[1]杨金超,王锡栋.船用高强钢T型接头焊接角变形预测仿真[J].应用科技,2017,(04):12-15.[doi:10.11991/yykj.201607020]
 YANG Jinchao,WANG Xidong.Simulation of T-joint based welding angular deformation in marine high-strength steel[J].yykj,2017,(04):12-15.[doi:10.11991/yykj.201607020]
点击复制

船用高强钢T型接头焊接角变形预测仿真(/HTML)
分享到:

《应用科技》[ISSN:1009-671X/CN:23-1191/U]

卷:
期数:
2017年04期
页码:
12-15
栏目:
船舶与海洋工程
出版日期:
2017-08-05

文章信息/Info

Title:
Simulation of T-joint based welding angular deformation in marine high-strength steel
作者:
杨金超1 王锡栋2
1. 中国船级社 秦皇岛分社, 河北 秦皇岛 066001;
2. 哈尔滨工程大学 船舶工程学院, 黑龙江 哈尔滨 150001
Author(s):
YANG Jinchao1 WANG Xidong2
1. Qinhuangdao Branch, China Classification Society, Qinhuangdao 066001, China;
2. College of Shipbuilding Engineering, Harbin Engineering University, Harbin 150001, China
关键词:
人工神经网络T型接头角变形BP神经网络模型焊接工艺船体钢结构仿真计算MATLAB
Keywords:
artificial neural networkT-jointangular deformationBP neural network modelwelding processhull steel structuresimulation calculationMATLAB
分类号:
U671.83
DOI:
10.11991/yykj.201607020
文献标志码:
A
摘要:
以船用高强钢的T型接头为研究对象,在物理模拟试验的基础上,基于人工神经网络调用MATLAB软件的工具箱建立船用高强钢T型接头角变形BP神经网络模型,仿真焊接工艺参数、底板厚度、焊接顺序等因素对角变形的影响,探索抑制船体钢结构焊接角变形的有效措施。结果表明该方法可以快速预测、预报船舶T型接头焊接过程中产生的角变形量。测试结果与仿真结果之间的偏差较小,采用分段退焊的角变形量最小,T型接头焊接角变形随焊接电流的增大而增大,随底板板厚增加而减小。
Abstract:
Based on the physical tests of marine T-joint, the back-propagation network was built by using Artificial Neural Network (ANN) tool box of MATLAB software during CO2 welding. The influence of welding parameters, plate thickness and welding sequence on angular deformation was simulated. The valid path of controlling the welding angular deformation for marine high-strength steel was attained. The results show that the method can predict and forecast the angular deformation of the T-joint in the ship. The deviation between the test result and the simulation result is small, the angular deformation of the segmented welding is the smallest, and the angular deformation increases with the increase of the welding current and decreases with the increase of the plate thickness.

参考文献/References:

[1] 王凯, 李冬青, 张忠典, 等. 人工神经网络及其在焊接中的应用与展望[J]. 焊接, 2005(6):5-9.
[2] 乔小杰. 基于BP神经网络钢/铝激光焊工艺优化及组织性能研究[D]. 长沙:湖南大学, 2013.
[3] 杨建国, 周号, 雷靖, 等. 焊接应力与变形数值模拟领域的若干关键问题[J]. 焊接, 2014(3):8-17.
[4] ROSEN C J, GUMENYUK A, ZHAO H, et al. Influence of local heat treatment on residual stresses in electron beam welding[J]. Science & technology of welding & joining, 2007, 12(7):614-619.
[5] LIU C, WU B, ZHANG J X. Numerical investigation of residual stress in thick titanium alloy plate joined with electron beam welding[J]. Metallurgical & materials transactions B, 2010, 41(5):1129-1138.
[6] HU J F, YANG J G, FANG H Y, et al. Numerical simulation on temperature and stress fields of welding with weaving[J]. Science & technology of welding & joining, 2013, 11(3):358-365.
[7] ZHANG T, WU C S, QIN G L, et al. Thermomechanical analysis for Laser + GMAW-P hybrid welding process[J]. Computational materials science, 2010, 47(3):848-856.
[8] 田鹏. 基于壳单元的船体典型接头焊接变形与残余应力预测[D]. 上海:上海交通大学, 2014.
[9] 张磊. 船体装焊过程精度控制关键技术的研究[D]. 哈尔滨:哈尔滨工程大学, 2014.
[10] 梁国俐. 基于有限元和人工神经网络的焊接过程数值模拟[D]. 大连:连理工大学, 2004.
[11] 万嘉礼. 机电工程金属材料手册[M]. 上海:上海科学技术出版社, 1990.
[12] 李亚芝. T型焊接构件固有应变规律的研究及应用[J]. 门窗, 2015(9):256.

相似文献/References:

[1]张家驹,吴洪涛.基于神经网络的机器人无标定视觉伺服系统仿真[J].应用科技,2011,(09):1.[doi:10.3969/j.issn.1009671X.2011.09.01]
 ZHANG Jiaju,WU Hongtao.Simulation of an uncalibrated robotic visual servo system based on neural network[J].yykj,2011,(04):1.[doi:10.3969/j.issn.1009671X.2011.09.01]
[2]钟宇光,薛开,张家泰.船舶管子加工CAPP系统关键技术的研究[J].应用科技,2005,(05):4.

备注/Memo

备注/Memo:
收稿日期:2016-07-27。
基金项目:国家自然科学基金项目(51379040,51679052).
作者简介:杨金超(1982-),男,工程师;王锡栋(1993-),男,硕士研究生.
通讯作者:王锡栋,E-mail:wangxidong@hrbeu.edu.cn.
更新日期/Last Update: 2017-08-24