Using particle swarm optimization scheme to settlement prediction

To predict the settlement of foundations is an important issue in geotechnical engineering and one of the main concerns in design. The mechanism of particle swarm optimization (PSO) is inspired from the complex social behavior shown by the nature species. The advantage of PSO over many other optimization algorithms is its simplicity in implementation and its ability to converge to a reasonably good solution quickly. In this paper, PSO is used in an attempt to obtain accurate settlement prediction. The predicted settlements obtained by PSO are compared with those predicted by the least squares fitting method, Asaoka method and GA. The results show that PSO is a useful technique for predicting the settlement of foundations.