKe, CaoZixiang, LiuXiaoli, et al. Prediction of TBM tunneling parameters based on GRU-RF model[J]. Journal of Basic Science and Engineering, 2023, 31(6): 1519-1539.
[22]
LiuZ, WangY, LiL, et al. Realtime prediction of hard rock TBM advance rate using temporal convolutional network (TCN) with tunnel construction big data[J]. Frontiers of Structural and Civil Engineering, 2022, 16(4): 401-413.
ZhangChi, LiYan, WangPeng, et al. Prediction of tunneling performance in stable stage of tunnel boring machine based on gated recurrent unit[J]. Science Technology and Engineering, 2022, 22(32): 14443-14450.
ZhuMengqi, ZhuHehua, WangXin, et al. Prediction of TBM tunneling parameters and surrounding rock grade based on ensemble CART algorithm[J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(9): 1860-1871.
SunJiahao, WangWenjie, XieLianku. Short-term rockburst prediction model based on microseismic monitoring and probability-optimized naive Bayes[J]. Rock and Soil Mechanics, 2024, 45(6): 1884-1894.
[29]
CaoY, DingY, JiaM, et al. A novel temporal convolutional network with residual self-attention mechanism for remaining useful life prediction of rolling bearings[J]. Reliability Engineering & System Safety, 2021, 215: 107813.
[30]
HuZ, GaoY, JiS, et al. Improved multistep ahead photovoltaic power prediction model based on LSTM and self-attention with weather forecast data[J]. Applied Energy, 2024, 359: 122709.
[31]
MengS, ShiZ, GutierrezM. Interpretable CEEMDAN-SMA-LSSVM hybrid model for predicting shield tunnel-induced settlement[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2025, 17(10): 6179-6194.
[32]
ZhangQ, ZhaoX, DuL, et al. Bayesian ensemble learning for rockburst grade prediction in high geo-stress TBM tunnels with SHAP-based interpretability[J]. Engineering Failure Analysis, 2026, 185: 110425.
ZhenJiajie, LaiFengwen, HuangMing, et al. Based on LightGBM-Informer long time series prediction model for segment floating in shield tunnels[J]. Rock and Soil Mechanics, 2024, 45(12): 3791-3801.