Open Access Article
This Open Access Article is licensed under a Creative Commons Attribution-Non Commercial 3.0 Unported LicenceExperiment-in-Loop Interactive Optimization of Polymer Composites for "5G-and-Beyond"
(Note: The full text of this document is currently only available in the PDF Version )
Bin Xu , Touchy Abeda Sultana , Koki Kitai , Jiang Guo , Toyomitsu Seki , Ryo Tamura , Koji Tsuda and Junichiro Shiomi
First published on 21st February 2025
Abstract
“Fifth generation and beyond” communication technologies have sparked considerable demand for polymer composite materials with low thermal expansion coefficients (CTE) and low dielectric loss under high operation frequency. However, the complexity of process parameters and the lack of knowledge in fabrication procedures hinder this goal. In this study, state-of-the-art experiment-in-loop Bayesian optimization (EiL-BO) is developed to optimize a composite of perfluoroalkoxyalkane matrix with silica fillers. The Gaussian process equipped with an automatic relevance determination kernel that automatically adjusts the scaling parameters of individual dimensions effectively enhances the EiL-BO’s ability to search for candidates in a complex and anisotropic multidimensional space. This address the most critical issue regarding the eight-dimensional parameters, including filler morphology, surface chemistry, and compounding process parameters. The obtained optimal composite shows a low CTE of 24.7 ppm/K and an extinction coefficient of 9.5×10-4, outperforming existing polymeric composite, revealing exceptionally effective and versatile of EiL-BO in accelerates the advanced materials development.