Diatom-inspired architected materials using language-based deep learning: Perception, transformation and manufacturing
This work addresses the challenge of creating nature-inspired architected materials for applications in materials science and engineering, but it appears incremental as it builds on existing computational methods.
The paper tackled the problem of generating biologically inspired designs of diatom structures by using transformer neural networks and natural language models to learn and transfer insights, resulting in a series of novel designs and a manufactured specimen created via additive manufacturing.
Learning from nature has been a quest of humanity for millennia. While this has taken the form of humans assessing natural designs such as bones, butterfly wings, or spider webs, we can now achieve generating designs using advanced computational algorithms. In this paper we report novel biologically inspired designs of diatom structures, enabled using transformer neural networks, using natural language models to learn, process and transfer insights across manifestations. We illustrate a series of novel diatom-based designs and also report a manufactured specimen, created using additive manufacturing. The method applied here could be expanded to focus on other biological design cues, implement a systematic optimization to meet certain design targets, and include a hybrid set of material design sets.