Cover Image

Applied machine learning to estimate length of separation and reattachment flows as parameter active flow control in backward facing step / Ahmad Fakhri Giyats, Mohamad Yamin and Cokorda Prapti Mahandari

Recently, large amounts of data from experimental measurements and simulations with high fidelity have extensively accelerated fluid mechanics advancement. Machine learning (ML) offers a wealth of techniques to extract data that can be translated into knowledge about the underlying fluid mechanics....

Full description

Saved in:
Bibliographic Details
Main Authors: Giyats, Ahmad Fakhri, Yamin, Mohamad, Cokorda Prapti Mahandari, Cokorda Prapti Mahandari
Format: Article
Language:English
Published: Faculty of Mechanical Engineering Universiti Teknologi MARA (UiTM) 2023
Subjects:
Hydraulic machinery
Online Access:https://ir.uitm.edu.my/id/eprint/84115/1/84115.pdf
https://doi.org/10.24191/jmeche.v20i3.23904
https://ir.uitm.edu.my/id/eprint/84115/
https://doi.org/10.24191/jmeche.v20i3.23904
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uitm.ir.84115
record_format eprints
spelling my.uitm.ir.841152023-09-18T03:50:39Z https://ir.uitm.edu.my/id/eprint/84115/ Applied machine learning to estimate length of separation and reattachment flows as parameter active flow control in backward facing step / Ahmad Fakhri Giyats, Mohamad Yamin and Cokorda Prapti Mahandari jmeche Giyats, Ahmad Fakhri Yamin, Mohamad Cokorda Prapti Mahandari, Cokorda Prapti Mahandari Hydraulic machinery Recently, large amounts of data from experimental measurements and simulations with high fidelity have extensively accelerated fluid mechanics advancement. Machine learning (ML) offers a wealth of techniques to extract data that can be translated into knowledge about the underlying fluid mechanics. Backward-Facing Step (BFS) is well-known for its application to fluid mechanics, particularly flow turbulence. Typically, a numerical approach can be used to understand the flow phenomena on BFS. In some instances, numerical investigations have a computational time limitation. This paper examines the application of ML to predict reattachment length on BFS flow. The procedure begins with a simulated meshing sensitivity of 1.27 cm in step height. This numerical analysis was conducted in the turbulent zone with a Reynolds number between 35587 and 40422. OpenFOAM® was used to perform numerical simulations using the turbulence model of k-omega shear stress transport. ML employed information in the form of Velocity and Pressure at every node to represent the type of turbulence. Using Recurrent Neural Networks (RNNs) as the most effective model to predict reattachment length values, the reattachment length was predicted with a Root Mean Square Error of 0.013. Faculty of Mechanical Engineering Universiti Teknologi MARA (UiTM) 2023-09 Article PeerReviewed text en https://ir.uitm.edu.my/id/eprint/84115/1/84115.pdf Applied machine learning to estimate length of separation and reattachment flows as parameter active flow control in backward facing step / Ahmad Fakhri Giyats, Mohamad Yamin and Cokorda Prapti Mahandari. (2023) Journal of Mechanical Engineering (JMechE) <https://ir.uitm.edu.my/view/publication/Journal_of_Mechanical_Engineering_=28JMechE=29/>, 20 (3): 7. pp. 131-154. ISSN 1823-5514 ; 2550-164X https://doi.org/10.24191/jmeche.v20i3.23904 https://doi.org/10.24191/jmeche.v20i3.23904
institution Universiti Teknologi Mara
building Tun Abdul Razak Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Mara
content_source UiTM Institutional Repository
url_provider http://ir.uitm.edu.my/
language English
topic Hydraulic machinery
spellingShingle Hydraulic machinery
Giyats, Ahmad Fakhri
Yamin, Mohamad
Cokorda Prapti Mahandari, Cokorda Prapti Mahandari
Applied machine learning to estimate length of separation and reattachment flows as parameter active flow control in backward facing step / Ahmad Fakhri Giyats, Mohamad Yamin and Cokorda Prapti Mahandari
description Recently, large amounts of data from experimental measurements and simulations with high fidelity have extensively accelerated fluid mechanics advancement. Machine learning (ML) offers a wealth of techniques to extract data that can be translated into knowledge about the underlying fluid mechanics. Backward-Facing Step (BFS) is well-known for its application to fluid mechanics, particularly flow turbulence. Typically, a numerical approach can be used to understand the flow phenomena on BFS. In some instances, numerical investigations have a computational time limitation. This paper examines the application of ML to predict reattachment length on BFS flow. The procedure begins with a simulated meshing sensitivity of 1.27 cm in step height. This numerical analysis was conducted in the turbulent zone with a Reynolds number between 35587 and 40422. OpenFOAM® was used to perform numerical simulations using the turbulence model of k-omega shear stress transport. ML employed information in the form of Velocity and Pressure at every node to represent the type of turbulence. Using Recurrent Neural Networks (RNNs) as the most effective model to predict reattachment length values, the reattachment length was predicted with a Root Mean Square Error of 0.013.
format Article
author Giyats, Ahmad Fakhri
Yamin, Mohamad
Cokorda Prapti Mahandari, Cokorda Prapti Mahandari
author_facet Giyats, Ahmad Fakhri
Yamin, Mohamad
Cokorda Prapti Mahandari, Cokorda Prapti Mahandari
author_sort Giyats, Ahmad Fakhri
title Applied machine learning to estimate length of separation and reattachment flows as parameter active flow control in backward facing step / Ahmad Fakhri Giyats, Mohamad Yamin and Cokorda Prapti Mahandari
title_short Applied machine learning to estimate length of separation and reattachment flows as parameter active flow control in backward facing step / Ahmad Fakhri Giyats, Mohamad Yamin and Cokorda Prapti Mahandari
title_full Applied machine learning to estimate length of separation and reattachment flows as parameter active flow control in backward facing step / Ahmad Fakhri Giyats, Mohamad Yamin and Cokorda Prapti Mahandari
title_fullStr Applied machine learning to estimate length of separation and reattachment flows as parameter active flow control in backward facing step / Ahmad Fakhri Giyats, Mohamad Yamin and Cokorda Prapti Mahandari
title_full_unstemmed Applied machine learning to estimate length of separation and reattachment flows as parameter active flow control in backward facing step / Ahmad Fakhri Giyats, Mohamad Yamin and Cokorda Prapti Mahandari
title_sort applied machine learning to estimate length of separation and reattachment flows as parameter active flow control in backward facing step / ahmad fakhri giyats, mohamad yamin and cokorda prapti mahandari
publisher Faculty of Mechanical Engineering Universiti Teknologi MARA (UiTM)
publishDate 2023
url https://ir.uitm.edu.my/id/eprint/84115/1/84115.pdf
https://doi.org/10.24191/jmeche.v20i3.23904
https://ir.uitm.edu.my/id/eprint/84115/
https://doi.org/10.24191/jmeche.v20i3.23904
_version_ 1778165991779336192
score 13.211869

Similar Items