Fiber-reinforced polymer composites are exposed to severe environmental conditions throughout their intended lifespan. It is essential to investigate how they age when exposed to cold and hot water to increase the durability of fiber-reinforced polymer composites. This work uses a hand lay-up process to create composites with different weight percentages of glass fiber, nanoclay, and epoxy. ASTM guidelines are followed for performing tensile and flexural tests. The input parameters, varying wt.% of glass fiber and nanoclay, are continuous, and the aging condition is deemed a categorical factor. The mechanical properties are considered as response variables (output). The mechanical properties are optimized using Response Surface Methodology (RSM), while Artificial Neural Networks (ANNs) provide a reliable predictive model with high correlation coefficients. The findings demonstrate that ANNs outperform RSM in flexural strength prediction, whereas RSM offers greater accuracy for tensile strength modeling. SEM analysis of the fracture surfaces reveals the causes of specimen failure under tensile load, with distinct differences between dry, cold, and boiling water-soaked specimens.

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.

The present work seeks to investigate the problem of stable laminar micropolar fluid flow through porous walls of varying permeability. Furthermore, the effect of an external magnetic field is investigated. The resulting solution is extended to analyse the nonlinear differential equation of heat and mass transfer in the flow situation. The velocity and microrotation at the channel’s entrance are assumed to be those of Poiseuille flow. Using appropriate transformations, the governing nonlinear equations are transformed to a system of ordinary differential equations, which are then solved using a novel numerical technique based on a finite difference scheme termed the Keller-box method. The results show that the smooth and straightforward Keller-box method is an appropriate method for estimating solutions of complex governing equations since it is simple to implement. Graphs and tables are used to explain the effect of significant parameters such as the suction Reynolds number, micro rotation/angular velocity parameters, and Peclet number on the stream function, temperature distribution, and concentration properties of the fluid. The effect of wall permeability on longitudinal velocity and microrotation has been investigated. The couple stress and skin friction on the walls have also been calculated. The effect of variation in Reynolds number is showing the importance of inertial forces in comparison with viscous forces. The velocity boundary layer is observed to decrease when there is an increase in Reynolds number. Furthermore, the accuracy and convergence of the obtained solutions show that the Keller-box method is applicable to various nonlinear physical problems, even those with significant non-linearity.