Reinforcement learning-based optimizer to improve the steering of shield tunneling machine.

Reliable and timely prediction of the shield tunneling path is essential to avoid deviation and successfully complete a tunneling project. This study presents a reinforcement learning-based new optimal model for improving the forecasting accuracy of the shield tunneling path and alleviating shield drivers' over-reliance on their practical experience. This model integrates the Q-learning network with a metaheuristic gray wolf algorithm to explore and exploit the implicit information of the shield machine through Q-Table. The proposed method is applied to a field tunneling case with data collected from a real tunneling scenario in Tianjin City, China. The model is also evaluated using various numerical benchmark approaches and compared to a deep learning method. The results show that the proposed model produces an accurate prediction with a root-mean-square error of 0.539 and correlation coefficient of 0.925 for pitch values. A sensitivity analysis indicated that the thrust force and the buried depth have a significant influence on the prediction of shield tunneling trajectory. [ABSTRACT FROM AUTHOR]