Review on the Application of Deep Learning in Reconstruction of Turbulent Flame DOI

Weiyi Zhu,

Chuang Zhou, Yang Zhang

et al.

International Journal of Aeronautical and Space Sciences, Journal Year: 2025, Volume and Issue: unknown

Published: May 5, 2025

Language: Английский

Flame structure transition and instability excitation by pilot fuel in a centrally staged combustor DOI
Pengfei Fu, Shan Li,

Lingyun Hou

et al.

Physics of Fluids, Journal Year: 2025, Volume and Issue: 37(1)

Published: Jan. 1, 2025

The pilot stage plays a crucial role in central-staged combustion technology. This study aimed to investigate the impact of jet-type on flame structure and instability novel strong coupled centrally staged swirl gas turbine combustor, using both experiments large eddy simulations (LES). Nonlinear dynamic analyses pressure, including phase recurrence plots, were performed alongside proper orthogonal decomposition structures. It is indicated that richer worsens system. An increase equivalence ratio leads enhanced non-premixed downstream shift heat release region. transition results shape from an attached V-shaped intermittent lifting U-shaped flame. surface statistics LES strain rate progress variable gradient lean rich conditions compared. Under conditions, demonstrates increased sensitivity flow field fluctuations, intensifying vortex–flame interactions. interaction causes large-scale stretching even extinction flame, exacerbating observed this study. These insights offer deeper understanding multi-staged central systems.

Language: Английский

Citations

1

Experimental investigation of scale effects on ignition progress in scramjet combustors DOI

P J Li,

Zun Cai, Jianheng Ji

et al.

Physics of Fluids, Journal Year: 2025, Volume and Issue: 37(4)

Published: April 1, 2025

The design of large-scale scramjet combustors encounters challenges due to nonlinear scale effects resulting from geometric scaling combustors. This study investigated the transient ignition caused by through experiments conducted on ethylene-fueled with a similarity ratio 2:1 under inflow Mach number 2.52. Schlieren imaging and CH* chemiluminescence diagnostics were employed systematically analyze spatiotemporal flame evolution characteristics. results indicate that process consists two distinct phases: cavity global establishment. Higher energy substantially reduces time. smaller-scale combustor has shorter times, where kernels directly ignite shear layers. In contrast, larger-scale relies recirculation-dominated propagation, leading longer times. Applying 2-fold partially compensates for scale-induced delay time, achieving temporal comparable theoretical predictions (1:2). larger combustor, benefiting enhanced fuel mixing efficiency relatively thinner boundary layers, enable reliable across multiple positions. It offers essential insights are crucial optimizing strategies in

Language: Английский

Citations

0

A review of deep learning for super-resolution in fluid flows DOI
Filippos Sofos, Dimitris Drikakis

Physics of Fluids, Journal Year: 2025, Volume and Issue: 37(4)

Published: April 1, 2025

Integrating deep learning with fluid dynamics presents a promising path for advancing the comprehension of complex flow phenomena within both theoretical and practical engineering domains. Despite this potential, considerable challenges persist, particularly regarding calibration training models. This paper conducts an extensive review analysis recent developments in architectures that aim to enhance accuracy data interpretation. It investigates various applications, architectural designs, performance evaluation metrics. The covers several models, including convolutional neural networks, generative adversarial physics-informed transformer diffusion reinforcement frameworks, emphasizing components improving reconstruction capabilities. Standard metrics are employed rigorously evaluate models' reliability efficacy producing high-performance results applicable across spatiotemporal data. findings emphasize essential role representing flows address ongoing related systems' high degrees freedom, precision demands, resilience error.

Language: Английский

Citations

0

Clustering investigation of scramjet combustion processes based on contrastive learning DOI

Hedong Liu,

Yuqian Chen, Yue Huang

et al.

Acta Astronautica, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

Citations

0

Review on the Application of Deep Learning in Reconstruction of Turbulent Flame DOI

Weiyi Zhu,

Chuang Zhou, Yang Zhang

et al.

International Journal of Aeronautical and Space Sciences, Journal Year: 2025, Volume and Issue: unknown

Published: May 5, 2025

Language: Английский

Citations

0