Design analysis for thermoforming of thermoplastic composites: prediction and machine learning-based optimization

The correct prediction of a composite parts’ final performance is paramount importance during the initial design phase manufacturing process. To this end evaluation most effective process parameters and their influence on parts key for success Our aim with paper to provide methodologies temperature field in thermoplastic composites thermoforming propose strategy parameter selection. We measured variations over different stages compared these values analytical finite element results. results show accuracy predictions laminate respect spring-in angle. discuss essential features needed accurate fields whole at an early stage potential Machine Learning procedure based Artificial Neural Network optimum range desired part outcome. In conclusion, we guidelines blank predictions, benefit machine learning-based tool traditional approaches.