Application of an immune algorithm to settlement prediction

The settlement curve of the foundation endured the ramp load is an S-type curve, which is usually simulated via Poisson curve. Aimed at the difficulty of preferences in Poisson curve, an immune algorithm (IA) is used. IA is able to obtain a multiple quasi-optimum solution while maintaining the population diversity. In this paper, IA is used in an attempt to obtain accurate settlement prediction. The predicted settlements obtained by IA are compared with those predicted by the least squares fitting method (LSM), the Asaoka method and the genetic algorithm (GA). The results show that IA is a useful technique for predicting the settlement of foundations with an acceptable degree of accuracy and has much better performance than GA and the Asaoka methods.