Search

Abstract: The main aim of this paper is to propose an efficient soft computing based methodology to achieve optimal shape design of arch dams subjected to natural frequency constraints. Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) as two popular metaheuristics are employed to perform optimization task. As in the present paper fluid–structure interaction is considered, computing the natural frequencies by Finite Element Analysis (FEA) during the optimization process is time consuming. In order to reduce the computational burden, Back Propagation (BP) and Radial Basis Function (RBF) neural networks are used to predict the arch dam natural frequencies. The numerical results show that PSO incorporating BP provides the best results. [Copyright &y& Elsevier]

Abstract: An efficient optimization procedure is introduced to find the optimal shapes of arch dams considering fluid–structure interaction subject to earthquake loading. The optimization is performed by a combination of simultaneous perturbation stochastic approximation (SPSA) and particle swarm optimization (PSO) algorithms. This serial integration of the two single methods is termed as SPSA–PSO. The operation of SPSA–PSO includes three phases. In the first phase, a preliminary optimization is accomplished using the SPSA. In the second phase, an optimal initial swarm is produced using the first phase results. In the last phase, the PSO is employed to find the optimum design using the optimal initial swarm. The numerical results demonstrate the high performance of the proposed strategy for optimal design of arch dams. The solutions obtained by the SPSA–PSO are compared with those of SPSA and PSO. It is revealed that the SPSA–PSO converges to a superior solution compared to the SPSA and PSO having a lower computation cost. [Copyright &y& Elsevier]

An efficient methodology is proposed to find the optimum shape of arch dams considering fluid-structure interaction subject to earthquake loading. The earthquake load is considered by time variant ground acceleration applied in the upstream-downstream direction of the arch dam. The optimization is carried out by particle swarm optimization, employing real values of design variables. To reduce the computational cost of the optimization process, two strategies are adopted. In the first strategy, the most influential design variables on arch-dam response from original variables are selected using an adaptive neuro-fuzzy inference system. In the second, arch-dam response is predicted by a properly trained wavelet radial basis function neural network employing the influential design variables as the inputs. In order to assess the effectiveness of the suggested methodology, a real arch dam is considered as a test example. The numerical results demonstrate the computational advantages of the proposed methodology for the optimal design of arch dams. [ABSTRACT FROM AUTHOR]

An efficient method is proposed to find optimal shape of arch dams subjected to response spectrum loading. The optimization is performed by a combination of simultaneous perturbation stochastic approximation (SPSA) and genetic algorithm (GA) methods. This new method is called simultaneous perturbation genetic algorithm (SPGA). Operation of SPGA includes three phases. In the first phase, a preliminary optimization is accomplished using SPSA. In the second phase, an optimal initial population is produced using the first phase results. In the last phase, GA is employed to find optimum design using the optimal initial population. The numerical results reveal the robustness and high performance of the proposed method for optimum shape design of arch dams. The optimum design obtained by SPGA is compared with those of SPSA and GA. It is demonstrated that the SPGA converges to better solution compared to SPSA and GA by spending lower computational cost. [ABSTRACT FROM AUTHOR]