Adaptive Neuro-Fuzzy Inference System for High-Speed Computing in Optimal Shape Design of Arch Dams Subjected to Earthquake Loading#

An efficient methodology is proposed to find optimal shapes of arch dams, including fluid-structure interaction for earthquake loading. The optimization is implemented using a particle swarm optimization (PSO). In order to reduce the computational cost of the optimization process, an adaptive neuro-fuzzy inference system (ANFIS) is utilized to predict the arch dam response instead of directly evaluating it by a time-consuming finite element analysis (FEA). The presented ANFIS is compared with a back-propagation neural network (BPNN) and appears to have better performance. Test example results demonstrate the computational advantages of the proposed method for the optimal design of arch dams when compared with those of obtained through FEA.