Non-Linear prediction model for scour and air entrainment based static neural network approach

Research output: Contribution to journalArticle

Abstract

The current study aims at investigating the potential of utilizing the Artificial Neural Network (ANN) in prediction both the scour depth and air entrainment amounts based on previous experimental plunge pool scour tests for inclined circular jets. Furthermore, the current manuscript introduced a single ANN model to predict air entrainment devoid of pre-knowledge of the jet condition either smooth or rough jet. Regarding ANN applicability validation, its prediction results was compared to the earlier experimental results for three regression models; one for scour, and two air-models for a smooth and rough jet. The results from each model out of the three ANN models are proved more accurate than the corresponding pre-developed regression models. Relative error envelop of 5% was found to bound all the records for the prediction of air in both ANN models (smooth and rough). For the prediction of the scour, the ANN model was also better than the regression model with only two data records of 20% relative error. It can be concluded from the presented results that ANN is an efficient, accurate, and robust modeling way to predict scour and air entrainment regardless of the previous knowledge whether a smooth or rough jet boundary conditions are prevailing.

Original languageEnglish
Pages (from-to)400-416
Number of pages17
JournalEuropean Journal of Scientific Research
Volume27
Issue number3
Publication statusPublished - 2009

Fingerprint

Nonlinear Prediction
Air entrainment
Nonlinear Dynamics
Entrainment
Scour
scour
Neural Networks (Computer)
entrainment
Prediction Model
neural networks
Nonlinear Model
Artificial Neural Network
Air
artificial neural network
Neural Networks
Neural networks
air
prediction
Neural Network Model
Rough

Keywords

  • Air entrainment
  • Artificial intelligent model
  • Physical model
  • Plunge pool scour
  • Regression model

ASJC Scopus subject areas

  • General

Cite this

@article{1b3d204956e84d86ad64b442ac90e316,
title = "Non-Linear prediction model for scour and air entrainment based static neural network approach",
abstract = "The current study aims at investigating the potential of utilizing the Artificial Neural Network (ANN) in prediction both the scour depth and air entrainment amounts based on previous experimental plunge pool scour tests for inclined circular jets. Furthermore, the current manuscript introduced a single ANN model to predict air entrainment devoid of pre-knowledge of the jet condition either smooth or rough jet. Regarding ANN applicability validation, its prediction results was compared to the earlier experimental results for three regression models; one for scour, and two air-models for a smooth and rough jet. The results from each model out of the three ANN models are proved more accurate than the corresponding pre-developed regression models. Relative error envelop of 5{\%} was found to bound all the records for the prediction of air in both ANN models (smooth and rough). For the prediction of the scour, the ANN model was also better than the regression model with only two data records of 20{\%} relative error. It can be concluded from the presented results that ANN is an efficient, accurate, and robust modeling way to predict scour and air entrainment regardless of the previous knowledge whether a smooth or rough jet boundary conditions are prevailing.",
keywords = "Air entrainment, Artificial intelligent model, Physical model, Plunge pool scour, Regression model",
author = "Ahmed Elshafie and {A. Karim}, Othman and Taha, {Mohd. Raihan}",
year = "2009",
language = "English",
volume = "27",
pages = "400--416",
journal = "European Journal of Scientific Research",
issn = "1450-202X",
publisher = "European Journals Inc.",
number = "3",

}

TY - JOUR

T1 - Non-Linear prediction model for scour and air entrainment based static neural network approach

AU - Elshafie, Ahmed

AU - A. Karim, Othman

AU - Taha, Mohd. Raihan

PY - 2009

Y1 - 2009

N2 - The current study aims at investigating the potential of utilizing the Artificial Neural Network (ANN) in prediction both the scour depth and air entrainment amounts based on previous experimental plunge pool scour tests for inclined circular jets. Furthermore, the current manuscript introduced a single ANN model to predict air entrainment devoid of pre-knowledge of the jet condition either smooth or rough jet. Regarding ANN applicability validation, its prediction results was compared to the earlier experimental results for three regression models; one for scour, and two air-models for a smooth and rough jet. The results from each model out of the three ANN models are proved more accurate than the corresponding pre-developed regression models. Relative error envelop of 5% was found to bound all the records for the prediction of air in both ANN models (smooth and rough). For the prediction of the scour, the ANN model was also better than the regression model with only two data records of 20% relative error. It can be concluded from the presented results that ANN is an efficient, accurate, and robust modeling way to predict scour and air entrainment regardless of the previous knowledge whether a smooth or rough jet boundary conditions are prevailing.

AB - The current study aims at investigating the potential of utilizing the Artificial Neural Network (ANN) in prediction both the scour depth and air entrainment amounts based on previous experimental plunge pool scour tests for inclined circular jets. Furthermore, the current manuscript introduced a single ANN model to predict air entrainment devoid of pre-knowledge of the jet condition either smooth or rough jet. Regarding ANN applicability validation, its prediction results was compared to the earlier experimental results for three regression models; one for scour, and two air-models for a smooth and rough jet. The results from each model out of the three ANN models are proved more accurate than the corresponding pre-developed regression models. Relative error envelop of 5% was found to bound all the records for the prediction of air in both ANN models (smooth and rough). For the prediction of the scour, the ANN model was also better than the regression model with only two data records of 20% relative error. It can be concluded from the presented results that ANN is an efficient, accurate, and robust modeling way to predict scour and air entrainment regardless of the previous knowledge whether a smooth or rough jet boundary conditions are prevailing.

KW - Air entrainment

KW - Artificial intelligent model

KW - Physical model

KW - Plunge pool scour

KW - Regression model

UR - http://www.scopus.com/inward/record.url?scp=65349109986&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=65349109986&partnerID=8YFLogxK

M3 - Article

VL - 27

SP - 400

EP - 416

JO - European Journal of Scientific Research

JF - European Journal of Scientific Research

SN - 1450-202X

IS - 3

ER -