Adaptive Multi-Level Search for Global Optimization: An Integrated Swarm Intelligence-Metamodelling Technique

Over the last decade, metaheuristic algorithms have emerged as a powerful paradigm for global optimization of multimodal functions formulated by nonlinear problems arising from various engineering subjects. However, numerical analyses many complex design may be performed using finite element method (FEM) or computational fluid dynamics (CFD), which function evaluations population-based are repetitively computed to seek optimum. It is noted that these simulations become computationally prohibitive structures. To efficiently and effectively address this class problems, an adaptively integrated swarm intelligence-metamodelling (ASIM) technique enabling multi-level search model management optimal solution proposed in paper. The developed comprises two steps: first step, global-level exploration near adaptive swarm-intelligence algorithm, second local-level exploitation fine studied on metamodels, constructed multipoint approximation (MAM). demonstrate superiority over other methods, such conventional MAM, particle optimization, hybrid cuckoo search, water cycle algorithm terms expense associated with solving one benchmark mathematical example real-world examined. In particular, key factors responsible balance between discussed well.