Preliminary design of ruble mound breakwaters by using artificial neural networks Taş Dolgu Dalgakiranlarin Yapay Sinir Aǧlari ile Ön Tasarimi


KOÇ M. L., BALAS C. E., ARSLAN A.

Teknik Dergi/Technical Journal of Turkish Chamber of Civil Engineers, cilt.15, sa.4, ss.3351-3375, 2004 (SCI-Expanded) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 15 Sayı: 4
  • Basım Tarihi: 2004
  • Dergi Adı: Teknik Dergi/Technical Journal of Turkish Chamber of Civil Engineers
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, TR DİZİN (ULAKBİM)
  • Sayfa Sayıları: ss.3351-3375
  • Gazi Üniversitesi Adresli: Evet

Özet

A neural network is an artificial intelligence technique used in complex systems. It is based on the simplified simulation of biological neurons in human brain. Van der Meer equations are utilized for the design of rubble mound breakwaters. Van der Meer equations are the most commonly utilized emprical equations for the preliminary design of rubble mound breakwaters. However, since these equations only represent the mean value of hydraulic model tests, there exists significant uncertainties and variations in the design. In order to pre-design of rubble mound breakwaters, "artificial neural networks for design" were established and applied preliminary design of Mersin Yacht Harbour. The results showed that neural networks have a better performance in the ability of modelling than Van der Meer equations. Artificial neural networks can handle more accurately the uncertainties inherent in the design of rubble mound breakwaters than deterministic design; hence the need of complex models generally used for the design has been significantly decreased.