Optimizing wear and mechanical characteristics of jute fiber composites reinforced with silicon carbide and prediction using neural network technique.

This research article focuses on optimizing the strength and wear characteristics of nanocomposites strengthened with silicon carbide and jute fiber using neural network techniques. In this study, three different percentages of nanoparticles of SiC (3%, 6%, and 9%) were prepared and added to the jute fiber and epoxy resin as a base matrix to the composite. The hardness of the composites with and without reinforcement was measured, and it was observed that the upsurge in the percentage of nanoparticles of SiC led to an increase in composite hardness. The wear test was conducted based on L27 array of experiments, where the composition, load, speed, and sliding distance were taken as input parameters, and the specific rate of wear (Srw) was the response studied in this research. Taguchi analysis was performed to determine the optimal combination for minimizing the response. The findings indicated that the larger in the proportion of nanocomponents of SiC and reduction in load reduced the wear of the composites. Moreover, an machine learning based model was developed to forecast the outcomes. The established ANN model was highly accurate in predicting the responses, which demonstrates the potential of neural network techniques in optimizing the mechanical properties of nanocomposites. Overall, this study provides a comprehensive understanding of the consequence of nano SiC on the wear and mechanical characteristics of jute fiber material. The established ANN model can be used as a tool for forecasting the wear and mechanical properties of nanocomposites and can be further used for developing improved composites. The findings of this research can be beneficial in various industries, such as automotive, aerospace, and manufacturing, where the wear and mechanical properties of materials are critical factors. [ABSTRACT FROM AUTHOR]