Mechanical assessment for enhancing hybrid composite performance through silane treatment using RSM and ANN

Abstract

The study utilized Response Surface Methodology (RSM) and Artificial Neural Networks (ANN) to identify the optimal combination of three key factors for producing polymer composites: nanoparticle percentage, silane concentration, and silane dipping duration. RSM and Analysis of Variance (ANOVA) were applied to explore the relationships between these variables and their effects on composite properties. Additionally, the ANN was used to analyze multiple factors, revealing a strong correlation between predicted and observed results. The findings highlighted that silane treatment was the most influential factor in enhancing the composite's flexural strength. Fiber-related properties, particularly the duration of silane dipping, significantly impacted both flexural strength and hardness. Nanoparticles further strengthened the fiber matrix by encouraging effective agglomeration. The ANN demonstrated 95% accuracy in predicting flexural strength and hardness, and its predictions were validated by comparing them with experimental data and the regression model's outcomes. Silane concentration also notably influenced flexural properties. The RSM analysis identified the optimal combination for maximizing flexural strength and hardness: 5% nanoparticles, 10% silane concentration, and a 20-minute silane dipping time.

Keywords

• Artificial neural network
• Silane treatment
• RSM
• ANOVA
• Nanoparticles