EUVIMEDEUVIMED entdecken
Crossref

Scalable Super-Resolution of Flow Conveyance Systems Through Adaptive Domain Decomposition

Wenzhuo Xu, Akibi Archer, Mike McCarrell, Scott Hesser, Noelia Grande Gutiérrez, Christopher McComb

Journal of Computing and Information Science in Engineering · 01.12.2026 · 26 (12)

DOI: 10.1115/1.4071858 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computing and Information Science in Engineering, online erschienen am 22.06.2026. Verfasst von Wenzhuo Xu und 5 weiteren Autor:innen. Die Arbeit nennt 71 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modern engineering design requires high-fidelity simulations, which can impose an enormous computational burden and slow the speed of design iteration. Data-driven up-sampling methods like physics-informed neural networks (PINNs) help reduce the computational resources required. However, machine learning model capacity and hardware limitations still pose challenges when evaluating large engineering simulations with complex physics dynamics. Recently, methods have been proposed to enforce the principle of locality in physical systems to neural network layers, allowing for concurrent inference on smaller subdomains with improved efficiency and accuracy. Based on such an idea, we extend the theory of domain decomposition to complex three-dimensional geometries using graph neural networks (GNNs). We developed a graph decomposition method to improve the training and inference efficiency of machine learning models. Super-resolution GNNs are then trained on individual subdomains distributed among GPU nodes. This approach significantly reduces computational overhead while maintaining simulation accuracy. We validate the method’s performance on two engineering applications: a variable inlet-angle mixing elbow junction and a low-pressure bleed duct from an Airbus A350 aircraft. For the elbow geometry with varying inlet angles (0–60 deg), the framework achieves R2 values exceeding 0.995 for velocity predictions across all configurations while demonstrating adaptability to different flow geometries and the presence of secondary flows. For the larger-scale Airbus duct system, we achieve 0.9947 in R2 metric in velocity and 0.9996 in pressure compared with high-fidelity simulations, with a 5.5× computational speedup and reciprocal scaling with GPU count. These results demonstrate that our approach can effectively bridge the gap between computational efficiency and simulation fidelity across different scales of complex engineering design tasks.

Zitieren

APA

Xu, W., Archer, A., McCarrell, M., Hesser, S., Gutiérrez, N. G., & McComb, C. (2026). Scalable Super-Resolution of Flow Conveyance Systems Through Adaptive Domain Decomposition. Journal of Computing and Information Science in Engineering, 26(12). https://doi.org/10.1115/1.4071858

Vancouver

Xu W, Archer A, McCarrell M, Hesser S, Gutiérrez NG, McComb C. Scalable Super-Resolution of Flow Conveyance Systems Through Adaptive Domain Decomposition. Journal of Computing and Information Science in Engineering. 2026;26(12). doi:10.1115/1.4071858

BibTeX
@article{Xu2026,
  author = {Xu, Wenzhuo and Archer, Akibi and McCarrell, Mike and Hesser, Scott and Gutiérrez, Noelia Grande and McComb, Christopher},
  title = {Scalable Super-Resolution of Flow Conveyance Systems Through Adaptive Domain Decomposition},
  journal = {Journal of Computing and Information Science in Engineering},
  year = {2026},
  volume = {26},
  number = {12},
  doi = {10.1115/1.4071858}
}
Kostenlos starten →