Towards Cost-Optimal Zero-Defect Manufacturing in Injection Molding: An Explainable and Transferable Machine Learning Framework

In the era of Industry 4.0, Zero-Defect Manufacturing is critical for injection molding but faces three major hurdles: severe class imbalance, the “black-box” nature of AI models, and the lack of scalability across machines. This study presents a comprehensive framework addressing these challenges. Using industrial datasets, we evaluated state-of-the-art supervised algorithms. Results show that CatBoost outperforms other architectures. Crucially, we demonstrate that maximizing accuracy is insufficient; instead, we introduce a cost-sensitive threshold optimization that minimizes economic risk, identifying an optimal classification threshold significantly lower than the standard. To enhance trust, SHAP analysis reveals that motor power and specific nozzle temperatures are the primary defect drivers. Finally, we validate a transfer learning approach using LightGBM, proving that models can be adapted to new datasets with minimal retraining. The implementation of cost-sensitive thresholding reduces total failure costs by over 75% compared to standard classification, while the transfer learning approach cuts the data requirements for new machine adaptation by more than half, providing a high-impact, scalable solution for sustainable smart manufacturing.