Reduced-order modeling of supersonic fuel–air mixing in a multi-strut injection scramjet engine using machine learning techniques

Ispir, Ali Can; Zdybał, Kamila; Saracoglu, Bayindir H.; Magin, Thierry; Parente, Alessandro; Coussement, Axel

doi:10.1016/j.actaastro.2022.11.013

Cited by 15 publications

(2 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contemporary research practices, the generation of substantial datasets based on either physics-based models or experimental data has become a prevailing trend across diverse scientific domains. This approach serves the dual purpose of mitigating computational complexities while harnessing the capabilities of state-of-the-art machine learning models [32]. In the context of our study, we meticulously curated a dataset by drawing from the results of Computational Fluid…”

Section: Artificial Neural Network Algorithmmentioning

confidence: 99%

A Study on Machine Learning Models’ Capability as an Alternative for CFD in Modeling Heat Transfer

Godasiaei

2024

Preprint

View full text Add to dashboard Cite

This research assesses the viability of utilizing machine learning models as alternatives to computational fluid dynamics for heat transfer modeling. Driven by a heightened interest in evaluating the benefits of machine learning for precise predictions in forced convection heat transfer, the study investigates the potential of artificial neural networks, super-gradient boosting, and random forests as alternatives to traditional methods. Employing artificial intelligence algorithms and implemented through Python software, the methodology conducts a meticulous analysis of a dataset comprising 210 data points. The dataset includes critical heat transfer parameters such as nanoparticle characteristics, size, Reynolds number, Nusselt number, and volume fraction. The selected machine learning algorithms are systematically applied to predict forced convection heat transfer outcomes, and their accuracy is rigorously assessed through comparisons using machine learning R-Squared, Mean Absolute Error, and Root Mean Squared Error values. The results demonstrate promising predictive capabilities, with super-gradient boosting, random forest, and artificial neural network models achieving accuracies of 91%, 90%, and 86%, respectively. The corresponding mean squared error values of 1.07, 1.65, and 16.1 underscore the high accuracy and predictive prowess of these machine learning models in simulating forced convection heat transfer processes.

show abstract

Section: Artificial Neural Network Algorithmmentioning

confidence: 99%

A Study on Machine Learning Models’ Capability as an Alternative for CFD in Modeling Heat Transfer

Godasiaei

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Numerical simulations help investigate the performances of such engines while avoiding the repetition of experimental tests, which can be expensive and difficult to set up. For instance, the fuel injection strategy has a varying impact on the efficiency of mixing and combustion that can be attained in scramjets, and several injection configurations have been numerically investigated, such as cavity-based [4][5][6], dual-cavity [7,8], strut [9,10], multi-strut injections [11], or the combination of multiple strategies [12][13][14], to assess whether design variations are advantageous for experimental testing and prototyping.…”

Section: Introductionmentioning

confidence: 99%

Mixing time scale analysis of the Partially Stirred Reactor model for high-speed turbulent combustion of hydrogen in vitiated air

Piscopo,

Iavarone,

Savarese

et al. 2024

Acta Astronautica

Self Cite

View full text Add to dashboard Cite

Reduced Order Computational Methods for the Development of Propulsive Technologies for Supersonic Aviation to Achieve Climate Neutrality

Van den Borre,

Ispir,

Cakir

et al. 2024

Advanced Computational Methods and Design for Greener Aviation

View full text Add to dashboard Cite

Reduced-order modeling of supersonic fuel–air mixing in a multi-strut injection scramjet engine using machine learning techniques

Cited by 15 publications

References 49 publications

A Study on Machine Learning Models’ Capability as an Alternative for CFD in Modeling Heat Transfer

A Study on Machine Learning Models’ Capability as an Alternative for CFD in Modeling Heat Transfer

Mixing time scale analysis of the Partially Stirred Reactor model for high-speed turbulent combustion of hydrogen in vitiated air

Reduced Order Computational Methods for the Development of Propulsive Technologies for Supersonic Aviation to Achieve Climate Neutrality

Contact Info

Product

Resources

About