Evolutionary design of a generalized polynomial neural network for modelling sediment transport in clean pipes

Abstract

To determine the minimum velocity required to prevent sedimentation, six different models were proposed to estimate the densimetric Froude number (Fr). The dimensionless parameters of the models were applied along with a combination of the group method of data handling (GMDH) and the multi-target genetic algorithm. Therefore, an evolutionary design of the generalized GMDH was developed using a genetic algorithm with a specific coding scheme so as not to restrict connectivity configurations to abutting layers only. In addition, a new preserving mechanism by the multi-target genetic algorithm was utilized for the Pareto optimization of GMDH. The results indicated that the most accurate model was the one that used the volumetric concentration of sediment (C_V), relative hydraulic radius (d/R), dimensionless particle number (D_gr) and overall sediment friction factor (λ_s) in estimating Fr. Furthermore, the comparison between the proposed method and traditional equations indicated that GMDH is more accurate than existing equations.

Keywords:

• sediment transport
• bed load
• clean pipe
• genetic algorithm
• Pareto optimization

Disclosure statement

No potential conflict of interest was reported by the authors.