Artificial Neural Network and Response Surface Methodology Based Analysis on Solid Particle Erosion Behavior of...

Area of Science:

• Materials Science and Engineering
• Polymer Composites
• Tribology

Background:

• Polymer-based fibrous composites offer advantages like high strength-to-weight ratio and durability, making them suitable for marine and sports applications.
• The erosive wear of these composites under cyclic abrasive impact remains a critical challenge for researchers and industries.

Purpose of the Study:

• To analyze the bonding behavior and erosion resistance of S-type woven glass fiber reinforced polymer matrix composites (PMCs) against natural abrasive slurry.
• To investigate the influence of key erosion parameters on the wear performance of these composite materials.

Main Methods:

• Utilized Response Surface Methodology (RSM) to model and analyze the effects of slurry pressure, impingement angle, and nozzle diameter on erosion loss.
• Employed Artificial Neural Network (ANN) modeling to validate the experimental outcomes and identify optimal erosion conditions.
• Measured erosion loss as the primary response parameter, quantifying weight loss during the abrasive wear process.

Main Results:

• Both RSM and ANN models demonstrated good agreement in predicting the erosion behavior of the glass fiber reinforced polymer matrix composites.
• The study successfully analyzed the reinforcement-matrix bonding characteristics under abrasive slurry conditions.

Conclusions:

• The developed RSM and ANN models provide reliable tools for understanding and predicting the abrasive erosion resistance of glass fiber reinforced polymer matrix composites.
• Findings contribute to the improved design and application of these composites in demanding environments prone to abrasive wear.