Answers are grounded in this paper and cite their sources.
Study optimizes mechanical properties in ceramic composites, suggesting enhanced 3D printing techniques.
This study proposes an Artificial Intelligence-based framework to optimize the 3D printing of high-performance ceramic composites by predicting key mechanical properties from process parameters. A Temporal Attention Recurrent Graph Neural Network (TAR-GNN) models the spatial and temporal relationships between printing parameters, including infill density, wall thickness, and layer height, and output properties such as tensile strength, elongation, and surface roughness. A temporal attention mechanism enhances prediction accuracy by emphasizing critical process features, while Velocity Pausing Particle Swarm Optimization (VPPSO) fine-tunes the model weights to improve convergence and predictive performance. The framework is trained and evaluated using the 3D Printer Dataset for Mechanical Engineers in Python. Performance is assessed using RMSE, accuracy, precision, recall, and F1-score. Experimental results demonstrate that the proposed TAR-GNN-VPPSO framework outperforms CNN, MLP-ANN, and ANN, providing an effective solution for intelligent optimization of ceramic composite additive manufacturing.
No takes yet. Share an insight, caveat, or question.
Karpagavalli et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: