FlowFrontNet: Improving Carbon Composite Manufacturing with CNNs

Carbon fiber reinforced polymers (CFRP) are light yet strong composite materials designed to reduce the weight of aerospace or automotive components – contributing reduced emissions. Resin transfer molding (RTM) is a manufacturing process for CFRP that can be scaled up industrial-sized production. It prone errors such as voids dry spots, resulting in high rejection rates and costs. At runtime, only limited in-process information made available diagnostic insight via grid pressure sensors. We propose FlowFrontNet, deep learning approach enhance in-situ perspective by mapping from sensors flow front “images” (using upscaling layers), capture spatial irregularities predict spots convolutional layers). On simulated data 6 million single time steps 36k injection processes, we achieve step accuracy 91.7% when using \(38 \times 30\) sensor 1 cm distance x- y-direction. \(10 8\), with 4 cm, 83.7% accuracy. In both settings, FlowFrontNet provides significant advantage over direct end-to-end models.