Scour prediction in long contractions using ANFIS and SVM

OCEAN ENGINEERING

卷:111

Article

Najafzadeh, Mohammad¹  Etemad-Shahidi, Amir²  Lim, Siow Yong³ 

[1] Grad Univ Adv Technol Kerman, Dept Civil Engn, Kerman, Iran

[2] Griffith Univ, Griffith Sch Engn, Southport, Qld 4215, Australia

[3] Nanyang Technol Univ, Sch Civil & Environm Engn, Singapore 639798, Singapore

关键词: Adaptive Neuro-Fuzzy Inference System;    Support vector machines;    Long contraction;    Rectangular channel;    Scour depth;    Traditional equations;   

DOI  :  10.1016/j.oceaneng.2015.10.053

来源: Elsevier

【 摘 要 】

Protection of the channel bed in waterways against scour phenomena in long contractions is a very significant issue in channels design. Several field and experimental investigations were carried out to produce a relationship between the scour depth due to the contracted channels width and the governing variables. However, existing empirical equations do not always provide accurate scour prediction due to the complexity of the scour process. This paper investigates local scour depth in long contractions of rectangular channels using the Adaptive Neuro-Fuzzy Inference System (ANFIS) and Support Vector Machines (SVM). For modeling of ANFIS and SVM, the input parameters that affect the scour phenomena are average flow velocity, critical threshold velocity of sediment movement, flow depth, median particle diameter, geometric standard deviation, un-contracted and contracted channel widths. Training and testing stages of the models are carried out using experimental data collected from different literature. The performances of the developed models are compared with those calculated using existing scour prediction equations. The results show that the developed ANFIS model can predict scour depth more accurately than SVM and the existing equations. A sensitivity analysis is also performed to determine the most important parameter in predicting the scour depth in long contractions. (C) 2015 Elsevier Ltd. All rights reserved.

【 授权许可】

Free