Estimating downstream scour of the grade-control structure using nonlinear regression and genetic programming

Masume Fattahi, Babak Lashkar-Ara, Mahsa Valipour

Thursday 2 july 2015

12:33 - 12:36h at South America (level 0)

Themes: (T) Water engineering, (ST) Hydraulic machinery and industrial flows, Poster pitches

Parallel session: Poster pitches: 11C. Engineering - Industrial

This paper describes nonlinear regression and genetic programming approachs for predicting scour downstream of grade control structures. dimensional analysis and nonlinear regression-based equations proposed for estimation of maximum scour depth, location of the scour hole, location and height of the dune downstream of the structures.In the second part, The GP-based formulation results are compared with experimental results and other accurate equations .The results analysis showed that the equations derived using Forward Stepwise nonlinear regression method have correlation coefficient of R^2= 0.962 and 0.971 respectively for estimating the relative parameter of maximum scour depth (s/z) in comparison with the genetic programming model. Furthermore, the slope of the fitted line extracted from computations and observations for dimensionless parameters s/z, Xs/z , hd/z ,XD/z using both model indicate the superiority of nonlinear regression equations over genetic programming (GP) . Keywords: nonlinear regression, genetic programming, scour, grade-control structures