Extension of an Autopilot Model of Shield Tunneling Machines to Curved Section using Machine Learning

Although a shield tunneling machine should excavate a tunnel along its planned alignment, deviations occur between the planned alignment and the actual result. In this case, the deviating shield machine should return to the planned alignment gradually. However, because controlling the shield machine is difficult and time-consuming, and excavation managers and operators are aging, their skills may be lost in the near future. Artificial intelligence is expected to play an important role in automating the operation of shield tunneling machines, but the method proposed by the authors and the methods of related studies could not automatically calculate the optimum operation parameters for a curved section of the planned alignment. Therefore, in this research, the purpose is to develop an autopilot model that automatically calculates optimal operation parameters of the shield machine for straight and curved sections of the planned alignment, based on the method proposed by the authors. Besides, the effectiveness of the developed model was evaluated using the sensing data from a previously constructed tunnel.