Answers are grounded in this paper and cite their sources.
Hybrid composite laminates provide broad design flexibility, but their mechanical response depends on coupled effects of ply material, stacking sequence, ply number, ply position, and fiber volume fraction. This study presents a mechanics-informed machine learning framework for the preliminary screening and ranking of symmetric carbon/basalt/glass epoxy hybrid laminates. Symmetric 4-, 6-, and 8-ply configurations were generated using unidirectional carbon, basalt, and glass plies. Classical Lamination Theory was used to calculate tensile modulus, flexural modulus, a lamina-level longitudinal tensile strength indicator, nominal first-failure stress, and tensile resilience at selected fiber volume fractions. The resulting analytical dataset was used to train Support Vector Regression, Multi-Layer Perceptron, and Gaussian Process Regression models after Bayesian hyperparameter optimization. On the held-out analytical test set, Gaussian Process Regression reproduced the CLT-derived targets most closely, with an overall R² of 0.991. The trained model was then used for laminate ranking, feature-importance analysis, and Monte Carlo-based design-space exploration. Carbon-rich laminates showed the highest overall performance, while selected carbon–glass hybrids offered competitive balanced responses. The framework provides a physically interpretable tool for screening hybrid laminate designs before experimental validation.
No takes yet. Share an insight, caveat, or question.
Uluocak et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: