Tunnel Boring Machines (TBMs) typically consist of a rotating cutter head that breaks up the rock or soil and a conveyor system that removes the excavated material. TBMs are preferred over traditional drill and blast techniques due to their higher efficiency, safer working conditions, minimal environmental disturbance, and reduced project costs. TBMs have become prevalent in tunnel construction due to their high efficiency and reliability. The proliferation of data obtained from site investigations and data acquisition systems provides an opportunity for the application of machine learning (ML) techniques. ML algorithms have been successfully applied in TBM tunneling because they are particularly effective in capturing complex, non-linear relationships.
Literature | Data Processing a | Algorithms b | Hyperparameter Tuning c |
Targets d | Data Size and Data Set |
---|---|---|---|---|---|
Grima et al. [26] | PCA | MR, ANN, ANFIS | - | PR, AR | 640 tunnel project |
Benardos and Kaliampakos [31] | - | ANN | - | AR | 11-Athens metro |
Tiryaki [28] | PCA | MR, ANN | - | specific energy | 44-Three tunnel projects |
Mikaeil et al. [41] | - | FL | - | Penetrability | 151-Queens water tunnel |
Yagiz [59] | PCC | MR, ANN | - | PR | 151-Queens water tunnel |
Javad and Narges [60] | - | ANN | - | PR | 185-Three tunnel projects |
Mahdevari et al. [43] | - | MR, SVM | - | PR | 151-Queens water tunnel |
Salimi et al. [27] | PCA | MR, SVM, ANFIS | - | FPI | 75-Zagros lot 1B and 2 |
Armaghani et al. [30] | - | ANN | PSO, ICA | PR | 1286-Pahang-Selangor raw water transfer |
Armaghani et al. [61] | - | MR, GEP | - | PR | 1286-Pahang-Selangor raw water transfer |
Sun et al. [18] | Kriging interpolation, rate of change | RF | - | TH, TO, PR | 88-Shenzhen metro |
Armaghani et al. [55] | - | ANN | PSO, ICA | AR | 1286-Pahang-Selangor raw water transfer |
Koopialipoor et al. [62] | - | ANN, DNN | - | PR | 1286-Pahang-Selangor raw water transfer |
Salimi et al. [48] | PCA | MR, CART, GP | - | FPI | 580-Seven tunnel projects |
Zhang et al. [47] | PCC | RF | PSO | TO, TH, PR, FP | 294-Changsha metro line 4 |
Koopialipoor et al. [63] | - | ANN | firefly algorithm | PR | 1200-Pahang-Selangor raw water transfer |
Mokhtari and Mooney [44] | PCC, Relief | SVM | BO | PR | Northgate Link tunnel |
Wang et al. [64] | - | ANN, LSTM, RF, SVM | - | AR | 806-Nanning metro line 1 |
Zhang et al. [49] | - | SVM, CART, RF, bagging, Ada boosting | BO | PR | 151-Queens water tunnel |
Zhang et al. [22] | WT, MD, GRG | LSTM, RF | PSO | TH, TO, PR, RPM, CP | 3549-Changsha metro line 4 and Zhengzhou metro line 2 |
Zhou et al. [65] | - | ANN, GP | - | AR | 1286-Pahang-Selangor raw water transfer |
Bai et al. [45] | PCC, Seasonal-trend decomposition | MR, SVM, DT, GBoost | - | TO, TH, FP | 450-Xi’an metro |
Bardhan et al. [66] | - | hybrid ensemble model | - | PR | 185-Three tunnel project |
Harandizadeh et al. [56] | - | ANFIS-PNN | ICA | PR | 209-Pahang-Selangor raw water transfer |
Lin et al. [67] | - | MR, ANN, SVM, LSTM, GRU, EML | PR | 1000-Shenzhen railway | |
Parsajoo et al. [42] | - | ANFIS | artificial bee colony | FPI | 150-Queens water tunnel |
Zeng et al. [35] | - | EML | PSO | AR | 1286-Pahang-Selangor raw water transfer |
Zhou et al. [54] | - | XGBoost | BO | AR | 1286-Pahang-Selangor raw water transfer |
Zhou et al. [50] | - | ANN, RF, XGBoost, SVM | GWO, PSO, SCA, SSO, MVO, MFO | PR | 1286-Pahang-Selangor raw water transfer |
Lin et al. [25] | - | LSTM | PSO | TH | 1500-Shenzhen railway |
Lin et al. [68] | - | GRU | PSO | TO | 1500-Shenzhen railway |
Salimi et al. [69] | - | MR, CART | - | FPI | 666-Eight tunnel projects |
Yang et al. [3] | - | SVM | GWO, biogeography-based optimisation | PR | 503-Shenzhen metro line |
Model Type | Dataset | Data Size | Parameters | Open Access | Limitations |
---|---|---|---|---|---|
Model A | 640 tunnel projects | - | Geological conditions, Operational parameters, TBM type and size |
No | hard to access |
Model B | Queen water tunnel | 151 | Geological conditions | Yes | overfitting or lack of generalisability |
