Artificial intelligence methods in breakwater damage ratio estimation

Yagci O., MERCAN D., CIGIZOGLU H. K., Kabdasli M. S.

OCEAN ENGINEERING, cilt.32, ss.2088-2106, 2005 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 32
  • Basım Tarihi: 2005
  • Doi Numarası: 10.1016/j.oceaneng.2005.03.004
  • Dergi Adı: OCEAN ENGINEERING
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.2088-2106
  • İstanbul Teknik Üniversitesi Adresli: Hayır

Özet

The anticipation of damage ratio with an acceptable accuracy is a vital issue in breakwater design. The presented study covers the employment of three different artificial neural network methods and a fuzzy model for this problem. Inputs like mean wave period, wave steepness, significant wave height and the breakwater slope are used as input to estimate the corresponding damage ratio value. All artificial neural network methods and fuzzy logic model provided quite close estimations for the experimental values. The testing stage results were significantly superior to the conventional multi-linear regression method in terms of the selected performance criteria. (c) 2005 Elsevier Ltd. All rights reserved.