Experimental and Machine Learning Study on Friction Stir Surface Alloying in Al1050-Cu Alloy

Abstract

This study employs friction stir processing to create a surface alloy using Al1050 aluminum as the base material, with Cu powder applied to enhance surface properties. Various parameters, including tool rotation speed, feed rate, and the number of passes, are investigated for their effects on the microstructure and mechanical properties of the resulting surface alloy. The evaluation methods include tensile testing, microhardness measurements, and metallographic examinations. The initial friction stir alloying pass produced a non-uniform stir zone, which was subsequently homogenized with additional passes. Through the plasticization of Al1050, initial agglomerates of copper particles were compacted into larger ones and saturated with aluminum. The alloyed samples exhibited up to an 80% increase in the strength of the base metal. This significant enhancement is attributed to the Cu content and grain size refinement post-alloying. Additionally, machine learning techniques, specifically Genetic Programming, were used to model the relationship between processing parameters and the mechanical properties of the alloy, providing predictive insights for optimizing the surface alloying process.