Interval multi-objective optimisation of structures using adaptive Kriging approximations

This paper proposes an interval uncertain multi-objective optimisation (IUMOO) method for structures with uncertain-but-bounded parameters. An adaptive Kriging model is established to improve the computational efficiency and numerical accuracy in the approximation of design functions. Latin Hypercube Design (LHD) is applied to achieve a set of sampling points both in the design and uncertain spaces for calibrating the Kriging surrogate model. The interval number programming method is used to transform the uncertain optimisation into a corresponding deterministic multi-objective optimisation. Typical numerical examples are used to demonstrate the effectiveness of the proposed methodology.

► An interval uncertain multi-objective optimisation (IUMOO) method is proposed. ► Interval model is used to describe structures with uncertain-but-bounded parameters. ► An adaptive approximation scheme is proposed using the Kriging model and LHD method. ► The adaptive model is sequentially updated via the space-filling design criteria. ► Interval number programming method is used to generate deterministic optimisations.