Prediction of berm geometry using a set of laboratory tests combined with teaching-learning-based optimization and artificial bee colony algorithms


UZLU E. , Komurcu M. I. , Kankal M. , DEDE T. , ÖZTÜRK H. T.

APPLIED OCEAN RESEARCH, vol.48, pp.103-113, 2014 (Journal Indexed in SCI) identifier identifier

  • Publication Type: Article / Article
  • Volume: 48
  • Publication Date: 2014
  • Doi Number: 10.1016/j.apor.2014.08.002
  • Title of Journal : APPLIED OCEAN RESEARCH
  • Page Numbers: pp.103-113
  • Keywords: Coastal profiles, Cross-shore sediment transport, Berm, Accretion, Teaching-learning-based optimization, Artificial bee colony algorithm, PARAMETER OPTIMIZATION, NEURAL-NETWORKS, BEACH RIDGES, SWASH ZONE, EROSION, DESIGN, DYNAMICS, SAND, ACCRETION, SYSTEM

Abstract

Understanding sediment movement in coastal areas is crucial in planning the stability of coastal structures, the recovery of coastal areas, and the formation of new coast. Accretion or erosion profiles form as a result of sediment movement. The characteristics of these profiles depend on the bed slope, wave conditions, and sediment properties. Here, experimental studies were performed in a wave flume with regular waves, considering different values for the wave height (H-0), wave period (T), bed slope (m), and mean sediment diameter (d(50)). Accretion profiles developed in these experiments, and the geometric parameters of the resulting berms were determined. Teaching-learning-based optimization (TLBO) and artificial bee colony (ABC) algorithms were applied to regression functions of the data from the physical model. Dimensional and dimensionless equations were found for each parameter. These equations were compared to data from the physical model, to determine the best equation for each parameter and to evaluate the performances of the TLBO and ABC algorithms in the estimation of the berm parameters. Compared to the ABC algorithm, the TLBO algorithm provided better accuracy in estimating the berm parameters. Overall, the equations successfully determined the berm parameters. (C) 2014 Elsevier Ltd. All rights reserved.