Diffusion transformers with hybrid conditioning for structural optimization
Structural and Multidisciplinary Optimization · 2026-10 · 69 (10)
DOI: 10.1007/s00158-026-04429-0 ↗Kurz gefasst
Fachartikel in der Zeitschrift Structural and Multidisciplinary Optimization, online erschienen am 09.10.2026. Verfasst von Aaron Lutheran und 2 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Digital Engineering - USA.
Abstract (Originalsprache)
This work presents a diffusion transformer framework for data-driven structural topology optimization that combines the accuracy of physics-based methods with the efficiency of generative deep learning. Conventional density-based approaches which use the solid isotropic material with penalization (SIMP) scheme with a gradient update require repeated finite element analyses at every iteration, making large-scale or real-time optimization computationally expensive. We propose a hybrid conditioning diffusion transformer (DiT) model that learns to generate near-optimal topologies directly from problem definitions, eliminating iterative analysis during inference. The model integrates spatially distributed conditioning through concatenated stress and strain fields and global conditioning via adaptive layer normalization (AdaLN) using scalar descriptors such as load position, magnitude, and prescribed volume fraction. A dataset of 30,000 two-dimensional SIMP-optimized structures was generated for training and evaluation. Results demonstrate that the proposed DiT achieves less than 1% compliance errors relative to ground-truth SIMP solutions while maintaining accurate volume fractions and structural connectivity. Deterministic DDIM sampling enables high-fidelity topology generation in seconds using as few as five denoising steps, enabling near-real-time performance. The hybrid conditioning diffusion transformer thus provides an efficient and scalable alternative to traditional topology optimization methods, with strong potential for integration into interactive computer-aided design workflows.
Förderung
- Institute of Digital Engineering - USA
Zitieren
APA
Lutheran, A., Das, S., & Tabarraei, A. (2026). Diffusion transformers with hybrid conditioning for structural optimization. Structural and Multidisciplinary Optimization, 69(10). https://doi.org/10.1007/s00158-026-04429-0
Vancouver
Lutheran A, Das S, Tabarraei A. Diffusion transformers with hybrid conditioning for structural optimization. Structural and Multidisciplinary Optimization. 2026;69(10). doi:10.1007/s00158-026-04429-0
BibTeX
@article{Lutheran2026,
author = {Lutheran, Aaron and Das, Srijan and Tabarraei, Alireza},
title = {Diffusion transformers with hybrid conditioning for structural optimization},
journal = {Structural and Multidisciplinary Optimization},
year = {2026},
volume = {69},
number = {10},
doi = {10.1007/s00158-026-04429-0}
}
EUVIMED