Surrogate-based optimization with adaptive parallel infill strategy enhanced by inaccurate multi-objective search

In recent decades, surrogate-based optimization (SBO) has been developed to replace costly models with cheap surrogates to improve efficiency. In this article, an adaptive parallel infill strategy is proposed to balance exploration and exploitation over the design space during the optimization process of SBO. Within this method, an inaccurate search strategy is adopted to optimize the surrogate models, thereby helping to locate the exploitation point. An elite archive is exploited to store superior sampling points for batch sampling, while a customized batch size determination strategy is introduced. The proposed SBO method with its adaptive parallel sampling strategy is tested on six unconstrained and five constrained analytical cases with the optimization results compared to state-of-the-art optimization algorithms. The optimization of a 582-bar tower truss system is also performed and utilized to verify the proposed SBO method. The proposed SBO with the adaptive parallel sampling strategy shows excellent performance and better stability.

Automated summary

The article introduces an adaptive parallel infill strategy to balance exploration and exploitation in the optimization process of SBO. It uses an inaccurate search strategy to optimize surrogate models and incorporates an elite archive and customized batch size determination strategy. The proposed SBO method shows excellent performance and better stability in various analytical cases and a tower truss system optimization.