Artificial Intelligence #topology optimization#convolutional neural network
New CNN Model eCNNTO Cuts Topology Optimization Iterations by Up to 97%
Researchers propose eCNNTO, a convolutional neural network that accelerates density-based topology optimization by predicting near-optimal densities from early iteration histories. The model achieves up to 90% reduction in iterations for 2D problems and 97% for 3D, requiring only small training datasets and generalizing to diverse boundary conditions and geometries.
Jun 20, 2026 1 source