Prediction of Temperature Distribution with Deep Learning Approaches for SM1 Flame Configuration

This study investigates the application of deep learning (DL) techniques for predicting temperature fields in the SM1 swirl-stabilized turbulent non-premixed flame. Two distinct DL approaches were developed using a comprehensive CFD database generated via the steady laminar flamelet model coupled wi...

Full description

Saved in:
Bibliographic Details
Main Authors: Gökhan Deveci, Özgün Yücel, Ali Bahadır Olcay
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/14/3783
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246483525664768
author Gökhan Deveci
Özgün Yücel
Ali Bahadır Olcay
author_facet Gökhan Deveci
Özgün Yücel
Ali Bahadır Olcay
author_sort Gökhan Deveci
collection DOAJ
description This study investigates the application of deep learning (DL) techniques for predicting temperature fields in the SM1 swirl-stabilized turbulent non-premixed flame. Two distinct DL approaches were developed using a comprehensive CFD database generated via the steady laminar flamelet model coupled with the SST k-ω turbulence model. The first approach employs a fully connected dense neural network to directly map scalar input parameters—fuel velocity, swirl ratio, and equivalence ratio—to high-resolution temperature contour images. In addition, a comparison was made with different deep learning networks, namely Res-Net, EfficientNetB0, and Inception Net V3, to better understand the performance of the model. In the first approach, the results of the Inception V3 model and the developed Dense Model were found to be better than Res-Net and Efficient Net. At the same time, file sizes and usability were examined. The second framework employs a U-Net-based convolutional neural network enhanced by an RGB Fusion preprocessing technique, which integrates multiple scalar fields from non-reacting (cold flow) conditions into composite images, significantly improving spatial feature extraction. The training and validation processes for both models were conducted using 80% of the CFD data for training and 20% for testing, which helped assess their ability to generalize new input conditions. In the secondary approach, similar to the first approach, studies were conducted with different deep learning models, namely Res-Net, Efficient Net, and Inception Net, to evaluate model performance. The U-Net model, which is well developed, stands out with its low error and small file size. The dense network is appropriate for direct parametric analyses, while the image-based U-Net model provides a rapid and scalable option to utilize the cold flow CFD images. This framework can be further refined in future research to estimate more flow factors and tested against experimental measurements for enhanced applicability.
format Article
id doaj-art-3c3d5b25fd5747ed8fa1c2e227dc5513
institution Kabale University
issn 1996-1073
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-3c3d5b25fd5747ed8fa1c2e227dc55132025-08-20T03:58:30ZengMDPI AGEnergies1996-10732025-07-011814378310.3390/en18143783Prediction of Temperature Distribution with Deep Learning Approaches for SM1 Flame ConfigurationGökhan Deveci0Özgün Yücel1Ali Bahadır Olcay2Department of Mechanical Engineering, Yeditepe University, Istanbul 34755, TurkeyDepartment of Chemical Engineering, Gebze Technical University, Kocaeli 41400, TurkeyPadnos College of Engineering, Grand Valley State University, Grand Rapids, MI 49504, USAThis study investigates the application of deep learning (DL) techniques for predicting temperature fields in the SM1 swirl-stabilized turbulent non-premixed flame. Two distinct DL approaches were developed using a comprehensive CFD database generated via the steady laminar flamelet model coupled with the SST k-ω turbulence model. The first approach employs a fully connected dense neural network to directly map scalar input parameters—fuel velocity, swirl ratio, and equivalence ratio—to high-resolution temperature contour images. In addition, a comparison was made with different deep learning networks, namely Res-Net, EfficientNetB0, and Inception Net V3, to better understand the performance of the model. In the first approach, the results of the Inception V3 model and the developed Dense Model were found to be better than Res-Net and Efficient Net. At the same time, file sizes and usability were examined. The second framework employs a U-Net-based convolutional neural network enhanced by an RGB Fusion preprocessing technique, which integrates multiple scalar fields from non-reacting (cold flow) conditions into composite images, significantly improving spatial feature extraction. The training and validation processes for both models were conducted using 80% of the CFD data for training and 20% for testing, which helped assess their ability to generalize new input conditions. In the secondary approach, similar to the first approach, studies were conducted with different deep learning models, namely Res-Net, Efficient Net, and Inception Net, to evaluate model performance. The U-Net model, which is well developed, stands out with its low error and small file size. The dense network is appropriate for direct parametric analyses, while the image-based U-Net model provides a rapid and scalable option to utilize the cold flow CFD images. This framework can be further refined in future research to estimate more flow factors and tested against experimental measurements for enhanced applicability.https://www.mdpi.com/1996-1073/18/14/3783SM1 flamedeep learningRGB fusionCFDcombustion model
spellingShingle Gökhan Deveci
Özgün Yücel
Ali Bahadır Olcay
Prediction of Temperature Distribution with Deep Learning Approaches for SM1 Flame Configuration
Energies
SM1 flame
deep learning
RGB fusion
CFD
combustion model
title Prediction of Temperature Distribution with Deep Learning Approaches for SM1 Flame Configuration
title_full Prediction of Temperature Distribution with Deep Learning Approaches for SM1 Flame Configuration
title_fullStr Prediction of Temperature Distribution with Deep Learning Approaches for SM1 Flame Configuration
title_full_unstemmed Prediction of Temperature Distribution with Deep Learning Approaches for SM1 Flame Configuration
title_short Prediction of Temperature Distribution with Deep Learning Approaches for SM1 Flame Configuration
title_sort prediction of temperature distribution with deep learning approaches for sm1 flame configuration
topic SM1 flame
deep learning
RGB fusion
CFD
combustion model
url https://www.mdpi.com/1996-1073/18/14/3783
work_keys_str_mv AT gokhandeveci predictionoftemperaturedistributionwithdeeplearningapproachesforsm1flameconfiguration
AT ozgunyucel predictionoftemperaturedistributionwithdeeplearningapproachesforsm1flameconfiguration
AT alibahadırolcay predictionoftemperaturedistributionwithdeeplearningapproachesforsm1flameconfiguration