Next Article in Journal
Assessment of Thermal Management Using a Phase-Change Material Heat Sink under Cyclic Thermal Loads
Previous Article in Journal
Novel Custom Loss Functions and Metrics for Reinforced Forecasting of High and Low Day-Ahead Electricity Prices Using Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) and Ensemble Learning
Previous Article in Special Issue
Prediction of Heat Transfer during Condensation of Ammonia Inside Tubes and Annuli
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Review

Assessment of Machine Learning Techniques for Simulating Reacting Flow: From Plasma-Assisted Ignition to Turbulent Flame Propagation

by
Mashrur Ertija Shejan
,
Sharif Md Yousuf Bhuiyan
,
Marco P. Schoen
* and
Rajib Mahamud
*
Department of Mechanical Engineering, Idaho State University, Colonial Hall, Room 102, Pocatello, ID 83209, USA
*
Authors to whom correspondence should be addressed.
Energies 2024, 17(19), 4887; https://doi.org/10.3390/en17194887 (registering DOI)
Submission received: 30 July 2024 / Revised: 24 September 2024 / Accepted: 25 September 2024 / Published: 29 September 2024
(This article belongs to the Special Issue Heat Transfer and Multiphase Flow)

Abstract

Combustion involves the study of multiphysics phenomena that includes fluid and chemical kinetics, chemical reactions and complex nonlinear processes across various time and space scales. Accurate simulation of combustion is essential for designing energy conversion systems. Nonetheless, due to its multiscale, multiphysics nature, simulating these systems at full resolution is typically difficult. The massive and complex data generated from experiments and simulations, particularly in turbulent combustion, presents both a challenge and a research opportunity for advancing combustion studies. Machine learning facilitates data-driven techniques to manage the substantial amount of combustion data that is either obtained through experiments or simulations, and thereby can find the hidden patterns underlying these data. Alternatively, machine learning models can be useful to make predictions with comparable accuracy to existing models, while reducing computational costs significantly. In this era of big data, machine learning is rapidly evolving, offering promising opportunities to explore its integration with combustion research. This work provides an in-depth overview of machine learning applications in turbulent combustion modeling and presents the application of machine learning models: Decision Trees (DT) and Random Forests (RF), for the spatio-temporal prediction of plasma-assisted ignition kernels, based on the initial degree of ionization, with model validations against DNS data. The results demonstrate that properly trained machine learning models can accurately predict the spatio-temporal ignition kernel profile based on the initial energy deposition and distribution.
Keywords: machine learning; combustion; plasma; ignition; turbulence; DNS; DT; RF machine learning; combustion; plasma; ignition; turbulence; DNS; DT; RF

Share and Cite

MDPI and ACS Style

Shejan, M.E.; Bhuiyan, S.M.Y.; Schoen, M.P.; Mahamud, R. Assessment of Machine Learning Techniques for Simulating Reacting Flow: From Plasma-Assisted Ignition to Turbulent Flame Propagation. Energies 2024, 17, 4887. https://doi.org/10.3390/en17194887

AMA Style

Shejan ME, Bhuiyan SMY, Schoen MP, Mahamud R. Assessment of Machine Learning Techniques for Simulating Reacting Flow: From Plasma-Assisted Ignition to Turbulent Flame Propagation. Energies. 2024; 17(19):4887. https://doi.org/10.3390/en17194887

Chicago/Turabian Style

Shejan, Mashrur Ertija, Sharif Md Yousuf Bhuiyan, Marco P. Schoen, and Rajib Mahamud. 2024. "Assessment of Machine Learning Techniques for Simulating Reacting Flow: From Plasma-Assisted Ignition to Turbulent Flame Propagation" Energies 17, no. 19: 4887. https://doi.org/10.3390/en17194887

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.
Back to TopTop