AUTHOR=Meruane Viviana , Puiggros Ignacio , Fernandez Ruben , Ruiz Rafael O. 

TITLE=Efficient design of sandwich panels with cellular truss cores and large phononic band gaps using surrogate modeling and global optimization

JOURNAL=Frontiers in Mechanical Engineering

VOLUME=Volume 10 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/mechanical-engineering/articles/10.3389/fmech.2024.1329345

DOI=10.3389/fmech.2024.1329345

ISSN=2297-3079

ABSTRACT=This study explores the potential of architected cellular materials, particularly in the design of sandwich panels with cellular truss cores aiming to achieve substantial phononic band gaps. The proposed methodology integrates surrogate modeling and a global optimization strategy to design the sandwich panels. To create the surrogate models, three machine learning algorithms were assessed: k-Nearest Neighbors (kNN), Random Forest Regression (RFR), and Artificial Neural Networks (ANN). These surrogate models were trained using data from parameterized finite element (FE) models of the panels under investigation. After training, the surrogate models were integrated with Particle Swarm Optimization (PSO) to optimize the design. This allowed to effectively search for optimal truss core configurations, resulting in sandwich panels with band gaps tailored to specific design frequencies. Furthermore, the proposed methodology demonstrated significant improvements in computational efficiency compared to non-surrogated optimization techniques, especially when designing for multiple target frequencies.