We present a hybrid approach to manufacturing a new class of large-scale self-shaping structures through a method of additive fabrication combining fused granular fabrication (FGF) and integrated hygroscopic wood actuators (HWAs). Wood materials naturally change shape with high forces in response to moisture stimuli. The strength and simplicity of this actuation make the material suitable for self-shaping architectural-scale components. However, the anisotropic composition of wood, which enables this inherent behavior, cannot be fully customized within existing stock. On the other hand, FGF allows for the design of large physical parts with multi-functional interior substructures as inspired by many biological materials. We propose to encode passively actuated movement into physical structures by integrating HWAs within 3D-printed meta-structures with functionally graded stiffnesses. By leveraging robotic manufacturing platforms, self-shaping biocomposite material systems can be upscaled with variable resolutions and at high volumes, resulting in large-scale structures capable of transforming from flat to curved simply through changes in relative humidity.
This paper develops a workflow to train machine learning (ML) models with a small dataset from physical samples to predict the curvatures of self-shaping wood bilayers based on local variations in the grain. In contrast to state-of-the-art predictive models, specifically 1.) a 2D Timoshenko model and 2.) a 3D numerical model with a rheological model, our method accounts for natural and unavoidable material variations. In this paper, we only focus on local grain variations as the main driver for curvatures in small-scale material samples. We extracted a feature matrix from grain images of active and passive layers as a Grey Level Co-Occurrence Matrix and used it as the input for our ML models. We also analysed the impact of grain variations on the feature matrix. We trained and tested several tree-based regression models with different features. The models achieved very accurate predictions for curvatures in each sample (R²>0.9) and extend the range of parameters that is incalculable by a Timoshenko model. This research contributes to the material-efficient design of weatherresponsive shape-changing wood structures by further leveraging the use of natural material features and explainable data-driven modelling and extends the topic in ML for material behaviour-driven design among the CAADRIA community.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.