Optimized machine learning with hyperparameter tuning and response surface methodology for predicting tribological performance in bio‐composite materials

Abstract

Abstract This study investigates the influence of NaOH treatment on tribological behavior in hybrid fiber‐reinforced composites, specifically employing Banana fiber with Al 2 O 3 filler in an epoxy matrix. Through design of experiments (DOE), disc speed, wear duration, and NaOH treatment are analyzed for specific wear rate (SWR) and coefficient of friction (COF). To advance the understanding of wear characteristics, the study leverages advanced machine learning, using Python‐powered artificial neural networks (ANN), is integrated with innovative ANN hyperparameter optimization. Optimized parameters (1050 rpm, 60 s, 5% treatment) significantly minimize SWR (12.38 × 10 −5 mm 3 /Nm) and COF (0.2). Scanning electron microscopy (SEM) analysis reveals improved interfacial adhesion and identifies micro‐cracks as the primary wear mechanism. This work contributes to a profound understanding of wear in hybrid composites, offering a fine‐tuned predictive model for optimizing tribological behavior and advancing material science and engineering. Highlights Reduced SWR, COF in composites via NaOH optimization. DOE: Explored disc speed, duration, NaOH impact. Advanced machine learning techniques enhanced wear prediction. Innovative: ANN hyperparameter optimization. Optimal Parameters: 1050 rpm, 60 s, 5% treatment.