Multi-Fidelity Design Framework Integrating Compositional Kernels to Facilitate Early-Stage Design Exploration of Complex Systems

Abstract

Abstract Early-stage design of complex systems is considered by many to be one of the most critical design phases because that is where many of the major decisions are made. The design process typically starts with low-fidelity tools, such as simplified models and reference data, but these prove insufficient for novel designs, necessitating the introduction of high-fidelity tools. This challenge can be tackled through the incorporation of multifidelity models. The application of multifidelity (MF) models in the context of design optimization problems represents a developing area of research. This study proposes incorporating compositional kernels into the autoregressive scheme (AR1) of multifidelity Gaussian processes, aiming to enhance the predictive accuracy and reduce uncertainty in design space estimation. The effectiveness of this method is assessed by applying it to five benchmark problems and a simplified design scenario of a cantilever beam. The results demonstrate significant improvement in the prediction accuracy and a reduction in the prediction uncertainty. Additionally, the article offers a critical reflection on scaling up the method and its applicability in early-stage design of complex engineering systems, providing insights into its practical implementation and potential benefits.