An Advanced Machine Learning Based Wear Optimization of Nano Particles Reinforced with High Strength Metal Matrix Composite

The use of Aluminium alloys in various industries has increased the demand for strong Aluminium alloys. To meet this demand, researchers are exploring new compositions for hybrid Aluminium metal matrix mixtures. In this study, an attempt was made to create a hybrid Aluminium alloy using stir-casting method and reinforcement with nanoparticles of boron nitride (BN) and nano zirconium dioxide (ZrO2) in 6070 Aluminium alloy. The Taguchi technique was used to enhance the stir-casting procedure limits that as agitation speed, agitation time, and temperature. The optimization was performed by varying the reinforcement content (0–12%) and the above-mentioned process parameters. The microhardness and wear resistance of the stir-cast materials were determined using a Vickers hardness tester and a wear tester. The results showed that the optimization of process parameters and reinforcement content had a significant impact on the microhardness and wear resistance of the Aluminium alloy. By analyzing the results, the optimum conditions for the stir-casting process were determined, leading to the production of Aluminium alloys with improved microhardness and reduced wear rate. In conclusion, this study demonstrated that the addition of BN and ZrO2 nanoparticles to 6070 Aluminium alloy using stir-casting method can enhance the microhardness and wear resistance of the alloy. The Taguchi method showed to be an effective tool in optimizing the stir-casting procedure limits, leading to the production of high-performance hybrid Aluminium alloys. Machine learning technique is used to forecast the responses and the developed neural model predicts response at higher accuracy.