This study presents an integrated approach to minimize warpage and shrinkage in automotive A-pillar plastic components fabricated via injection moulding. The research systematically investigates the effect of key process parameters mould temperature, injection pressure, and melt temperature alongside three distinct gate configurations: single middle, double middle, and two-end double gates. Simulations were conducted using Autodesk Moldflow Adviser, and the Taguchi method was employed to design experiments and analyse the significance of each factor using signal-to-noise (S/N) ratios and ANOVA. Results indicate that melt temperature is the most influential parameter, contributing up to 96.25% to warpage formation, followed by mould temperature and injection pressure. Among the gate designs, the double middle gate configuration demonstrated the best balance between reduced deflection and structural integrity. Optimized parameters (melt temperature: 190°C, mould temperature: 20–40°C, injection pressure: 90–130 MPa) effectively reduced deflection by up to 4.50%. Furthermore, an Artificial Neural Network (ANN) model trained with experimental data accurately predicted deflection values with less than 15% deviation from simulated and actual results. The integration of simulation, statistical optimization, and machine learning provides a robust framework for enhancing dimensional accuracy and process efficiency. This study offers a scalable methodology for automotive part manufacturers seeking to optimize injection moulding processes and ensure higher product quality with reduced material waste.
Ramli et al. (Thu,) studied this question.