A Study of Mechanical Kansei Using Force-Flow as a Cue

The capability to make unconscious and intuitive judgments for the mechanics aspect of an object is called Mechanical Kansei, and there are attempts to elucidate how this capability is utilized in the realization of structural rationality within the design process. This study focuses on the fact that there are many descriptions of the internal force-flow within the structure in explanations of functional beauty and design education. We hypothesize that the intuitive ability to visualize these force-flows without mechanical analysis is based on Mechanical Kansei. We try to reproduce that intuitive process by training a deep learning network model that can generate the stress tensor distribution inside the structure under various conditions without a mechanics-based model. The obtained network model implies a mapping from structural conditions to the stress tensors that can be used to derive the principal stresses. The directional distribution of these principal stresses suggests the force-flow and could help us understand the Mechanical Kansei.