Research on an SVM Prediction of Welding Deformation Rectification for High-Strength Steel Fillet-Welded Joints after Traveling Induction Heating

IF 0.5 4区 工程技术 Q4 ENGINEERING, MARINE
Yulong Feng, Yujun Liu, Ji Wang, Rui Li
{"title":"Research on an SVM Prediction of Welding Deformation Rectification for High-Strength Steel Fillet-Welded Joints after Traveling Induction Heating","authors":"Yulong Feng, Yujun Liu, Ji Wang, Rui Li","doi":"10.5957/jspd.12210031","DOIUrl":null,"url":null,"abstract":"\n \n To effectively realize the welding deformation rectification of high-strength steel fillet-welded joints in hull construction, a traveling induction coil was used to research the rectification effect of the welding deformation, and the support vector machine (SVM) method was applied to study the ability to predict the rectification amount. Welding and induction heating experiments were carried out on the fillet-welded joints, and finite element models, which were used to expand the prediction sample library of the SVM model, were established according to the experimental process. Then, the induction current, frequency, moving rate of the induction coil, weld deformation amount, and sheet thickness were selected as the input characteristic parameters of the SVM model to predict the rectification results achieved by traveling induction heating. It can be concluded that the established finite element model can accurately simulate the continuous machining process of welding-induction heating in reality, the induction heating method can actively eliminate welding deformation, and the SVM algorithm based on the radial basis function can predict the rectification result of weld deformation with high precision.\n \n \n \n The welding process of fillet-welded joints is one of the most common basic construction process units in shipbuilding, and the welding deformation caused by thermal elastoplastic deformation directly threatens the structural strength of hull construction (Liang et al. 2015; Yi et al. 2020). Extensive results indicate that welding deformation and welding residual stress are the main causes of hull structure deformation and stress corrosion; therefore, how to effectively realize the welding deformation rectification of fillet-welded joints has become a research topic of interest (Zhou & Wang 2019). At present, the flame heating method is the preferred method used to rectify a welding deformation; however, some disadvantages in the flame heating method, which include temperature control difficulties, poor automation, harsh construction environments, and ease of material property damage, can seriously affect the quality and strength of a hull structure (Kotani et al. 2016; Kalyankar & Shah 2018). In contrast, electromagnetic induction heating technology, which has a high degree of controllability, environmental friendliness, high heating efficiency, and low dependence on worker experience, has attracted the attention of researchers (Barclay et al. 2013; Haglund & Kristoffersen 2014).\n","PeriodicalId":48791,"journal":{"name":"Journal of Ship Production and Design","volume":" ","pages":""},"PeriodicalIF":0.5000,"publicationDate":"2022-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Ship Production and Design","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.5957/jspd.12210031","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, MARINE","Score":null,"Total":0}
引用次数: 0

Abstract

To effectively realize the welding deformation rectification of high-strength steel fillet-welded joints in hull construction, a traveling induction coil was used to research the rectification effect of the welding deformation, and the support vector machine (SVM) method was applied to study the ability to predict the rectification amount. Welding and induction heating experiments were carried out on the fillet-welded joints, and finite element models, which were used to expand the prediction sample library of the SVM model, were established according to the experimental process. Then, the induction current, frequency, moving rate of the induction coil, weld deformation amount, and sheet thickness were selected as the input characteristic parameters of the SVM model to predict the rectification results achieved by traveling induction heating. It can be concluded that the established finite element model can accurately simulate the continuous machining process of welding-induction heating in reality, the induction heating method can actively eliminate welding deformation, and the SVM algorithm based on the radial basis function can predict the rectification result of weld deformation with high precision. The welding process of fillet-welded joints is one of the most common basic construction process units in shipbuilding, and the welding deformation caused by thermal elastoplastic deformation directly threatens the structural strength of hull construction (Liang et al. 2015; Yi et al. 2020). Extensive results indicate that welding deformation and welding residual stress are the main causes of hull structure deformation and stress corrosion; therefore, how to effectively realize the welding deformation rectification of fillet-welded joints has become a research topic of interest (Zhou & Wang 2019). At present, the flame heating method is the preferred method used to rectify a welding deformation; however, some disadvantages in the flame heating method, which include temperature control difficulties, poor automation, harsh construction environments, and ease of material property damage, can seriously affect the quality and strength of a hull structure (Kotani et al. 2016; Kalyankar & Shah 2018). In contrast, electromagnetic induction heating technology, which has a high degree of controllability, environmental friendliness, high heating efficiency, and low dependence on worker experience, has attracted the attention of researchers (Barclay et al. 2013; Haglund & Kristoffersen 2014).
高强钢角焊缝移动感应加热后焊接变形校正的SVM预测研究
为有效实现船体结构中高强度钢角焊接头的焊接变形纠偏,采用移动感应线圈对焊接变形的纠偏效果进行了研究,并应用支持向量机(SVM)方法对纠偏量的预测能力进行了研究。对角焊接头进行焊接和感应加热实验,并根据实验过程建立有限元模型,扩展支持向量机模型的预测样本库。然后,选择感应电流、频率、感应线圈的移动速度、焊缝变形量和薄板厚度作为支持向量机模型的输入特征参数,预测行走感应加热的整流效果。结果表明:所建立的有限元模型能够准确模拟现实中焊接-感应加热的连续加工过程,感应加热方法能够主动消除焊接变形,基于径向基函数的支持向量机算法能够高精度地预测焊接变形的纠正结果。角焊接头的焊接工艺是船舶制造中最常见的基础施工工艺单元之一,由热弹塑性变形引起的焊接变形直接威胁到船体结构的强度(Liang et al. 2015;Yi et al. 2020)。大量结果表明,焊接变形和焊接残余应力是导致船体结构变形和应力腐蚀的主要原因;因此,如何有效地实现角焊接头的焊接变形校正成为一个感兴趣的研究课题(Zhou & Wang 2019)。目前,火焰加热法是矫正焊接变形的首选方法;然而,火焰加热方法的一些缺点,包括温度控制困难,自动化程度差,施工环境恶劣,容易损坏材料性能,会严重影响船体结构的质量和强度(Kotani et al. 2016;Kalyankar & Shah 2018)。相比之下,电磁感应加热技术具有可控性高、环境友好、加热效率高、对工人经验依赖性低等特点,引起了研究人员的关注(Barclay et al. 2013;Haglund & Kristoffersen 2014)。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
1.10
自引率
0.00%
发文量
19
期刊介绍: Original and timely technical papers addressing problems of shipyard techniques and production of merchant and naval ships appear in this quarterly publication. Since its inception, the Journal of Ship Production and Design (formerly the Journal of Ship Production) has been a forum for peer-reviewed, professionally edited papers from academic and industry sources. As such it has influenced the worldwide development of ship production engineering as a fully qualified professional discipline. The expanded scope seeks papers in additional areas, specifically ship design, including design for production, plus other marine technology topics, such as ship operations, shipping economics, and safety. Each issue contains a well-rounded selection of technical papers relevant to marine professionals.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信