TY - JOUR
T1 - Design analysis for thermoforming of thermoplastic composites
T2 - Prediction and machine learning-based optimization
AU - Nardi, Davide
AU - Sinke, Jos
PY - 2021
Y1 - 2021
N2 - The correct prediction of a composite parts’ final performance is of paramount importance during the initial design phase of the manufacturing process. To this end the correct evaluation of the most effective process parameters and their influence on the parts performance is key for the success of the manufacturing process. Our aim with this paper is to provide methodologies for the prediction of the temperature field in thermoplastic composites during thermoforming and to propose a strategy for process parameter selection. We measured the temperature variations over the different thermoforming stages and compared these values with analytical and finite element results. Our results show the accuracy of the predictions and the importance of the correct laminate temperature with respect to the prediction of the parts’ spring-in angle. We discuss the essential features needed for accurate predictions of the temperature fields over the whole thermoforming process at an early design stage and the potential of a Machine Learning procedure based on Artificial Neural Network to aim for the optimum range of process parameters for a desired part performance outcome. In conclusion, we provide essential guidelines for blank temperature predictions, and the benefit of a machine learning-based tool over traditional approaches.
AB - The correct prediction of a composite parts’ final performance is of paramount importance during the initial design phase of the manufacturing process. To this end the correct evaluation of the most effective process parameters and their influence on the parts performance is key for the success of the manufacturing process. Our aim with this paper is to provide methodologies for the prediction of the temperature field in thermoplastic composites during thermoforming and to propose a strategy for process parameter selection. We measured the temperature variations over the different thermoforming stages and compared these values with analytical and finite element results. Our results show the accuracy of the predictions and the importance of the correct laminate temperature with respect to the prediction of the parts’ spring-in angle. We discuss the essential features needed for accurate predictions of the temperature fields over the whole thermoforming process at an early design stage and the potential of a Machine Learning procedure based on Artificial Neural Network to aim for the optimum range of process parameters for a desired part performance outcome. In conclusion, we provide essential guidelines for blank temperature predictions, and the benefit of a machine learning-based tool over traditional approaches.
KW - Analytical solutions
KW - Finite element analysis
KW - Machine learning
KW - Manufacturing
UR - http://www.scopus.com/inward/record.url?scp=85113307025&partnerID=8YFLogxK
U2 - 10.1016/j.jcomc.2021.100126
DO - 10.1016/j.jcomc.2021.100126
M3 - Article
AN - SCOPUS:85113307025
SN - 2666-6820
VL - 5
JO - Composites Part C: Open Access
JF - Composites Part C: Open Access
M1 - 100126
ER -