Accurate and Efficient Fluid Flow Regime Classification Using Localized Texture Descriptors and Machine Learning

This paper presents an image-based framework for classifying fluid flow regimes into low and high-speed states by utilizing spatially localized texture features combined with machine learning techniques. Traditional approaches, such as Computational Fluid Dynamics (CFD) and Direct Numerical Simulati...

Full description

Saved in:
Bibliographic Details
Main Authors: Manimaran Renganathan, Palani Thanaraj Krishnan, C. Christopher Columbus, T. Sunil Kumar
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11106484/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849391594493444096
author Manimaran Renganathan
Palani Thanaraj Krishnan
C. Christopher Columbus
T. Sunil Kumar
author_facet Manimaran Renganathan
Palani Thanaraj Krishnan
C. Christopher Columbus
T. Sunil Kumar
author_sort Manimaran Renganathan
collection DOAJ
description This paper presents an image-based framework for classifying fluid flow regimes into low and high-speed states by utilizing spatially localized texture features combined with machine learning techniques. Traditional approaches, such as Computational Fluid Dynamics (CFD) and Direct Numerical Simulations (DNS), often require extensive post-processing to extract fluid flow properties. This makes them time-consuming and less practical for real-time applications. To address this, the proposed method leverages the Local Binary Pattern (LBP) feature extraction technique. LBP effectively captures local neighborhood patterns and converts complex flow behaviors into quantifiable texture features from images of CFD. These features are then classified using various machine learning models, namely Random Forest (RF), Support Vector Machines (SVM), and k-Nearest Neighbors (k-NN). The LBP-based approach demonstrates excellent performance, with the k-NN classifier achieving a maximum accuracy of 0.9879 in the case of flow past an elliptical cylinder. Similarly, the SVM classifier attains up to 0.9540 accuracy for the flow past an airfoil. Evaluations cover a range of Reynolds numbers from 200 to 5000 and turbulence intensities of 5% and 20%, confirming the robustness and effectiveness of the method. A comparative analysis with other texture-based techniques, namely Local Ternary Pattern (LTP) and Gray Level Co-occurrence Matrix (GLCM), further highlights the advantages of the proposed method. The LBP approach outperforms LTP and GLCM by 14.5% and 2.4%, respectively, in terms of prediction accuracy. This demonstrates the superior capability of LBP in flow regime classification. The dataset used in this study is publicly available at: <uri>https://www.kaggle.com/datasets/palanithanarajk/fluid-flow-images</uri>
format Article
id doaj-art-a5555899bbb145fcb891567e9e2f0129
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-a5555899bbb145fcb891567e9e2f01292025-08-20T03:41:01ZengIEEEIEEE Access2169-35362025-01-011313633613635110.1109/ACCESS.2025.359485011106484Accurate and Efficient Fluid Flow Regime Classification Using Localized Texture Descriptors and Machine LearningManimaran Renganathan0Palani Thanaraj Krishnan1https://orcid.org/0000-0002-4214-9685C. Christopher Columbus2https://orcid.org/0000-0002-7525-1328T. Sunil Kumar3https://orcid.org/0000-0003-0934-7230School of Mechanical Engineering, Vellore Institute of Technology, Chennai, IndiaSchool of Computer Science and Engineering, Vellore Institute of Technology, Chennai, IndiaSchool of Computer Science and Engineering, Vellore Institute of Technology, Chennai, IndiaDepartment of Electrical Engineering, Mathematics and Science, University of G&#x00E4;vle, G&#x00E4;vle, SwedenThis paper presents an image-based framework for classifying fluid flow regimes into low and high-speed states by utilizing spatially localized texture features combined with machine learning techniques. Traditional approaches, such as Computational Fluid Dynamics (CFD) and Direct Numerical Simulations (DNS), often require extensive post-processing to extract fluid flow properties. This makes them time-consuming and less practical for real-time applications. To address this, the proposed method leverages the Local Binary Pattern (LBP) feature extraction technique. LBP effectively captures local neighborhood patterns and converts complex flow behaviors into quantifiable texture features from images of CFD. These features are then classified using various machine learning models, namely Random Forest (RF), Support Vector Machines (SVM), and k-Nearest Neighbors (k-NN). The LBP-based approach demonstrates excellent performance, with the k-NN classifier achieving a maximum accuracy of 0.9879 in the case of flow past an elliptical cylinder. Similarly, the SVM classifier attains up to 0.9540 accuracy for the flow past an airfoil. Evaluations cover a range of Reynolds numbers from 200 to 5000 and turbulence intensities of 5% and 20%, confirming the robustness and effectiveness of the method. A comparative analysis with other texture-based techniques, namely Local Ternary Pattern (LTP) and Gray Level Co-occurrence Matrix (GLCM), further highlights the advantages of the proposed method. The LBP approach outperforms LTP and GLCM by 14.5% and 2.4%, respectively, in terms of prediction accuracy. This demonstrates the superior capability of LBP in flow regime classification. The dataset used in this study is publicly available at: <uri>https://www.kaggle.com/datasets/palanithanarajk/fluid-flow-images</uri>https://ieeexplore.ieee.org/document/11106484/Image processingflow classificationcomputational fluid dynamicslow and high-speed flowlocal binary pattern
spellingShingle Manimaran Renganathan
Palani Thanaraj Krishnan
C. Christopher Columbus
T. Sunil Kumar
Accurate and Efficient Fluid Flow Regime Classification Using Localized Texture Descriptors and Machine Learning
IEEE Access
Image processing
flow classification
computational fluid dynamics
low and high-speed flow
local binary pattern
title Accurate and Efficient Fluid Flow Regime Classification Using Localized Texture Descriptors and Machine Learning
title_full Accurate and Efficient Fluid Flow Regime Classification Using Localized Texture Descriptors and Machine Learning
title_fullStr Accurate and Efficient Fluid Flow Regime Classification Using Localized Texture Descriptors and Machine Learning
title_full_unstemmed Accurate and Efficient Fluid Flow Regime Classification Using Localized Texture Descriptors and Machine Learning
title_short Accurate and Efficient Fluid Flow Regime Classification Using Localized Texture Descriptors and Machine Learning
title_sort accurate and efficient fluid flow regime classification using localized texture descriptors and machine learning
topic Image processing
flow classification
computational fluid dynamics
low and high-speed flow
local binary pattern
url https://ieeexplore.ieee.org/document/11106484/
work_keys_str_mv AT manimaranrenganathan accurateandefficientfluidflowregimeclassificationusinglocalizedtexturedescriptorsandmachinelearning
AT palanithanarajkrishnan accurateandefficientfluidflowregimeclassificationusinglocalizedtexturedescriptorsandmachinelearning
AT cchristophercolumbus accurateandefficientfluidflowregimeclassificationusinglocalizedtexturedescriptorsandmachinelearning
AT tsunilkumar accurateandefficientfluidflowregimeclassificationusinglocalizedtexturedescriptorsandmachinelearning