[HTML][HTML] Additive-feature-attribution methods: a review on explainable artificial intelligence for fluid dynamics and heat transfer
The use of data-driven methods in fluid mechanics has surged dramatically in recent years
due to their capacity to adapt to the complex and multi-scale nature of turbulent flows, as …
due to their capacity to adapt to the complex and multi-scale nature of turbulent flows, as …
A physics-constrained and data-driven method for modeling supersonic flow
T Zhao, J An, Y Xu, G He, F Qin - Physics of Fluids, 2024 - pubs.aip.org
A fast solution of supersonic flow is one of the crucial challenges in engineering applications
of supersonic flight. This article introduces a deep learning framework, the supersonic …
of supersonic flight. This article introduces a deep learning framework, the supersonic …
[HTML][HTML] Full-scale numerical simulation and experimental validation of the thermal environment under the heating mode in an air-conditioned room
H Zhu, S Hu, G Wang, L Han, M Jing, X Zhao - Case Studies in Thermal …, 2023 - Elsevier
The numerical simulation of the air flow of the room equipped with the crossflow fan air
conditioners has been conducted a lot. However, the simulation of the air flow distribution …
conditioners has been conducted a lot. However, the simulation of the air flow distribution …
Field inversion machine learning augmented turbulence modeling for time-accurate unsteady flow
Field inversion machine learning (FIML) has the advantages of model consistency and low
data dependency and has been used to augment imperfect turbulence models. However …
data dependency and has been used to augment imperfect turbulence models. However …
[HTML][HTML] Implementation and validation of a generalized wall stress function
K Xue, D Quosdorf, L Zhao, M Manhart - Physics of Fluids, 2024 - pubs.aip.org
The generalized wall function by Shih et al.[Report No. M-1999-209398 (1999)], which
accounts for non-equilibrium effects by the presence of favorable and adverse pressure …
accounts for non-equilibrium effects by the presence of favorable and adverse pressure …
[HTML][HTML] Levenberg–Marquardt backpropagation neural networking (LMB-NN) analysis of hydrodynamic forces in fluid flow over multiple cylinders
The mathematical formulation of the flowing liquid stream around and through confined
multiply connected domains brings a complex differential system. Due to this, one cannot …
multiply connected domains brings a complex differential system. Due to this, one cannot …
Scalable Artificial Intelligence for Science: Perspectives, Methods and Exemplars
In a post-ChatGPT world, this paper explores the potential of leveraging scalable artificial
intelligence for scientific discovery. We propose that scaling up artificial intelligence on high …
intelligence for scientific discovery. We propose that scaling up artificial intelligence on high …
Mixed-precision numerics in scientific applications: survey and perspectives
The explosive demand for artificial intelligence (AI) workloads has led to a significant
increase in silicon area dedicated to lower-precision computations on recent high …
increase in silicon area dedicated to lower-precision computations on recent high …
Testing a Generalized Two-Equation Turbulence Model for Computational Aerodynamics of a Mid-Range Aircraft
V Rossano, G De Stefano - Applied Sciences, 2023 - mdpi.com
The generalized k-ω formulation provides a relatively new flexible eddy-viscosity Reynolds-
averaged Navier–Stokes modeling approach to turbulent flow simulation, where free …
averaged Navier–Stokes modeling approach to turbulent flow simulation, where free …
A Machine-Learned Actuator Line Model for Hydrokinetic Turbines
This study introduces a machine-learned actuator Line model (ML-ALM) for hydrokinetic
turbines to enhance computational fluid dynamics (CFD) simulations of turbine wakes and …
turbines to enhance computational fluid dynamics (CFD) simulations of turbine wakes and …