Study on the Optimization Method for the Deformation Prediction of Tunnel Construction on Adjacent Bridge Piles

Tunnel construction will affect the normal use and safety of adjacent existing bridges. To improve the precision of prediction models, this paper proposes a new method based on the particle swarm optimization (PSO) algorithm and the general regression neural network (GRNN). First, employing the technology of neural network to build up a regression model based on the original data acquired by one adjacent bridge piles monitoring, and takes advantage of PSO algorithm to optimize the parameters of the network, which is believed to reduce the adverse influence of human-induced factors in model construction. Then, two major influence factors, including the maximum induced tangential stress on the boundaries of tunnels or caverns and the elastic energy index of the rock are selected as the inputs for establishing the PSO-GRNN model. The generated PSO-GRNN model is finally applied to predict the deformation in which the feasibility and applicability of the proposed approach are illustrated. It indicates that the PSO-GRNN model can improve the predicting precision, as well as significantly guiding the construction.