Machine Learning for Dynamic Pressure Coefficient Prediction in Vertical Water Jets

Vertical water jets present significant challenges for hydraulic structures due to their potential to cause erosion and structural damage. This study aimed to predict the dimensionless pressure coefficient (C<sub>p</sub>) of vertical water jets by examining the relationships between expe...

Full description

Saved in:
Bibliographic Details
Main Authors: Amin Salemnia, Seyedehmaryam Hosseini Boldaji, Vida Atashi, Manoochehr Fathi-Moghadam
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Fluids
Subjects:
Online Access:https://www.mdpi.com/2311-5521/9/9/205
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850261273887899648
author Amin Salemnia
Seyedehmaryam Hosseini Boldaji
Vida Atashi
Manoochehr Fathi-Moghadam
author_facet Amin Salemnia
Seyedehmaryam Hosseini Boldaji
Vida Atashi
Manoochehr Fathi-Moghadam
author_sort Amin Salemnia
collection DOAJ
description Vertical water jets present significant challenges for hydraulic structures due to their potential to cause erosion and structural damage. This study aimed to predict the dimensionless pressure coefficient (C<sub>p</sub>) of vertical water jets by examining the relationships between experimental parameters, such as Froude number, slope, and the ratio of waterfall height over the product of the Froude number and diameter, referred to as α, using machine learning models. Two hundred forty controlled experiments were conducted, with pressure data collected. To address the problem’s non-linearity, six machine learning models were tested: linear regression, K-nearest neighbors, decision tree, support vector regression, random forest, and XGBoost. The XGBoost model outperformed others, achieving an R-squared of 0.953 and a Root Mean Squared Error (RMSE) of 0.191. Residual analysis validated its better performance, demonstrating that it delivered the most accurate predictions with minimal bias. Feature importance analysis revealed the Froude number was the most significant predictor, followed by slope and diameter. This study emphasizes the importance of the Froude number in predicting jet behavior and shows the efficacy of advanced machine learning models in capturing complex fluid dynamics, providing valuable insights for optimizing engineering applications such as water jet cutting and cooling systems.
format Article
id doaj-art-fe0c5bc785c04c528399f6fcebbf7f00
institution OA Journals
issn 2311-5521
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Fluids
spelling doaj-art-fe0c5bc785c04c528399f6fcebbf7f002025-08-20T01:55:27ZengMDPI AGFluids2311-55212024-09-019920510.3390/fluids9090205Machine Learning for Dynamic Pressure Coefficient Prediction in Vertical Water JetsAmin Salemnia0Seyedehmaryam Hosseini Boldaji1Vida Atashi2Manoochehr Fathi-Moghadam3Department of Water Engineering, Shahid Chamran University, Ahvaz 6135743136, IranDepartment of Electrical and Computer Engineering, K. N. Toosi University of Technology, Tehran 163171419, IranFaculty of Civil Engineering Department, University of North Dakota, Grand Forks, ND 58202, USAFaculty of Water and Environmental Engineering Department, Shahid Chamran University, Ahvaz 6135743136, IranVertical water jets present significant challenges for hydraulic structures due to their potential to cause erosion and structural damage. This study aimed to predict the dimensionless pressure coefficient (C<sub>p</sub>) of vertical water jets by examining the relationships between experimental parameters, such as Froude number, slope, and the ratio of waterfall height over the product of the Froude number and diameter, referred to as α, using machine learning models. Two hundred forty controlled experiments were conducted, with pressure data collected. To address the problem’s non-linearity, six machine learning models were tested: linear regression, K-nearest neighbors, decision tree, support vector regression, random forest, and XGBoost. The XGBoost model outperformed others, achieving an R-squared of 0.953 and a Root Mean Squared Error (RMSE) of 0.191. Residual analysis validated its better performance, demonstrating that it delivered the most accurate predictions with minimal bias. Feature importance analysis revealed the Froude number was the most significant predictor, followed by slope and diameter. This study emphasizes the importance of the Froude number in predicting jet behavior and shows the efficacy of advanced machine learning models in capturing complex fluid dynamics, providing valuable insights for optimizing engineering applications such as water jet cutting and cooling systems.https://www.mdpi.com/2311-5521/9/9/205vertical water jetsmachine learning modelspressure coefficientFroude number
spellingShingle Amin Salemnia
Seyedehmaryam Hosseini Boldaji
Vida Atashi
Manoochehr Fathi-Moghadam
Machine Learning for Dynamic Pressure Coefficient Prediction in Vertical Water Jets
Fluids
vertical water jets
machine learning models
pressure coefficient
Froude number
title Machine Learning for Dynamic Pressure Coefficient Prediction in Vertical Water Jets
title_full Machine Learning for Dynamic Pressure Coefficient Prediction in Vertical Water Jets
title_fullStr Machine Learning for Dynamic Pressure Coefficient Prediction in Vertical Water Jets
title_full_unstemmed Machine Learning for Dynamic Pressure Coefficient Prediction in Vertical Water Jets
title_short Machine Learning for Dynamic Pressure Coefficient Prediction in Vertical Water Jets
title_sort machine learning for dynamic pressure coefficient prediction in vertical water jets
topic vertical water jets
machine learning models
pressure coefficient
Froude number
url https://www.mdpi.com/2311-5521/9/9/205
work_keys_str_mv AT aminsalemnia machinelearningfordynamicpressurecoefficientpredictioninverticalwaterjets
AT seyedehmaryamhosseiniboldaji machinelearningfordynamicpressurecoefficientpredictioninverticalwaterjets
AT vidaatashi machinelearningfordynamicpressurecoefficientpredictioninverticalwaterjets
AT manoochehrfathimoghadam machinelearningfordynamicpressurecoefficientpredictioninverticalwaterjets