Abstract
The flower pollination algorithm (FPA) is an efficient metaheuristic optimization algorithm mimicking the pollination process of flowering species. In this study, FPA is applied, for the first time, to the optimum design of reinforced concrete (RC) cantilever retaining walls. It is found that FPA offers important savings with respect to conventional design approaches and that it outperforms genetic algorithm (GA) and the particle swarm optimization (PSO) algorithm in this design problem. Furthermore, parameter tuning reveals that the best FPA performance is achieved for switch probability values ranging between 0.4 and 0.7, a population size of 20 individuals and a Levy flight step size scale factor of 0.5. Finally, parametric optimum designs show that the optimum cost of RC retaining walls increases rapidly with the wall height and smoothly with the magnitude of surcharge loading.
Accepted Version (
Free)
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call