Prediction of local scour around bridge piers using the ANFIS method

Sung-Uk Choi, Byungwoong Choi, Seonmin Lee

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Local scour around bridge piers is a complicated physical process and involves highly three-dimensional flows. Thus, the scour depth, which is directly related to the safety of a bridge, cannot be given in the form of the exact relationship of dependent variables via an analytical method. This paper proposes the use of the adaptive neuro-fuzzy inference system (ANFIS) method for predicting the scour depth around a bridge pier. Five variables including mean velocity, flow depth, size of sediment particles, critical velocity for particles’ initiation of motion, and pier width were used for the scour depth. For comparison, predictions by the artificial neural network (ANN) model were also provided. Both the ANN model and ANFIS method were trained and validated. The findings indicate that the modeling with dimensional variables yields better predictions than when normalized variables are used. The ANN model was applied to a field-scale dataset. Prediction results indicated that the errors are much larger compared to the case of a laboratory-scale dataset. The MAPE by the ANN model trained with part of the field data was not seriously different from that by the model trained with the laboratory data. However, the application of the ANFIS method improved the predictions significantly, reducing the MAPE to the half of that by the ANN model. Five selected empirical formulas were also applied to the same dataset, and Sheppard and Melville’s formula was found to provide the best prediction. However, the MAPEs for the scour depths predicted by empirical formulas are much larger than MAPEs by either the ANN or the ANFIS method. The ANFIS method predicts much better if the range of the training dataset is sufficiently wide to cover the range of the application dataset.

Original languageEnglish
Pages (from-to)335-344
Number of pages10
JournalNeural Computing and Applications
Volume28
Issue number2
DOIs
Publication statusPublished - 2017 Feb 1

Fingerprint

Bridge piers
Scour
Fuzzy inference
Neural networks
Piers
Flow velocity
Sediments

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Choi, Sung-Uk ; Choi, Byungwoong ; Lee, Seonmin. / Prediction of local scour around bridge piers using the ANFIS method. In: Neural Computing and Applications. 2017 ; Vol. 28, No. 2. pp. 335-344.
@article{b420f89e243f4dbc914d42df57917dcf,
title = "Prediction of local scour around bridge piers using the ANFIS method",
abstract = "Local scour around bridge piers is a complicated physical process and involves highly three-dimensional flows. Thus, the scour depth, which is directly related to the safety of a bridge, cannot be given in the form of the exact relationship of dependent variables via an analytical method. This paper proposes the use of the adaptive neuro-fuzzy inference system (ANFIS) method for predicting the scour depth around a bridge pier. Five variables including mean velocity, flow depth, size of sediment particles, critical velocity for particles’ initiation of motion, and pier width were used for the scour depth. For comparison, predictions by the artificial neural network (ANN) model were also provided. Both the ANN model and ANFIS method were trained and validated. The findings indicate that the modeling with dimensional variables yields better predictions than when normalized variables are used. The ANN model was applied to a field-scale dataset. Prediction results indicated that the errors are much larger compared to the case of a laboratory-scale dataset. The MAPE by the ANN model trained with part of the field data was not seriously different from that by the model trained with the laboratory data. However, the application of the ANFIS method improved the predictions significantly, reducing the MAPE to the half of that by the ANN model. Five selected empirical formulas were also applied to the same dataset, and Sheppard and Melville’s formula was found to provide the best prediction. However, the MAPEs for the scour depths predicted by empirical formulas are much larger than MAPEs by either the ANN or the ANFIS method. The ANFIS method predicts much better if the range of the training dataset is sufficiently wide to cover the range of the application dataset.",
author = "Sung-Uk Choi and Byungwoong Choi and Seonmin Lee",
year = "2017",
month = "2",
day = "1",
doi = "10.1007/s00521-015-2062-1",
language = "English",
volume = "28",
pages = "335--344",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer London",
number = "2",

}

Prediction of local scour around bridge piers using the ANFIS method. / Choi, Sung-Uk; Choi, Byungwoong; Lee, Seonmin.

In: Neural Computing and Applications, Vol. 28, No. 2, 01.02.2017, p. 335-344.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Prediction of local scour around bridge piers using the ANFIS method

AU - Choi, Sung-Uk

AU - Choi, Byungwoong

AU - Lee, Seonmin

PY - 2017/2/1

Y1 - 2017/2/1

N2 - Local scour around bridge piers is a complicated physical process and involves highly three-dimensional flows. Thus, the scour depth, which is directly related to the safety of a bridge, cannot be given in the form of the exact relationship of dependent variables via an analytical method. This paper proposes the use of the adaptive neuro-fuzzy inference system (ANFIS) method for predicting the scour depth around a bridge pier. Five variables including mean velocity, flow depth, size of sediment particles, critical velocity for particles’ initiation of motion, and pier width were used for the scour depth. For comparison, predictions by the artificial neural network (ANN) model were also provided. Both the ANN model and ANFIS method were trained and validated. The findings indicate that the modeling with dimensional variables yields better predictions than when normalized variables are used. The ANN model was applied to a field-scale dataset. Prediction results indicated that the errors are much larger compared to the case of a laboratory-scale dataset. The MAPE by the ANN model trained with part of the field data was not seriously different from that by the model trained with the laboratory data. However, the application of the ANFIS method improved the predictions significantly, reducing the MAPE to the half of that by the ANN model. Five selected empirical formulas were also applied to the same dataset, and Sheppard and Melville’s formula was found to provide the best prediction. However, the MAPEs for the scour depths predicted by empirical formulas are much larger than MAPEs by either the ANN or the ANFIS method. The ANFIS method predicts much better if the range of the training dataset is sufficiently wide to cover the range of the application dataset.

AB - Local scour around bridge piers is a complicated physical process and involves highly three-dimensional flows. Thus, the scour depth, which is directly related to the safety of a bridge, cannot be given in the form of the exact relationship of dependent variables via an analytical method. This paper proposes the use of the adaptive neuro-fuzzy inference system (ANFIS) method for predicting the scour depth around a bridge pier. Five variables including mean velocity, flow depth, size of sediment particles, critical velocity for particles’ initiation of motion, and pier width were used for the scour depth. For comparison, predictions by the artificial neural network (ANN) model were also provided. Both the ANN model and ANFIS method were trained and validated. The findings indicate that the modeling with dimensional variables yields better predictions than when normalized variables are used. The ANN model was applied to a field-scale dataset. Prediction results indicated that the errors are much larger compared to the case of a laboratory-scale dataset. The MAPE by the ANN model trained with part of the field data was not seriously different from that by the model trained with the laboratory data. However, the application of the ANFIS method improved the predictions significantly, reducing the MAPE to the half of that by the ANN model. Five selected empirical formulas were also applied to the same dataset, and Sheppard and Melville’s formula was found to provide the best prediction. However, the MAPEs for the scour depths predicted by empirical formulas are much larger than MAPEs by either the ANN or the ANFIS method. The ANFIS method predicts much better if the range of the training dataset is sufficiently wide to cover the range of the application dataset.

UR - http://www.scopus.com/inward/record.url?scp=84942048113&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84942048113&partnerID=8YFLogxK

U2 - 10.1007/s00521-015-2062-1

DO - 10.1007/s00521-015-2062-1

M3 - Article

VL - 28

SP - 335

EP - 344

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

IS - 2

ER -