Application of a pattern recognition method to estimate wind loads on ships and marine objects

Abstract

AbstractThis paper presents an extension of the application capabilities of elliptic Fourier descriptors from the usual pattern recognition and classification problems to problems of very complex nonlinear multivariable approximations of multi‐input and multi‐output functions. Wind loads on ships and marine objects are a complicated phenomenon because of the complex configuration of the above‐water part of the structure. The proposed approach of the wind load estimation method presented in this paper consists of four basic parts: acquisition and pre‐processing of vessel images; image editing; data preparation for neural network training; validating and testing of the created neural network. The method is based on elliptic Fourier features of a closed contour which are used for the frontal and lateral closed contour representation of ships. Therefore, this approach takes into account all aspects of the variability of the above‐water frontal and lateral ship profile. For the purpose of multivariate nonlinear regression, the generalized regression radial basis neural network is trained by elliptic Fourier features of closed contours and wind load data derived from wind tunnel tests. The trained neural network is used for the estimation of non‐dimensional wind load coefficients. The results for a group of car carriers are presented and compared with the experimental data.