Machine Learning Based Uncertain Free Vibration Analysis of Hybrid Composite Plates

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.