J. Ocean Eng. Technol. Search


J. Ocean Eng. Technol. 2006;20(4):24-30.    

Application of Neural Network to the Estimation of Curvature Deformation of Steel Plates in Line Heating
Jeon, Byung-Jae;Kim, Hyun-Jun;Yang, Park-Dal-Chi;
Mastek Heavy Industry Co. Ltd.;Far East Ship Design & Engineering Co. Ltd;School of Naval Architecture and Ocean Engineering, Univ. of Ulsan;
인공신경망을 적용한 선상가열시 강판의 곡률변형 추정
마스텍중공업(주);(주)극동선박설계;울산대학교 조선해양공학부;
Copyright © 2006 The Korean Society of Ocean Engineers     Open access / Under a Creative Commons License
Key Words: Line heating, Curvature deformation, Gaussian curvature, Neural network
핵심용어: 선상가열, 곡률변형, 가우스 곡률, 신경망
Different methods exist for the estimation of thermaldeformation of plates in the line heating process. These are based on the assumption of residual strains in the heat-affected zone, known as the method of inherent strains, or simulated relations between heating conditions and residual deformations. The purpose of this paper is to develop a simulator of thermal deformation in the line heating, using the artificial neural network. Curvature deformations for the plate-forming are investigated, which can be used as a prime deformation parameter in the process. The curvature of plates are calculated using the approximation of plate surface by NURBS. Line heating experiments for 11 specimens of different thickness and heating conditions were performed. Two neural networks predicting the maximum temperature and curvature deformations at the heating line are studied. It was concluded that the thermal deformations predicted by the neural network can be used in a line heating simulator, which is considered an attractive and practical alternative to the existing methods.


Browse all articles >

Editorial Office
President Office BD Rm. 1302, 13 Jungang-daero 180beon-gil, Dong-gu, Busan 48821, Republic of Korea
Tel: +82-51-759-0656    Fax: +82-51-759-0656    E-mail: ksoehj@ksoe.or.kr                

Copyright © 2022 by The Korean Society of Ocean Engineers.

Developed in M2PI

Close layer
prev next