An Optimization Approach to the Dry Sliding Wear Behavior of Particulate Filled Glass Fiber Reinforced Hybrid Composites

Abstract

The new set of hybrid composites consisting of randomly oriented short e glass fiber reinforcement, polyester resin and titanium oxide (TiO2) particulate were developed by hand layup technique. Wear test was carried out by rubber wheel abrasive test (RWAT) rig with the four operating variables filler content, applied load, abrasive grit size (Al2O3) and test duration. The wear test of the composites were done on the basis of Taguchi's L9 (34) Orthogonal array. Analysis of variance and S/N ratio was used to study the optimum wear. From, Taguchi's experimental design a mathematical regression model of the wear rate was suggested. Genetic algorithm (GA) was used to compare the result which obtained from Taguchi's design of experiment. The fitness graph from the GA gives the better fitness function in which the operating variables were determined and the minimum wear rate was obtained. Scanning Electron Microscopy (SEM) image discovered to review the crater formation and fiber pull out.

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

“…ANNs, inspired by the human brain, possess the capability to learn complex patterns from data. [16][17][18][19] In this work, the novelty lies in not only employing ANNs for predictive analysis but also optimizing their hyperparameters. The hyperparameter optimization process fine-tunes the ANN models, enhancing their predictive accuracy and robustness in capturing intricate relationships within the tribological data.…”

“…To augment traditional tribological analyses, this study integrates advanced machine learning techniques, specifically artificial neural networks (ANNs) powered by Python. ANNs, inspired by the human brain, possess the capability to learn complex patterns from data 16–19 . In this work, the novelty lies in not only employing ANNs for predictive analysis but also optimizing their hyperparameters.…”

Effect of Filler Materials on Abrasive Wear Performance of Glass/Epoxy Composites

“…This is a prominent class of man-made composite materials for tribo-engineering, where triboperformance in non-lubricated settings is a key material selection characteristic [3]. RESEARCH Fiber and particulate-reinforced epoxy composite materials have suitable tribological characteristics [4][5][6][7][8]. The number of research articles on epoxy as a matrix material with glass fibres and ceramic fillers for improving the qualities in mechanical and abrasion resistance has increased over the past ten years [9][10][11][12][13][14][15][16][17][18].…”