Model C | Pahang-Selangor raw water transfer | 1286 | Geological conditions, Operational parameters |
Yes | hard to apply in practice |
Literature | Data Processing | Algorithms a | Hyperparameter Tuning | Targets | Data Size and Data Set |
---|---|---|---|---|---|
Suwansawat and Einstein [32] | - | ANN | - | Smax | 49-Bangkok subway project |
Boubou et al. [75] | - | ANN | - | S(X) | 432-Toulouse subway line B |
Pourtaghi and Lotfollahi-Yaghin [33] | - | Wavelet-ANN | - | Smax | 49-Bangkok subway project |
Dindarloo and Siami-Irdemoosa [76] | PCC | CART | - | Smax | 34-Various tunnel projects |
Goh et al. [77] | - | MARS | - | Smax | 148-Three Singapore MRT projects |
Chen et al. [24] | PCC | ANN, RBF, GRNN | - | Smax | 200-Changsha metro line 4 |
Zhang et al. [47] | PCC | RF | PSO | Smax | 294-Changsha metro line 4 |
Zhang et al. [34] | PCC | ANN, SVM, RF, EML, GRNN | PSO | Smax | 294-Changsha metro line 4 |
Zhang et al. [22] | WT, MD, GRG | LSTM, RF | PSO | Smax | 423-Changsha metro line 4 |
Zhang et al. [78] | PCC | XGBoost, ANN, SVM, MARS | - | Smax | 148-Three Singapore MRT projects |
Kannangara et al. [46] | PCC, sequential feature selection, Boruta algorithm | RF | - | Smax | 264-Hangzhou metro line 2 and line 6 |
Literature | Data Processing a | Algorithms b | Hyperparameter Tuning | Targets c | Data Size and Data Set |
---|---|---|---|---|---|
Guo et al. [20] | WT | Elman RNN | PSO | longitudinal settlement | Jiangji subway tunnel |
Zhang et al. [79] | WT | ANN, SVM | - | daily settlement | 60-Wuhan metro line 2 |
Gao et al. [37] | - | RNN, LSTM, GRU, SVM. RF, Lasso | - | TO, TH, AR, CP | 3000-Shenzhen metro |
Zhou et al. [23] | WT | ARIMA, LSTM, CNN-LSTM | - | HDSH, HDST, VDSH, VDST, roll, pitch |
5005-Sanyang Road Tunnel |
Gao et al. [80] | 3-sigma rule, MA, GRG | GRU | genetic algorithm | earth pressure | 1538-Luoyang metro line 2 |
Erharter and Marcher [81] | PCC | LSTM, RF, SVM | - | TO | 200,000-Brenner base tunnel |
Feng et al. [13] | 3-sigma rule, WT | DBN | - | FPI | 8915-Yingsong water diversion project |
Gao et al. [82] | - | ARIMA, RNN, LSTM | - | PR | Hangzhou second water source project |
Li et al. [2] | PCC | LSTM | - | TO, TH | 4650-Yingsong water diversion project |
Qin et al. [36] | cosine similarity | CNN-LSTM, XGBoost, RF, SVM, LSTM, RNN, CNN | - | TO | 150,000-Singapore metro T225 project |
Shi et al. [39] | WT, variational mode decomposition | LSTM, CNN, RNN, SVM, RF | - | TO | 60,000-Singapore metro T225 project |
Wang et al. [21] | WT, light gradient boosting machine | LSTM | - | PR, TO | 25,543-Sutong gas transmission line |
Xu et al. [14] | 3-sigma rule, MA, PCC | SVM, RF, CNN, LSTM, GBoost, KNN, Bayesian ridge regression | - | PR, TO, TH, RPM | 7000-Yingsong water diversion project |
Zhang et al. [83] | - | RF | - | Smax | 386-Changsha Metro Line 4 |
Huang et al. [53] | SelectKBest | LSTM | BO | TO | Yingsong water diversion project |
Shan et al. [19] | MA | RNN, LSTM | - | PR | 463-Changsha metro line 4 and Zhengzhou metro line 2 |
Shen et al. [17] | WT, Kriging interpolation | LSTM, SVM, RNN | - | HDSH, HDST, VDSH, VDST, roll, pitch | 1200-Shenzhen intercity railway |
Zhang et al. [29] | PCA, PCC | GRU, RNN, SVM | - | HDSH, HDST, VDSH, VDST, | 22,010-Guang-Fo intercity railway |
Literature | Category | Historical Data | Forecast Horizon | ||
---|---|---|---|---|---|
Step behind | Distance behind | Step ahead | Distance ahead | ||
Gao et al. [37] | high-frequency | 5 steps | 1.25 mm a | 1 step | 0.25 mm a |
Qin et al. [36] | 10 steps | - | 1 step | - | |
Huang et al. [53] | 6 steps | 22.4 mm a | 1 step | 3.73 mm a | |
Erharter and Marcher [81] | 50 steps | 2.75 m | 1 or 100 steps | 0.055 or 5.5 m | |
Shi et al. [39] | 10 steps | - | 1–5 steps | - | |
Gao et al. [80] | low-frequency | 5 steps | 7.5 m | 1 step | 1.5 m |
Feng et al. [13] | 7 steps | 7 m | 1 step | 1 m | |
Shan et al. [19] | 5 steps | 7.5 m | 1–5 steps | 1.5–7.5 m |
This entry is adapted from the peer-reviewed paper 10.3390/eng4020087