Surface roughness optimization of polyamide-6/nanoclay nanocomposites using artificial neural network: genetic...

Area of Science:

• Materials Science
• Manufacturing Engineering
• Artificial Intelligence

Background:

• Polymer nanocomposites are gaining significant R&D attention globally.
• Surface roughness is a critical factor influencing the quality and cost of machined nanocomposite products.
• Optimizing machining conditions is essential for achieving superior product quality and economic efficiency.

Purpose of the Study:

• To develop a predictive model for optimizing surface roughness in polyamide-6 (PA-6) nanocomposite milling.
• To integrate design of experiments with artificial intelligence for predictive modeling.
• To determine optimal milling parameters for minimizing surface roughness.

Main Methods:

• Developed an artificial neural network (ANN) model to predict surface roughness based on milling parameters (spindle speed, feed rate) and nanoclay (NC) content.
• Employed a genetic algorithm (GA) for training the ANN, addressing limitations of small datasets from full factorial design.
• Utilized the GA in conjunction with the derived ANN function for optimizing milling parameters.

Main Results:

• Successfully developed a robust ANN model for predicting surface roughness in PA-6 nanocomposites.
• Identified optimal milling parameters through GA-driven optimization for minimizing surface roughness.
• Demonstrated the efficacy of combining DOE and AI (ANN, GA) for machining process optimization.

Conclusions:

• The developed predictive model effectively optimizes surface roughness in PA-6 nanocomposite milling.
• The combined ANN and GA approach provides accurate and robust solutions for machining parameter optimization.
• This methodology contributes to enhancing machining performance and reducing production costs for polymer nanocomposites.