Modeling and Prediction for the thrust on EPB TBMs under different geological conditions by considering mechanical decoupling

EPB TBMs(Earth pressure balance Tunneling Boring Machines) are extensively used in tunneling constructions because of its high efficiency and low disturbance on structures above ground. It is critically significant to predict the thrust acting on TBMs under different geological conditions for both the design of power system and the control of tunneling process. The interaction between the cutterhead and the ground is the core of excavation, through which geological conditions determine the thrust re-quirement combined with operating status and structural characteristics. This paper conducted a mechanical decoupling analysis to obtain a basic expression of the cutterhead-ground interactive stress. Then more engineering factors(such as cutterhead topological structure, underground overburden, thrusts on other parts, etc.) were further considered to establish a predicting model for the total thrust acting on a machine during tunneling. Combined with three subway projects under different geological conditions in China, the model was verified and used to analyze how geological, operating and structural parameters influence the acting thrust.

A data-driven approach for modeling and predicting the thrust force of a tunnel boring machine

Thrust prediction of a tunnel boring machine(TBM)is crucial for the life span of disc cutters,cost forecasting,and its design optimization.Many factors affect the thrust of a TBM.The rock pressure on the shield,advance speed,and cutter water pressure will all have a certain impact.In addition,geological conditions and other random factors will also influence the thrust and greatly increase the difficulty of modeling it,seriously affecting the efficiency of tunnel excavation.To overcome these challenges,this paper establishes a thrust prediction model for the TBM based on the combination of on-site quality record data and surrogate model technology.Firstly,the thrust composition and influencing factors are analyzed and the thrust is modeled using a surrogate model based on field data.After main factor screening based on the Morris method,the accuracy of the surrogate model is greatly improved.The Kriging model with the highest accuracy is selected to model the thrust and predict the thrust of the unexcavated section.The results show that the thrust model has better thrust prediction by selecting similar conditions for modeling and reasonably increasing modeling samples.The thrust prediction method of TBM based on the combination of field data and surrogate model can accurately predict the dynamic thrust of the load and can also accurately estimate its statistical characteristics and effectively improve the excavation plan.