Full text not available from this repository.

Abstract

Increasing attention has recently been paid to the effects of localised pitting corrosion on the ultimate Q2 strength of marine structures. In this paper, an adaptive neuro-fuzzy inference system (ANFIS) method was developed to predict the ultimate strength reduction of steel plates with pitting corrosion subjected to uniaxial in-plane compressive loads. Published ultimate strength data-sets for unstiffened plates affected by pitting corrosion were used to train and test a series of ANFIS models composed of input variables. In order to develop the best accurate model, rule-based fuzzy sets were used for mapping the inputs to the output using seven different types of membership functions. The two-sidedGaussian-type function was found to be more effective and less sensitive to the sample size than other functions tested. The developed method provided good estimates (maximum RMSE of 0.019) in comparison with published results obtained using the finite element and artificial neural network methods.

Item Type:	Article
Authors/Creators:	Abdussamie, N and Ojeda, R and Daboos, M
Keywords:	marine structures, pitting corrosion, adaptive neuro-fuzzy inference system method
Journal or Publication Title:	Ships and Offshore Structures
Publisher:	Taylor & Francis
ISSN:	1744-5302
DOI / ID Number:	10.1080/17445302.2018.1439668
Copyright Information:	Copyright © 2018 Informa UK Limited
Related URLs:	Google Scholar: Abdussamie, N UTAS Profile: Ojeda, R
Item Statistics:	View statistics for this item

Actions (login required)

Item Control Page