Intelligent Modeling of Erosion-Corrosion in Polymer Composites: Integrating Fuzzy Logic and Machine Learning

Area of Science:

• Materials Science and Engineering
• Computational Intelligence
• Corrosion Science

Background:

• Glass-fiber-reinforced pipes (GRP) are susceptible to erosion-corrosion in aggressive environments.
• Predictive modeling of material degradation in GRP is crucial for operational safety and longevity.
• Existing models may not fully capture the complex interactions of multiple operational parameters.

Purpose of the Study:

• To develop a novel hybrid intelligent framework integrating fuzzy logic and artificial neural networks (ANN).
• To model and predict the erosion-corrosion behavior of GRP under various operational conditions.
• To identify optimal operating parameters for minimizing material degradation in GRP systems.

Main Methods:

• Utilized experimental data on abrasive sand concentration, flow rate, chlorine content, and exposure time.
• Developed a hybrid model combining fuzzy logic for qualitative insights and ANN for quantitative predictions.
• Employed statistical analysis to determine the influence of operational parameters on erosion-corrosion rates.

Main Results:

• Achieved good prediction accuracy for corrosion rate (R²=0.81) and moderate accuracy for erosion rate (R²=0.56).
• Identified flow rate and fuzzy severity as the most influential parameters affecting material degradation.
• Determined optimal conditions: low sand concentration, low flow rate, no chlorine, and short exposure times.

Conclusions:

• The hybrid intelligent framework effectively models GRP erosion-corrosion behavior.
• This approach enables predictive maintenance, operational optimization, and service life assessment for GRP systems.
• The study bridges experimental data and computational intelligence for enhanced material performance evaluation.