Machine Learning for Industrial Manufacturing: A Case Study on Injection Molding Machine Selection Support

Selecting the right injection molding machine for new products is a significant challenge for manufacturers. The traditional approach involves detailed calculations of clamping force, mechanical mold evaluations, and hands-on trials. This method is time-consuming, costly, and requires expert skills. This paper explores how machine learning can enhance machine selection efficiency and aid decision-making using criteria such as product type, material properties, and mold specifications. Two machine learning models, Support Vector Machine (SVM) and Random Forest, were applied using real data from the automotive plastics industry. Results show machine learning accurately predicts machine selection, with Random Forest outperforming SVM (Accuracy: 81%, F1: 78%, Precision: 85%, Recall: 81% vs. SVM’s Accuracy: 67%, F1: 66%, Precision: 66%, Recall: 67%). These findings highlight the potential benefits of integrating classification algorithms into injection molding workflows.