Machine learning-enabled forward prediction and inverse design of 4D-printed active plates.

Shape transformations of active composites (ACs) depend on the spatial distribution of constituent materials. Voxel-level complex material distributions can be encoded by 3D printing, offering enormous freedom for possible shape-change 4D-printed ACs. However, efficiently designing the material distribution to achieve desired 3D shape changes is significantly challenging yet greatly needed. Here, we present an approach that combines machine learning (ML) with both gradient-descent (GD) and evolutionary algorithm (EA) to design AC plates with 3D shape changes. A residual network ML model is developed for the forward shape prediction. A global-subdomain design strategy with ML-GD and ML-EA is then used for the inverse material-distribution design. For a variety of numerically generated target shapes, both ML-GD and ML-EA demonstrate high efficiency. By further combining ML-EA with a normal distance-based loss function, optimized designs are achieved for multiple irregular target shapes. Our approach thus provides a highly efficient tool for the design of 4D-printed active composites.

4D Printing of Freestanding Liquid Crystal Elastomers via Hybrid Additive Manufacturing.

Liquid crystal elastomers (LCE) are appealing candidates among active materials for 4D printing, due to their reversible, programmable and rapid actuation capabilities. Recent progress has been made on direct ink writing (DIW) or Digital Light Processing (DLP) to print LCEs with certain actuation. However, it remains a challenge to achieve complicated structures, such as spatial lattices with large actuation, due to the limitation of printing LCEs on the build platform or the previous layer. Herein, a novel method to 4D print freestanding LCEs on-the-fly by using laser-assisted DIW with an actuation strain up to -40% is proposed. This process is further hybridized with the DLP method for optional structural or removable supports to create active 3D architectures in a one-step additive process. Various objects, including hybrid active lattices, active tensegrity, an actuator with tunable stability, and 3D spatial LCE lattices, can be additively fabricated. The combination of DIW-printed functionally freestanding LCEs with the DLP-printed supporting structures thus provides new design freedom and fabrication capability for applications including soft robotics, smart structures, active metamaterials, and smart wearable devices.