The influence of fabric architecture on impregnation behavior and void formation: Artificial neural network and statistical‐based analysis

This work proposes an approach combining artificial neural networks (ANN) with statistical models to predict injection processing conditions for four reinforcement architectures: plain weave, bidirectional noncrimp fabrics, unidirectional fabrics (Uni) and random fiber mats (Random). Key results allow evaluating the velocity of flow front by parameters creating a three-dimensional response surface based on properly trained ANN. investigation is large number experimental results. The key role played some physical was associated predicting impregnation behavior (velocity front) during resin injection. main outcome aims provide better control void content in terms size position fibrous reinforcements considered.