Abstract
Temperature of the polymer melt is one of the most important parameters for the polymer continuous extrusion molding process. There are many factors influence the distribution of the melt temperature, these factors have the coupling and nonlinear relationship which is difficult to measure accurately by the traditional measuring method. In this study, a BP neural networks-based model approach is presented in which the effects of the die wall temperature and screw speed and the wall temperature of the transition section and the measurement section in the continuous extrusion molding are investigated. Comparison of the BP neural networks model predictions with the experimental data yields very good agreement and demonstrates that the BP neural networks model can predict the polymer melt temperature field with a high degree of precision (the mean square error within 0.03)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have