Effect Investigation of Process Parameters on 3D Printed Composites Tensile Performance Boosted by Attention Mechanism-Enhanced Multi-Modal Convolutional Neural Networks.

Fused Deposition Modeling (FDM) is a widely used additive manufacturing technique that enables the fabrication of components using polymeric and composite materials; however, the mechanical performance of printed parts is jointly influenced by multiple printing parameters, which complicates the control and prediction of their mechanical properties. In this study, an attention-enhanced multi-modal convolutional neural network (ATT-MM-CNN) is developed to predict the tensile performance of carbon fiber reinforced polylactic acid (PLA-CF) composites manufactured by FDM. Four key printing parameters, layer thickness, nozzle temperature, material flow rate, and printing speed, are systematically investigated, resulting in 256 parameter combinations and corresponding tensile test data for constructing a multi-modal dataset. By integrating multi-modal feature representations and incorporating an attention mechanism, the proposed model effectively learns the nonlinear relationships between printing parameters and mechanical performance under multi-parameter conditions. The results show that all evaluation metrics, including accuracy, precision, recall, and F1-score, exceed 0.95, and the prediction accuracy is improved by at least 17.3% compared with baseline models. These findings demonstrate that the proposed ATT-MM-CNN provides an effective and reliable framework for tensile property prediction and process-parameter optimization of FDM-printed composite structures.