A surrogate-based particle swarm optimization algorithm for solving optimization problems with expensive black box functions

In engineering applications, computer experiments such as finite element analysis and computational fluid dynamics are often used to model and analyse structural behaviours. In this article, a surrogate-based particle swarm optimization algorithm is proposed for solving optimization problems with expensive black box functions. An approximate optimization problem in which the black box functions are replaced by the hybrid surrogate models is efficiently solved to search and adjust the global optimum position during the iterative process. Since the presented method combines the merits of traditional optimization algorithms and particle swarm optimization, only a small number of particles is needed to achieve the optimal position after several iterations. Therefore, the method shows great advantages in solving engineering optimization problems with expensive black box functions. Several examples are presented to demonstrate the feasibility and effectiveness of the proposed method.