Data-driven surrogate modeling of DSMC solutions using deep neural networks
Aerospace Science and Technology · 2026-01 · 168 · 110785
DOI: 10.1016/j.ast.2025.110785 ↗Kurz gefasst
Fachartikel in der Zeitschrift Aerospace Science and Technology, 2026-01. Verfasst von Ehsan Roohi und 1 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 27 Literaturangaben.
Abstract (Originalsprache)
This study presents a deep neural network (DNN) framework that accelerates Direct Simulation Monte Carlo (DSMC) computations for rarefied-gas flows, while maintaining high physical fidelity. First, a fully connected deep neural network is trained on high-quality DSMC data for seven temperatures (200-650 K) to reproduce the Maxwell-Boltzmann speed distribution of argon. Injecting the physical boundary point into the training set enforces the correct low-speed limit. It reduces the mean-squared error to below 10^-5, thereby decreasing inference time from tens of minutes per DSMC run to milliseconds. For one-dimensional shock waves, a multi-output network equipped with learnable Fourier features learns the complete profiles of density, velocity, and temperature. Trained only on Mach numbers 1.4-1.9, it predicts a Mach 2 and 2.5 case with near-perfect agreement to DSMC, demonstrating robust out-of-training generalization. In a lid-driven cavity, the large parametric spread in Knudsen number is handled by a"family-of-experts"strategy: separate specialist models are trained at discrete Knudsen (Kn) values, and log-space interpolation fuses their outputs. This hybrid surrogate recovers the full 2-D velocity and temperature fields at unseen Kn with less than 2% spatial error. Key innovations include (i) explicit injection of physical constraints during data preprocessing, (ii) learnable Fourier feature mapping to capture steep shock gradients, and (iii) a modular expert-interpolation scheme to cover wide Knudsen ranges. Together, they establish a general recipe for trustworthy, rapid surrogate models that can be extended to non-equilibrium phenomena, gas mixtures, and design optimization workflows
Zitieren
APA
Roohi, E., & Shoja-Sani, A. (2026). Data-driven surrogate modeling of DSMC solutions using deep neural networks. Aerospace Science and Technology, 168, 110785. https://doi.org/10.1016/j.ast.2025.110785
Vancouver
Roohi E, Shoja-Sani A. Data-driven surrogate modeling of DSMC solutions using deep neural networks. Aerospace Science and Technology. 2026;168:110785. doi:10.1016/j.ast.2025.110785
BibTeX
@article{Roohi2026,
author = {Roohi, Ehsan and Shoja-Sani, Ahmad},
title = {Data-driven surrogate modeling of DSMC solutions using deep neural networks},
journal = {Aerospace Science and Technology},
year = {2026},
volume = {168},
pages = {110785},
doi = {10.1016/j.ast.2025.110785}
}
EUVIMED