English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper introduces a methodology designed to augment the inverse designoptimization process in scenarios constrained by limited compute, through thestrategic synergy of multi-fidelity evaluations, machine learning models, andoptimization algorithms. The proposed methodology is analyzed on two distinctengineering inverse design problems: airfoil inverse design and the scalarfield reconstruction problem. It leverages a machine learning model trainedwith low-fidelity simulation data, in each optimization cycle, therebyproficiently predicting a target variable and discerning whether ahigh-fidelity simulation is necessitated, which notably conserves computationalresources. Additionally, the machine learning model is strategically deployedprior to optimization to reduce the search space, thereby further acceleratingconvergence toward the optimal solution. The methodology has been employed toenhance two optimization algorithms, namely Differential Evolution and ParticleSwarm Optimization. Comparative analyses illustrate performance improvementsacross both algorithms. Notably, this method is adeptly adaptable across anyinverse design application, facilitating a harmonious synergy between arepresentative low-fidelity machine learning model, and high-fidelitysimulation, and can be seamlessly applied across any variety ofpopulation-based optimization algorithms.

Efficient Inverse Design Optimization through Multi-fidelity Simulations, Machine Learning, and Search Space Reduction Strategies