Optimal design of pile wall retaining system during deep excavation using swarm intelligence technique

Abstract

In this paper, the efficiency of various metaheuristic optimization algorithms in the optimum design of pile wall retaining systems is investigated. To achieve this aim, an on-going Tabriz Metro station project with a deep excavation pit is selected as a case study. Subsequently, the detailed finite element model is developed in the OpenSees platform to perform the static analyses. Four different optimization techniques including Genetic, Particle swarm optimization, Bee, and Biogeography-based optimization algorithms are selected for the optimization purposes. The total cost of the retaining structures is considered as an objective function, which should be minimized in the design space of the variables. The results show the efficiency of the applied techniques in achieving an optimal design of the considered retaining system. However, it can be concluded that the performance of the Bee algorithm is most effective in both obtaining the minimum objective function with lower dispersion as well as rapid convergence among other different algorithms. Finally, the pile lateral deflection during the different excavation phases as well as the soil shear stress are investigated based on the obtained optimal results.