Estimation of mass loss under wear test of nanoclay-epoxy nanocomposite using response surface methodology and artificial neural networks.

In this work, the wear behavior of nanoclay-epoxy nanocomposites is studied through Response Surface Methodology (RSM) and Artificial Neural Networks (ANN) as predictive models. This study aims to measure mass loss under wear conditions by studying critical parameters like nanoclay wt%, load, speed, time, and water soaking time. Experimental runs are planned based on the Box-Behnken design of RSM to create a regression model, which is then validated by ANOVA analysis. An ANN model is also trained and tested to improve predictive accuracy, performing better than RSM. The results show that wear resistance is greatly enhanced by increasing nanoclay content, which minimizes material loss. Water absorption adversely affects wear performance, resulting in enhanced mass loss caused by plasticization and swelling. The ANN model is more accurate in prediction than RSM, with minimal variation from experimental data. Scanning Electron Microscopy (SEM) analysis gives insights into wear mechanisms. The research demonstrates the efficiency of combining statistical and machine-learning methods for optimizing wear-resistant polymer nanocomposites.