Optimization of Injection-Molding Process for Thin-Walled Polypropylene Part Using Artificial Neural Network and...

Area of Science:

• Materials Science
• Manufacturing Engineering
• Computational Engineering

Background:

• Injection molding is a key manufacturing process for plastic parts.
• Common defects include short shot, shrinkage, and warpage, impacting product quality.
• Optimizing process parameters is crucial for defect reduction.

Purpose of the Study:

• To determine optimal injection molding process parameters for high-quality polypropylene parts.
• To minimize manufacturing defects such as short shot, shrinkage, and warpage.
• To validate the effectiveness of proposed optimization methods.

Main Methods:

• Utilized Artificial Neural Networks and Taguchi Techniques for parameter optimization.
• Employed Analytic Hierarchy Process to weigh defect significance.
• Performed Finite Element Analysis (FEA) using SolidWorks Plastics for simulation and validation.

Main Results:

• Optimal parameters identified: 1s filling time, 3s cooling time, 3s pressure-holding time, 230°C melt temperature.
• Filling time and pressure-holding time were the most influential parameters on end-product quality.
• The proposed optimization methods demonstrated a low error margin of 1.5%.

Conclusions:

• The integrated approach of ANNs, Taguchi, AHP, and FEA effectively optimizes injection molding parameters.
• Achieved significant reduction in defects, leading to superior end-product quality.
• The optimized process parameters provide a reliable guideline for defect-free plastic part manufacturing.