Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2025.072839
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Open Access

ARTICLE

Machine Learning Based Uncertain Free Vibration Analysis of Hybrid Composite Plates

Bindi Saurabh Thakkar1, Pradeep Kumar Karsh2,*
1 Faculty of Engineering & Technology, Parul University, Waghodia, Vadodara, 391760, Gujrat, India
2 Department of Mechanical Engineering, Parul Institute of Engineering & Technology, FET, Parul University, Waghodia, Vadodara, 391760, Gujrat, India
* Corresponding Author: Pradeep Kumar Karsh. Email: email

Computers, Materials & Continua https://doi.org/10.32604/cmc.2025.072839

Received 04 September 2025; Accepted 13 October 2025; Published online 20 November 2025

Abstract

This study investigates the uncertain dynamic characterization of hybrid composite plates by employing advanced machine-assisted finite element methodologies. Hybrid composites, widely used in aerospace, automotive, and structural applications, often face variability in material properties, geometric configurations, and manufacturing processes, leading to uncertainty in their dynamic response. To address this, three surrogate-based machine learning approaches like radial basis function (RBF), multivariate adaptive regression splines (MARS), and polynomial neural networks (PNN) are integrated with a finite element framework to efficiently capture the stochastic behavior of these plates. The research focuses on predicting the first three natural frequencies under material uncertainties, which are critical to ensuring structural reliability. Monte Carlo simulation (MCS) is used as a benchmark for generating probabilistic datasets, including mean values, standard deviations, and probability density functions. The surrogate models are then trained and validated against these datasets, enabling accurate representation of uncertainty with substantially fewer samples compared to conventional MCS. Among the methods studied, the RBF model demonstrates superior performance, closely approximating MCS results with a reduced sample size, thereby achieving significant computational savings. The proposed framework not only reduces computational time and costs but also maintains high predictive accuracy, making it well-suited for complex engineering systems. Beyond free vibration analysis, the methodology can be extended to more sophisticated scenarios, such as forced vibration, damping effects, and nonlinear structural responses. Overall, this work presents a computationally efficient and robust approach for surrogate-based uncertainty quantification, advancing the analysis and design of hybrid composite structures under uncertainty.

Keywords

Hybrid composite; surrogate model; RBF; MARS; PNN; uncertain free vibration analysis; machine learning

  • 175

    View

  • 23

    Download

  • 0

    Like

Related articles
Copyright© 2025 Tech Science Press
© 1997-2025 TSP (Henderson, USA) unless otherwise stated

Share Link