Advances in Nano Research

Volume 19, Number 6, 2025, pages 607-623

DOI: 10.12989/anr.2025.19.6.607

Predicting stability in advanced sports equipment: A nano-mechanics and machine learning approach to functionally graded material structures

Lin Hu , Dijun Shen , Mostafa Habibi , Zhem Bai

Abstract

The ongoing pursuit of performance enhancement and athlete safety in sports demands continuous innovation in equipment design. Modern sports gear, from bicycle frames to protective helmets, increasingly relies on advanced composite materials that are both lightweight and exceptionally strong. Understanding the mechanical stability, particularly the buckling behavior, of these materials at micro and nano scales is critical for developing the next generation of sports technology. This study investigates the buckling stability of functionally graded steel-concrete structures, which offer a unique combination of strength and durability, at these small scales. We develop a comprehensive theoretical framework by integrating the nonlocal strain gradient theory to capture size-dependent effects with the energy conservation method to derive the governing equations. The resulting equations are solved numerically using the general differential quadrature method to ensure high accuracy. To further advance the predictive capabilities for practical design applications, we employ an Artificial Neural Network model, trained on our numerical results, to forecast buckling responses rapidly. The findings demonstrate a significant synergy between computational mechanics and machine learning, providing a powerful toolset for the analysis and design of high-performance, reliable sports equipment. This research offers a pathway to creating safer and more efficient sporting goods through targeted material engineering and intelligent prediction models.

Key Words

advanced composites; artificial neural networks; buckling analysis; functionally graded materials; nanoscale structures; protective equipment; sports engineering; stability prediction

Address

PDF Viewer

Preview is limited to the first 3 pages. Sign in to access the full PDF.

Loading…