Loading...

Discussion of “Neuro-fuzzy GMDH systems based evolutionary algorithms to predict scour pile groups in clear water conditions” by M. Najafzadeh

Beheshti, A. A ; Sharif University of Technology

247 Viewed
  1. Type of Document: Article
  2. DOI: 10.1016/j.oceaneng.2016.07.005
  3. Publisher: Elsevier Ltd
  4. Abstract:
  5. The author utilized neuro-fuzzy based group method of data handling (NF-GMDH) to predict the local scour depth around pile groups under clear-water conditions. They collected the datasets from literature. To predict the local scour by using NF-GMDH, nine dimensional parameters were considered to define a functional relationship between input and output variables. The results of NF- GMDH networks were compared with that of the empirical equations. However, the collected datasets for pile group scouring, the method of implementing the empirical formula to calculate scour depth, and using the equation of Sheppard et al. (2004) suggested for single pier to predict local scouring around pile groups merits this discussion. Here, we will establish that a part of applied data and also some of the implemented equations were not related to pile group scour. The empirical formulations were not employed correctly too and all the conclusions and results of the paper are disbelieving. Finally, we will discuss on the wide use of various artificial intelligent methods
  6. Keywords:
  7. Empirical equations ; Neuro-fuzzy systems ; Pile group ; Scour
  8. Source: Ocean Engineering ; Volume 123 , 2016 , Pages 249-252 ; 00298018 (ISSN)
  9. URL: http://www.sciencedirect.com/science/article/pii/S0029801816302451