Dynamic prediction of mechanized shield tunneling performance

Abstract Slurry pressure balance shield, a kind of tunnel boring machine, is significantly affected by the operation parameters such as advance speed and torque. In this study, a dynamic regulation model is established based on wavelet transform and bidirectional long short-term memory method (Bi-LSTM) to predict advance speed and torque. For comparison, twenty parameters of the shield machine are input to predict the tunneling behavior through the Bi-LSTM model and the LSTM model. Comparison results indicate that the proposed model has a relatively high accuracy. Moreover, parametric sensitivity analysis is made to filter the parameters by using light gradient boosting machine, so that the ranking of importance for all parameters can be gained. The proposed dynamic regulation model is validated by the Sutong gas-insulated transmission line project in China with a complex underwater-work condition, which has a guiding significance in operating and adjusting the shield machine in a dynamic process.

[1]  Roland R. Draxler,et al.  Root mean square error (RMSE) or mean absolute error (MAE) , 2014 .

[2]  Zheng Liu,et al.  Human Reliability Assessment of Ergonomic Interaction Design for Engineering Software Based on Entropy–FTA–Delphi , 2020 .

[3]  Jürgen Schmidhuber,et al.  Learning Precise Timing with LSTM Recurrent Networks , 2003, J. Mach. Learn. Res..

[4]  Jürgen Schmidhuber,et al.  Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[5]  S. Shen,et al.  Approach based on TOPSIS and Monte Carlo simulation methods to evaluate lake eutrophication levels. , 2020, Water research.

[6]  Nakwan Kim,et al.  Dynamic model identification of unmanned surface vehicles using deep learning network , 2018, Applied Ocean Research.

[7]  Kazushi Ikeda,et al.  A new criterion using information gain for action selection strategy in reinforcement learning , 2004, IEEE Transactions on Neural Networks.

[8]  M. Mooney,et al.  A simplified excavation chamber pressure model for EPBM tunneling , 2020 .

[9]  Kwok-wing Chau,et al.  Improving Forecasting Accuracy of Annual Runoff Time Series Using ARIMA Based on EEMD Decomposition , 2015, Water Resources Management.

[10]  Tommy H.T. Chan,et al.  Hybrid meta-heuristic and machine learning algorithms for tunneling-induced settlement prediction: A comparative study , 2020 .

[11]  Yunpeng Wang,et al.  Long short-term memory neural network for traffic speed prediction using remote microwave sensor data , 2015 .

[12]  Jinhui Li,et al.  Advanced prediction of tunnel boring machine performance based on big data , 2021, Geoscience Frontiers.

[13]  Xin Wang,et al.  Similarity search and performance prediction of shield tunnels in operation through time series data mining , 2020, Automation in Construction.

[14]  Li Lin,et al.  Remaining useful life estimation of engineered systems using vanilla LSTM neural networks , 2018, Neurocomputing.

[15]  Lieyun Ding,et al.  Hybrid Support Vector Machine Optimization Model for Prediction of Energy Consumption of Cutter Head Drives in Shield Tunneling , 2019, Journal of Computing in Civil Engineering.

[16]  Wenli Liu,et al.  Global sensitivity analysis of influential parameters for excavation stability of metro tunnel , 2020 .

[17]  Guofang Gong,et al.  Precision versus intelligence: Autonomous supporting pressure balance control for slurry shield tunnel boring machines , 2020 .

[18]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.

[19]  Shui-Long Shen,et al.  Dynamic prediction of jet grouted column diameter in soft soil using Bi-LSTM deep learning , 2020 .

[20]  Shui-Long Shen,et al.  Modelling the performance of EPB shield tunnelling using machine and deep learning algorithms , 2021 .

[21]  Shui-Long Shen,et al.  Prediction Model of Shield Performance During Tunneling via Incorporating Improved Particle Swarm Optimization Into ANFIS , 2020, IEEE Access.

[22]  Guan Chen,et al.  Main frequency band of blast vibration signal based on wavelet packet transform , 2019, Applied Mathematical Modelling.

[23]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[24]  Dingli Zhang,et al.  Movements of ground and existing structures induced by slurry pressure-balance tunnel boring machine (SPB TBM) tunnelling in clay , 2020 .

[25]  J. M. Rodríguez,et al.  Prediction and analysis of subsidence induced by shield tunnelling in the Madrid Metro extension , 2002 .

[26]  Zhengjun Xi.  Information gain and information leak in quantum measurements , 2016 .

[27]  Lieyun Ding,et al.  Dynamic prediction for attitude and position in shield tunneling: A deep learning method , 2019, Automation in Construction.

[28]  J. Kent.  Information gain and a general measure of correlation , 1983 .

[29]  E. J. Chen,et al.  Effect of spatial variation of strength and modulus on the lateral compression response of cement-admixed clay slab , 2015 .

[30]  Guofang Gong,et al.  Predictive control of slurry pressure balance in shield tunneling using diagonal recurrent neural network and evolved particle swarm optimization , 2019, Automation in Construction.

[31]  Lei Zhang,et al.  Probabilistic stability analyses of undrained slopes by 3D random fields and finite element methods , 2017, Geoscience Frontiers.

[32]  Min-Yu Gao,et al.  Real-Time Dynamic Earth-Pressure Regulation Model for Shield Tunneling by Integrating GRU Deep Learning Method With GA Optimization , 2020, IEEE Access.

[33]  Qiyue Li,et al.  An experimental study of a novel liquid carbon dioxide rock-breaking technology , 2020 .

[34]  Sílvio Mariano,et al.  A bat optimized neural network and wavelet transform approach for short-term price forecasting , 2018 .

[35]  B. Grung,et al.  Determination of optimum number of components in partial least squares regression from distributions of the root‐mean‐squared error obtained by Monte Carlo resampling , 2018 .

[36]  Kun Zhang,et al.  Evolutionary hybrid neural network approach to predict shield tunneling-induced ground settlements , 2020 .

[37]  T. Chai,et al.  Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature , 2014 .

[38]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[39]  Karsten Schulz,et al.  Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks , 2018, Hydrology and Earth System Sciences.

[40]  Kleanthis Thramboulidis,et al.  A cyber-physical system-based approach for industrial automation systems , 2014, Comput. Ind..

[41]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.