AI-Driven Multi-Parameter Optimization of High-Performance Epoxy Composites for Tribological Applications
More details
Hide details
1
Department of Physics and Materials Sciences, College of Arts and Sciences, Qatar University
2
Production Engineering and Mechanical Design, Faculty of Engineering, Minia University, El-Minia 61111, Egypt
3
Mechanical Engineering Department, College of Engineering and Technology, Arab Academy for Science, Technology and Maritime Transport, Sadat Road - P.O. Box 11, Aswan, Egypt
Corresponding author
Mohamed Taha
Mechanical Engineering Department, College of Engineering and Technology, Arab Academy for Science, Technology and Maritime Transport, Sadat Road - P.O. Box 11, Aswan, Egypt
KEYWORDS
TOPICS
ABSTRACT
Epoxy composites reinforced with a hybrid nanofiller of paraffin oil and Al₂O₃ NPs, reveal superior mechanical and wear performance as frictional materials. The current study identifies optimal formulations through systematic tests on hardness, compressive yield strength, elastic modulus, COF, and wear resistance, complemented by 3D topographical and SEM of worn surface analyses. The addition of 0.5–2.0 wt.% Al₂O₃ NPs and 5.0 wt.% paraffin oil led to significant improvements: notably, the composite with 0.5 wt.% Al₂O₃ NPs exhibited superior mechanical properties, along with a remarkable 43% reduction in COF and 34% reduction in wear rate versus neat epoxy. It was indicated that the ANFIS model exhibited significant connection with experimental data, allowing accurate prediction of performance dependent on matrix composition and loading level. It can be evident that the hybrid experimental–AI technique increases material optimization and facilitates the design of high-performance epoxy nanocomposites.