Analysis of the Mechanical Properties of Graphene Reinforced Metal Matrix Composites Using Machine Learning
Mentor 1
Pradeep Rohatgi
Start Date
28-4-2023 12:00 AM
Description
This research project analyzed the mechanical properties of aluminum-graphene metal matrix composites (MMCs) reinforced with 5% and above graphene weight using experimental data from peer-reviewed sources. The study focused on the effects of increasing graphene content on the mechanical properties of reinforced aluminum composites, including yield strength, ultimate tensile strength, and hardness. The data was collected from over 25+ papers, and the findings associated with increasing the graphene content per gram of AI were considered for base metals AI6061, AI7075, AI2024, AA Annealed (O Temper), and Pure AI. The incorporation of graphene reinforcement into MMCs enhances their stress strength and durability while preserving their other mechanical properties and structure. However, due to the lack of experimental data for >2.5-4 weight% graphene, theoretical models were used and based on certain assumptions to predict the mechanical properties of different composites at weight% of graphene >= 5. Decision tree-based RF and GBM models were found to exhibit the best prediction of high dimensional data, while GBM and ANN models were found to be the best for continuous data. The machine learning analysis revealed that graphene content and hardness are the most significant variables for predictions, while the type of graphene is more influential. The morphology of graphene affects the level of elasticity and hardness with higher additions of graphene content. The lack of influence on hardness indicates that graphene content, is more important in determining the results. The study concludes that aluminum-graphene MMCs offer a cost-effective and lightweight solution for enhancing material durability in high-stress applications. The initial predictions made using machine learning models suggest that the use of aluminum-graphene MMCs offers a promising solution for enhancing material durability. Overall, this study contributes to the understanding of the mechanical properties of aluminum-graphene MMCs and their potential for use in various industries.
Analysis of the Mechanical Properties of Graphene Reinforced Metal Matrix Composites Using Machine Learning
This research project analyzed the mechanical properties of aluminum-graphene metal matrix composites (MMCs) reinforced with 5% and above graphene weight using experimental data from peer-reviewed sources. The study focused on the effects of increasing graphene content on the mechanical properties of reinforced aluminum composites, including yield strength, ultimate tensile strength, and hardness. The data was collected from over 25+ papers, and the findings associated with increasing the graphene content per gram of AI were considered for base metals AI6061, AI7075, AI2024, AA Annealed (O Temper), and Pure AI. The incorporation of graphene reinforcement into MMCs enhances their stress strength and durability while preserving their other mechanical properties and structure. However, due to the lack of experimental data for >2.5-4 weight% graphene, theoretical models were used and based on certain assumptions to predict the mechanical properties of different composites at weight% of graphene >= 5. Decision tree-based RF and GBM models were found to exhibit the best prediction of high dimensional data, while GBM and ANN models were found to be the best for continuous data. The machine learning analysis revealed that graphene content and hardness are the most significant variables for predictions, while the type of graphene is more influential. The morphology of graphene affects the level of elasticity and hardness with higher additions of graphene content. The lack of influence on hardness indicates that graphene content, is more important in determining the results. The study concludes that aluminum-graphene MMCs offer a cost-effective and lightweight solution for enhancing material durability in high-stress applications. The initial predictions made using machine learning models suggest that the use of aluminum-graphene MMCs offers a promising solution for enhancing material durability. Overall, this study contributes to the understanding of the mechanical properties of aluminum-graphene MMCs and their potential for use in various industries.
