Quality and Defect Prediction in Plastic Injection Molding using Machine Learning Algorithms based Gating Systems and Its Mathematical Models

To achieve high quality products from Plastic Injection Molding (PIM) process it is very essential to identify the defective operations in automatic manner which most challenging task. This paper proposes a Machine Learning (ML) approach detect complex faults occurrence during PIM process. During initial sampling of molding and low time consumption concentrate on suitable determination parameter values by considering properties injection For that purpose, novel machine learning algorithms based gating system introduced (MLGS-PIM). Technical evaluation can be done using simulation combines CATIA MATLAB. Therefore MLGS-PIM, holistic improve predict parameters approaches. The considered approaches for this are Artificial Neural Network (ANN) Support Vector (SVM). two models combined under various conditions. Such ML technique helps increase characteristics predicted with where data measurements handled an intelligent manner. materials thermoplastic polystyrene, acrylonitrile butadiene styrene polyvinyl chloride three types systems applied consists 3, 4 5 gates as well measured output analysis sum rate, bit error rate convergence plot. results show performance proposed MLGS-PIM significantly increases when compared earlier such AntLion Optimization PSO-MSQPA.