AN APPLICATION OF SOFT COMPUTING TECHNIQUES TOPREDICT DYNAMIC BEHAVIOUR OF MOORING SYSTEMS

Brodogradnja

article

Mentes, Ayhan¹  Yetkin, Murat² 

[1] Istanbul Technical University, Faculty of Naval Architecture and Ocean Engineering, Department of Shipbuilding & Ocean Engineering;INHA University, Department of Naval Architecture & OceanEngineering, Incheon

关键词: Spread Mooring System;    Soft Computing;    Artificial Neural Network;    Adaptive Neuro-Fuzzy Inference System;    OrcaFlex;   

DOI  :  10.21278/brod73207

学科分类：工程和技术（综合）

来源: Brodarski Institut

【 摘 要 】

A spread mooring system (SMS) allows a ship or a floating platform to moor the seafloorusing multiple mooring lines at a restricted region with a fixed heading in harsh weather. Thesesystems can be used for the operations of ships of different tonnage at different sea depths. Theoptimal design of these systems is a challenging engineering problem because of the effects ofmany design parameters and changing environmental conditions. Modern soft computingtechniques allow difficult engineering problems to be solved easily and precisely and arebecoming more and more popular. In this paper, Artificial Neural Network (ANN) andAdaptive Neuro-Fuzzy Inference System (ANFIS) as soft computation techniques have beenchosen to estimate the hawser tensions and displacements of a spread mooring system. Theattained results show both techniques can give consistent indicators for the modelling ofdynamic systems. Although these techniques performed very well, the ANFIS model isrelatively superior to the ANN technique, considering the accuracy of hawser tensions anddisplacements in terms of the relative errors and coefficient of correlation obtained for the ANNand ANFIS.

【 授权许可】

CC BY