Natural Hazards

, Volume 80, Issue 3, pp 1891–1911

Prediction of temporal scour hazard at bridge abutment

  • Reza Mohammadpour
  • Aminuddin Ab. Ghani
  • Mohammadtaghi Vakili
  • Tooraj Sabzevari
Original Paper

DOI: 10.1007/s11069-015-2044-8

Cite this article as:
Mohammadpour, R., Ghani, A.A., Vakili, M. et al. Nat Hazards (2016) 80: 1891. doi:10.1007/s11069-015-2044-8
  • 208 Downloads

Abstract

The scour around abutments is a major damage of bridge which appears during the flood hazard. Accurate prediction of scour depth at abutment is very essential to estimate foundation level for a cost-effective design. The accuracy of conventional method is low for prediction of temporal scour depth. However, in this study, two robust techniques, adaptive neuro-fuzzy inference system (ANFIS) and artificial neural networks (ANNs), were employed to estimate temporal scour depth at abutment. All experiments were conducted under clear-water conditions. Extensive data sets were collected from present and previous studies. To determine the best method, two models of ANNs, feed forward back propagation (FFBP) and radial basis function (RBF), and two kinds of ANFIS, subtractive clustering and grid partition, were investigated. The results showed that the accuracy of the FFBP with two hidden layers (RMSE = 0.011) is higher than that of RBF (RMSE = 0.055), multiple linear regression method (RMSE = 0.049) and previous empirical equations. A comparable prediction was provided by the ANFIS-grid partition method with RMSE = 0.041. This research highlights that the ANN-FFBP and ANFIS-grid partition can be successfully employed for prediction of scour hazard and reduction in bridge failure.

Keywords

Scour hazard Flood hazard Erosion Abutment scour Time variation Artificial neural networks Scour time 

List of symbols

bi

Bias

ds

Scour depth at time t

dse

Equilibrium scour depth

d50

Median size of the bed material

Fd

\({U \mathord{\left/ {\vphantom {U {\sqrt {\Delta \,gd_{50} } }}} \right. \kern-0pt} {\sqrt {\Delta \,gd_{50} } }}\) (Particles Froude number)

g

Gravity acceleration

I

Flow intensity

KG

Coefficient of channel cross-section geometry

Kθ

Coefficients of abutment alignment

Ks

Coefficients of abutment shape

L

Abutment length

n

Number of data

Oi

Observed value

\(\bar{O}_{i}\)

Average of observed value

Pi

Predicted value

Re

UL/ν (Abutment Reynolds number)

t

Time of scouring

te

Equilibrium time of scouring

T*

Time when ds = 0.632 dse

U

Mean flow velocity

Uc

Critical velocity for the beginning of motion of bed material

wi

ith weight of network

Xn

Normalized value of X

xi

Neuron value

y

Approach flow depth

ϕ(x)

Softmax transfer function

ρ

Fluid density

ρs

Sediment density

ν

Fluid kinematic viscosity

σg

Geometric standard deviation

Δ

(ρs − ρ)/ρ (Relative density)

μj

Center of radial basis function

σj

Radius of radial basis function

µAi(x) and µBi(x)

Membership functions

Copyright information

© Springer Science+Business Media Dordrecht 2015

Authors and Affiliations

  • Reza Mohammadpour
    • 1
    • 2
  • Aminuddin Ab. Ghani
    • 2
  • Mohammadtaghi Vakili
    • 3
  • Tooraj Sabzevari
    • 1
  1. 1.Department of Civil Engineering, Estahban BranchIslamic Azad UniversityEstahbanIran
  2. 2.REDACUniversiti Sains MalaysiaNibong TebalMalaysia
  3. 3.School of Industrial TechnologyUniversiti Sains MalaysiaNibong TebalMalaysia

Personalised recommendations