Dr. Marwa Ghazi Karim, a faculty member, published her research paper titled “Mechanical-Informed Hybrid Machine Learning Models for Predicting Mechanical Failure in Graphene Sponges: A Data-Constrained Strategy for Mechanical Engineering Applications” in the prestigious international journal Advanced Engineering Applications. The study addressed the development of a hybrid approach that integrates physical measurements and artificial intelligence techniques to accurately predict the mechanical failure strength of three-dimensional graphene sponges. Graphene sponges are nanomaterials with a complex porous structure that are difficult to model traditionally due to the overlap of their structural planes and the limited availability of experimental data.<\/p>\n
The results showed the remarkable superiority of the GPR model, achieving a coefficient of determination (R^2) of 0.967 and an average absolute error of 0.192 MPa. This demonstrates the ability of physics-informed AI-based models to provide accurate and productive mechanical predictions under data-constrained strategies, thus enhancing intelligent design methodologies for nanostructured materials. Advanced Engineering Applications<\/p>\n
It is worth noting that the journal Advanced Engineering Applications is ranked in the second quartile (Q2) in Clarivate and Scopus and is published by De Gruyter.<\/p>\n","protected":false},"excerpt":{"rendered":"