Predicting the NOx emissions of low heat value gas rich-quench-lean combustor via three integrated learning algorithms with Bayesian optimization

P Yan, W Fan, R Zhang - Energy, 2023 - Elsevier
With the increased attention to low heat value gas fuels in recent years, research on NOx
emissions from the combustors of low heat value gas fuels is necessary. This study …

Fast prediction and sensitivity analysis of gas turbine cooling performance using supervised learning approaches

Q Wang, L Yang, K Huang - Energy, 2022 - Elsevier
Fast prediction tools for turbine cooling performance have been demanded by industry for
decades to support the iterative design process and the comprehensive response analysis …

Physics-driven learning of the steady Navier-Stokes equations using deep convolutional neural networks

H Ma, Y Zhang, N Thuerey, X Hu, OJ Haidn - arXiv preprint arXiv …, 2021 - arxiv.org
Recently, physics-driven deep learning methods have shown particular promise for the
prediction of physical fields, especially to reduce the dependency on large amounts of pre …

Deep encoder–decoder hierarchical convolutional neural networks for conjugate heat transfer surrogate modeling

T Ebbs-Picken, DA Romero, CM Da Silva, CH Amon - Applied Energy, 2024 - Elsevier
Conjugate heat transfer (CHT) analyses are vital for the design of many energy systems.
However, high-fidelity CHT numerical simulations are computationally intensive, which limits …

Optimization of the semi-sphere vortex generator for film cooling using generative adversarial network

Y Wang, W Wang, G Tao, H Li, Y Zheng… - International Journal of …, 2022 - Elsevier
Film cooling has shown great potential in protecting hot section of high-pressure turbine
from melting down. A counter-rotating vortex pair (CVP) is produced downstream of the …

Approach to combustion calculation using neural network

VF Nikitin, IM Karandashev, MY Malsagov… - Acta Astronautica, 2022 - Elsevier
Numerical simulations of combustion processes in rocket engines requires a long run time of
supercomputer systems even for a very short physical time. Therefore, creating digital twins …

Deep learning method for fast prediction of film cooling performance

Z Li, L Su, F Wen, J Zeng, S Wang, J Zhang - Physics of Fluids, 2022 - pubs.aip.org
This study examines the predictive capability of deep learning method for adiabatic film
cooling effectiveness distribution with variable operating conditions and geometric layouts. A …

Two-dimensional film-cooling effectiveness prediction based on deconvolution neural network

Y Wang, W Wang, G Tao, X Zhang, S Luo… - … Communications in Heat …, 2021 - Elsevier
For film cooling in high-pressure turbines, it is vital to predict the temperature distribution and
film cooling effectiveness on the blade surface downstream of the cooling hole. This …

Coaxial-injector surrogate modeling based on Reynolds-averaged Navier–Stokes simulations using deep learning

M Krügener, JF Zapata Usandivaras… - Journal of Propulsion …, 2022 - arc.aiaa.org
Facing the need to increase the accuracy of rocket engine design tools, the present work
introduces an innovative methodology for the design and optimization of rocket engine …

Ensemble predictions of laser ignition with a hybrid stochastic physics-embedded deep-learning framework

WT Chung, C Laurent, D Passiatore, M Ihme - Proceedings of the …, 2024 - Elsevier
When investigating stochastic ignition phenomena, high-fidelity simulations and
experiments for statistical characterization can be a laborious endeavor. Machine learning …