A novel simulation of bottle blow molding to determine suitable parison thicknesses for die shaping

This study proposes the use of an artificial intelligence (AI) method to determine suitable parison thicknesses at the horizontal cross-section of a bottle in die shaping. The cross-section of the bottle was subjected to blow molding simulation by the finite element method (FEM) in order to achieve more accurate results than by simulating the full bottle shape. The absolute average error in cross-section simulation was 17.02% relative to experimental data. Subsequently, an artificial neural network (ANN) was trained using the FEM data on cross-section blow molding. The ANN was in good agreement with the experimental data for more complex shapes of two implementable bottles, and this model had an absolute average error of 15.66%. Eventually, a genetic algorithm (GA) was developed to determine the uniform perimeter thickness of a bottle so that it passes the top load testing. The predicted parison thickness by the AI model had an absolute average error of 4.18% from the desired thickness.