Abstract
This research delves into the tribological performance of hybrid aluminum metal matrix composites (HAMMCs) incorporating zirconium diboride (ZrB2) particles and fly ash as reinforcing agents. The study employs a linear reciprocating wear test to investigate the impact of dry sliding wear on these HAMMCs under ambient and elevated temperatures. Wear mechanisms are discerned through field emission scanning electron microscopy. Optimization of wear test parameters, coefficient of friction (COF), and wear rate is achieved using the genetic algorithm. Additionally, artificial neural network (ANN) and multiple linear regression analysis are employed to formulate a predictive model for wear, estimating specific wear rate and COF under various testing conditions. The ANN predictions exhibit a deviation ranging from 0% to 1.39% from the experimental values, indicating the model's effectiveness in understanding and predicting wear behavior in the study of HAMMC.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have