Additive manufacturing (AM), as resource-efficient fabrication processes, could also be used in the dimensions of the construction industry, as a variety of experimental projects using concrete and steel demonstrate. In timber construction, currently few additive technologies have been developed having the potential to be used in large scale. Currently known AM processes use wood in pulverized form, losing its inherent structural and mechanical properties. This research proposes a new material that maintains a complete wood structure with continuous and strong fibers, and that can be fabricated from fast-growing locally harvested plants. We describe the material technology to create a solid and continuous filament made of willow twigs and investigate binding and robotic AM methods for flat, curved, lamination, and hollow layering geometric typologies. The resulting willow filament and composite material are characterized for structural capacity and fabrication constraints. We discuss our technology in comparison with veneer-based lamination, existing wood filament printing, and fiberbased AM in terms of fabrication, material capacity, and sustainability. We conclude by showing possible applications in the construction industry and future research possibilities.

No abstract

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.

No abstract

No abstract