[HTML][HTML] Machine learning for combustion

L Zhou, Y Song, W Ji, H Wei - Energy and AI, 2022 - Elsevier
Combustion science is an interdisciplinary study that involves nonlinear physical and
chemical phenomena in time and length scales, including complex chemical reactions and …

Recent advances and effectiveness of machine learning models for fluid dynamics in the built environment

T Van Quang, DT Doan, GY Yun - International Journal of …, 2024 - Taylor & Francis
Indoor environmental quality is crucial for human health and comfort, necessitating precise
and efficient computational methods to optimise indoor climate parameters. Recent …

A critical review of physical models in high temperature multiphase fluid dynamics: Turbulent transport and particle-wall interactions

N Jain, A Le Moine… - Applied …, 2021 - asmedigitalcollection.asme.org
This review article examines the last decade of studies investigating solid, molten, and liquid
particle interactions with one another and with walls in heterogeneous multiphase flows …

Deep-learning accelerated calculation of real-fluid properties in numerical simulation of complex flowfields

PJ Milan, JP Hickey, X Wang, V Yang - Journal of Computational Physics, 2021 - Elsevier
A deep-learning based approach is developed for efficient evaluation of thermophysical
properties in numerical simulation of complex real-fluid flows. The work enables a significant …

Efficient premixed turbulent combustion simulations using flamelet manifold neural networks: A priori and a posteriori assessment

C Chi, X Xu, D Thévenin - Combustion and Flame, 2022 - Elsevier
Flamelet-based reduced manifold tabulation is very useful to save computing time compared
to simulations of turbulent flames with detailed kinetics. However, conventional tabulation …

Field inversion for data-augmented RANS modelling in turbomachinery flows

A Ferrero, A Iollo, F Larocca - Computers & Fluids, 2020 - Elsevier
Turbulence modelling in turbomachinery flows remains a challenge, especially when
transition and separation phenomena occur. Recently, several research efforts have been …

FluxNet: a physics-informed learning-based Riemann solver for transcritical flows with non-ideal thermodynamics

JCH Wang, JP Hickey - Computer Methods in Applied Mechanics and …, 2023 - Elsevier
Traditional Riemann solvers fall into two broad categories: exact solvers, which require
multiple iterations to achieve high accuracy, and approximate linearized solvers, which …

Application of machine learning in low-order manifold representation of chemistry in turbulent flames

A Mousemi, M Jadidi, SB Dworkin… - Combustion Theory and …, 2023 - Taylor & Francis
The Uniform Conditional State (UCS) and the Multidimensional Flamelet Manifold (MFM)
models are methods for the tabulation of chemistry in simulations of turbulent flames. The …

Gradient-harmonizing-based deep learning for thermophysical properties of carbon dioxide

C Ni, X Wang, H Liu, K Zhang, X Zheng… - Journal of Thermophysics …, 2023 - arc.aiaa.org
Carbon dioxide presents many unique advantages for cooling and power cycles under
supercritical or near-critical conditions, where the characterization of thermophysical …

[HTML][HTML] Application of dense neural networks for manifold-based modeling of flame-wall interactions

J Bissantz, J Karpowski, M Steinhausen, Y Luo… - Applications in Energy …, 2023 - Elsevier
Artifical neural networks (ANNs) are universal approximators capable of learning any
correlation between arbitrary input data with corresponding outputs, which can also be …