Experimental analysis and machine learning prediction of mechanical and wear behaviors in alcocrfenisi reinforced al5083 composites

Abstract

In recent decades, significant progress has been made in the utilization of aluminum in the automobile, aerospace and marine industries. Nevertheless, further research is still required on aluminum alloys to meet the growing demand for diverse applications. Though aluminum alloys have a wide range of uses, their poor surface properties, including high thermal expansion and limited wear resistance, restrict their application in mechanical and wear sensitive environments. Due to these surface restrictions, particularly in alloys such as Al5083, researchers are currently exploring suitable manufacturing techniques to enhance their characteristics. The integration of high entropy alloy (HEA) particles by friction stir processing (FSP) is an efficient method for enhancing the surface properties of metal matrix composites (MMCs). Also, identifying the optimal FSP parameters for better particle dispersion and grain refinement is still hard when trying to improving mechanical and tribological properties without changing the bulk properties. This research presents an in-depth study on the fabrication and optimization of Al5083 aluminum alloy composites reinforced with AlCoCrFeNiSi high entropy alloy particles via friction stir processing. newline