Bauhaus-Universität Weimar

On-demand inverse design of metamaterials via denoising diffusion probabilistic models

Abstract The nonlinear and non-unique relationship between unit-cell topology and bandgap properties motivates the development of complementary data-driven approaches for metamaterial inverse design. This work presents a conditional denoising diffusion probabilistic model (DDPM)-...

Lightweight return-mapping surrogates for multiscale plasticity: a practical guide

Abstract This paper presents a practical guide to building lightweight neural-network surrogates for the plastic return-mapping process in concurrent multiscale (FE 2 ) simulations. Rather than proposing a new architecture, we show how a deliberately simple feed-forward network,...

Theoretical and Numerical Study on Buckling Analysis of Cylindrical Shell Structures by Galerkin and Finite Element Methods

The structural instability of cylindrical shells has long attracted scholarly attention due to its inherently nonlinear response and extensive engineering relevance. Although numerous investigations have examined buckling phenomena arising from individual loading modes such as ax...

Lessons from the field: usability (engineering) in regulated healthcare

Abstract Regulated healthcare settings continue to face gaps between established HCI methodology, user-centered design principles, and everyday clinical practice. Although standards and regulatory frameworks mandate usability engineering, their integration into regulated clinical...

Towards unified AI-driven fracture mechanics: the extended deep energy method (XDEM)

Abstract Physics-Informed Neural Networks (PINNs) have recently emerged as powerful tools for solving partial differential equations (PDEs), with the Deep Energy Method (DEM) proving especially effective in fracture mechanics due to its energy-based formulation. Despite these adv...

A new behavioral evaluation framework for early-stage spatial optimization in high-mobility transit architecture design by applying virtual reality

Efficient wayfinding and spatial comfort are critical performance dimensions for high-mobility transit architecture, yet user-centered evaluation is rarely integrated into early-stage design workflows. This study proposes a virtual reality (VR)-driven behavioral evaluation framew...