Optimal earth pressure balance control for shield tunneling based on LS-SVM and PSO

To avoid ground deformation in the process of earth pressure balance (EPB) shield tunneling, it is necessary to keep the earth pressure balance on excavation face. However, at present the earth pressure control depends mainly on operation experiences which is hysteretic and could result in slow response to the change of earth pressure. To solve these problem, a predictive control strategy for earth pressure balance during excavation is proposed in this paper, where an earth pressure prediction model taking advance speed and screw conveyor speed as the control parameters is established by means of least squares support vector machine (LS-SVM). Further, by minimizing the difference between the predicted earth pressure and the desired one, an optimization model of the control parameters is established, and solved by the particle swarm optimization (PSO) algorithm. Therefore, an optimal EPB control scheme for shield tunneling automatically is presented here. The simulation results demonstrate that the method presented in this paper is very effective to control earth pressure balance.

Research Highlights
► We propose a predictive control strategy for excavation face balance during shield tunneling.
► We establish a prediction model of earth pressure in excavation chamber by means of LS-SVM.
► We establish an optimization model of control parameters based on the prediction model. It can minimize the difference between the predicted earth pressure and the desired one.
► We solve it by using PSO algorithm for the optimal control parameters.