Artificial Neural Network-Based Investigation of Zirconium Diboride Nanoparticles Reinforced in an Aluminium Alloy Matrix

This study supports advanced materials by examining the properties of Al 7175 alloy reinforced with zirconium diboride (ZrB2) nanoparticles. Understanding and improving the wear resistance of composites is an important goal because it is essential for many industrial applications. Hence, in this research, Al 7175 alloy is reinforced with nanoparticles of ZrB2 at three different percentages. This research was carefully designed to investigate the connection between material (such as composition, load, speed and sliding distance) and response (such as friction force (FF), wear rate (Sf) and friction coefficient (Cf)). The optimal combinations for reducing Cf, Sf, and FF are found using Taguchi SNR analysis. The result was 5% content, 25.2 N load, 400 rpm speed, and 71.2 m drift. The confirmation test was done, and it shows that the obtained responses are optimized for the predicted optimal combinations. Also, an artificial neural network (ANN) model was developed to predict responses based on input data, another advancement that has helped data scientists. The ANN model performed well in the training, validation and testing phases, with an overall prediction rate of 87.873%. The research outcomes show that with the increase in composition percentage of the ZrB2 and the reduction in speed and load, the wear rate is minimal. Hence, the alloy Al 7175 reinforced with the nanoparticles of Zrb2 at 5% tends to reduce the wear rate and its friction coefficients.