Enhancing structural analysis and electromagnetic shielding in carbon foam composites with applications in concrete integrating XGBoost machine learning, carbon nanotubes, and montmorillonite

Abstract

Electromagnetic shielding in carbon foam composites involves using the natural conductivity of carbon foam to block or absorb electromagnetic fields. These composites protect sensitive electronic devices from electromagnetic interference (EMI), which can disrupt or damage their operation. The inclusion of XGBoost machine learning analyzes and optimizes the material compositions for electromagnetic interference shielding. By integrating Carbon Nanotubes (CNTs) and Montmorillonite (MMT) into samples of carbon foam, this research aims to identify the electromagnetic shielding effectiveness (SE), electrical conductivity, and dielectric permittivity at different frequencies of carbon foam composites. This analysis will facilitate the development of enhanced composite materials tailored for effective EMI shielding in concrete environments, particularly in structures housing sensitive electronic equipment. The novelty of this study lies in the dual integration of carbon nanotubes and montmorillonite into carbon foam composites, uniquely exploring their synergistic effects on both mechanical and electrical properties. The study employs XGBoost machine learning to optimize the material compositions for enhanced electromagnetic interference shielding. This study probes the dual integration of CNTs and montmorillonite into carbon foam composites, evaluating their synergistic impact on mechanical and electromagnetic properties. Incorporating 1 %, 3 %, and 5 % of these additives into carbon foams, substantial improvements were recorded in compressive, tensile, and flexural strengths, peaking with a 5 % MMT enhancement that nearly doubled the compressive strength from 3.96 MPa to 9.44 MPa. Concurrently, these composites displayed enhanced EMI SE, with detailed electrical characterizations at varying frequencies. Employing XGBoost machine learning, optimal material compositions were derived for EMI shielding, presenting advancements for industrial applications requiring robust structural and electrical performance.