Neural Inverse Design of Self-Shaping Composites

Self-shaping frustrated composites are fiber-reinforced polymer sheets that transform from a flat state into a three-dimensional geometry without molds, driven by internal stresses embedded in the material. The mechanism relies on geometric frustration: during curing, laminated layers with different fiber orientations create incompatible internal strains. These strains drive the sheet to bend out of plane. Dividing the sheet into patches with distinct fiber orientations encodes the resulting shape in the material layout. The research addresses the inverse problem: determining the fiber layout required to produce a given target geometry. To this end, a computational pipeline was developed, based on a calibrated simulation and convolutional neural networks (CNN), and validated against physical samples.