CO<sub>2</sub>气体保护焊的焊缝形貌建模及虚拟化仿真系统开发

肖罡; 欧敏; 李时春; 万可谦; 周妃四; 杨钦文

doi:10.11973/jxgccl202311012

CO₂气体保护焊的焊缝形貌建模及虚拟化仿真系统开发

肖罡^1,2,3,
欧敏²,
李时春^2,,
万可谦¹,
周妃四²,
杨钦文³

1. 江西科骏实业有限公司, 南昌 330100;
2. 湖南科技大学, 难加工材料高效精密加工湖南省重点试验室, 湘潭 411201;
3. 湖南大学机械与运载工程学院, 长沙 410082

基金项目:

国家自然科学基金资助项目（52075159）；江西省自然科学基金资助项目（20224ACB218002）；江西省高层次高技能领军人才培养工程资助项目；湖南省自然科学基金资助项目（2022JJ30019）；湖南省教育厅科学研究项目（21A0301）；广西大学省部共建特色金属材料与组合结构全寿命安全国家重点实验室开放基金资助项目（2022GXYSOF24）

详细信息

作者简介:
肖罡(1983-),男,江西九江人,教授,博士

通讯作者:
李时春副教授

中图分类号: TG409
计量
- 文章访问数: 2
- HTML全文浏览量: 0
- PDF下载量: 2
出版历程
- 收稿日期: 2022-10-19
- 修回日期: 2023-09-07
- 刊出日期: 2023-11-19

Modeling and Virtual Simulation System Development of Weld Morphology in CO₂ Gas Shielded Welding

1. Jiangxi KMAX Industrial Co., Ltd., Nanchang 330100, China;
2. Hunan Provincial Key Laboratory for Efficient PrecisionMachining of Difficult to Machine Materials, Hunan University of Science and Technology, Xiangtan 411201, China;
3. College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082, China

摘要

摘要: 建立了CO₂气体保护焊工艺参数与焊缝几何尺寸（熔宽、熔深）之间的多层感知机神经网络预测模型，并基于焊接试验数据训练模型，确定了模型的数学解析式；通过分析焊缝截面和表面形貌特征，建立焊缝形貌的虚拟化仿真模型；通过python编程开发了焊缝形貌预测与虚拟化仿真系统。结果表明：所建立的多层感知机神经网络预测模型对熔宽预测的最大偏差为0.097 mm，模型拟合优度为0.999 269，对熔深预测的最大偏差为0.051 mm，模型拟合优度为0.999 567；建立了以焊缝熔深和熔宽为输入变量的焊缝截面形貌数学模型和以焊缝熔宽为输入变量的表面形貌数学模型。
- CO₂气体保护焊 /
- 多层感知机神经网络模型 /
- 焊缝形貌建模 /
- 虚拟化仿真系统
Abstract: A multi-layer perceptron neural network prediction model between the process parameters of CO₂ gas shielded welding and the weld geometry (melting width and depth) was established, and the mathematical analytic formula of the model was determined based on the welding test data training the model. The virtual simulation model of weld morphology was established by analyzing the characteristics of weld section and surface morphology. The weld morphology prediction and virtualization simulation system was developed by python programming. The results show that the maximum deviation for predicting melting width with the established multi-layer perceptron neural network prediction model was 0.097 mm with a model fitting coefficient of 0.999 269, and that for predicting melting depth was 0.051 mm with a model fitting coefficient of 0.999 567. The mathematical model of weld section morphology with melting depth and melting width as input variables and the mathematical model of surface morphology with melting width as input variables were established.
- CO₂ gas shielded welding /
- multi-layer perceptron neural network model /
- weld morphology modeling /
- virtual simulation system

HTML全文

参考文献(18)

[1]	程雨潇,朱玉斌,刘崇尧,等.焊接虚拟仿真技术应用分析[J].南方农机,2022,53(13):140-142. CHENG Y X,ZHU Y B,LIU C Y,et al.Application analysis of welding virtual simulation technology[J].China Southern Agricultural Machinery,2022,53(13):140-142.
[2]	张怡青,杨莉,谢胜利,等.虚拟仿真技术在焊接实训中的应用[J].科技与创新,2022(10):166-169. ZHANG Y Q,YANG L,XIE S L,et al.Application of virtual simulation technology in welding practice[J].Science and Technology & Innovation,2022(10):166-169.
[3]	谢本凯,张笑笑,蔡水涌,等.虚拟焊接训练技术研究进展[J].焊接,2022(5):43-51. XIE B K,ZHANG X X,CAI S Y,et al.Research progress on virtual welding training technology[J].Welding & Joining,2022(5):43-51.
[4]	刘红先.CO₂气体保护焊焊接工艺参数分析[J].科技传播,2014,6(19):120-121. LIU H X.Analysis of welding process parameters of CO₂ gas shielded welding[J].Public Communication of Science & Technology,2014,6(19):120-121.
[5]	赵维艳,张敏,崔志峰.焊接工艺参数对CO₂气体保护焊焊接质量的影响[J].焊接技术,2013,42(9):74-75. ZHAO W Y,ZHANG M,CUI Z F.Influence of welding process parameters on welding quality of CO₂ gas shielded welding[J].Welding Technology,2013,42(9):74-75.
[6]	王泽荫.工业机器人CO₂气体保护焊焊接工艺研究[J].世界有色金属,2021(2):139-140. WANG Z Y.Study on welding technology of industrial robot CO₂ gas shielded welding[J].World Nonferrous Metals,2021(2):139-140.
[7]	葛佳棋,万升云,汤旭祥,等.GMAW自动焊工艺参数对焊缝成形影响研究[J].金属加工(热加工),2022(6):45-48. GE J Q,WAN S Y,TANG X X,et al.Study on the influence of GMAW automatic welding process parameters on weld formation[J].MW Metal Forming,2022(6):45-48.
[8]	韩力,王天琪,龙斌,等.V型坡口多层多道焊焊道几何参数预测[J/OL].材料科学与工艺. [2022-09-14]. https://kns.cnki.net/kcms2/article/abstract?v=ncFPfL1MdGblT4_LTjYmT9rOCit14RiXm127LjdasxJZYEFOqUnyFN9GQO0Lk485SGF3Bj78VU3Zc3vC009sN-o5W7rLZ01CIAfsM1IyzL7k7pedpLOX0w==&uniplatform=NZKPT" target="_blank"> https://kns.cnki.net/kcms2/article/abstract?v=ncFPfL1MdGblT4_LTjYmT9rOCit14RiXm127LjdasxJZYEFOqUnyFN9GQO0Lk485SGF3Bj78VU3Zc3vC009sN-o5W7rLZ01CIAfsM1IyzL7k7pedpLOX0w==&uniplatform=NZKPT HAN L,WANG T Q,LONG B,et al. Geometric parameter prediction of multi-layer multi-pass welding bead for V-groove[J/OL].Materials Science and Technology. [2022-09-14]. https://kns.cnki.net/kcms2/article/abstract?v=ncFPfL1MdGblT4_LTjYmT9rOCit14RiXm127LjdasxJZYEFOqUnyFN9GQO0Lk485SGF3Bj78VU3Zc3vC009sN-o5W7rLZ01CIAfsM1IyzL7k7pedpLOX0w==&uniplat form=NZKPT
[9]	李建,左跃群.药芯焊丝CO₂气体保护焊打底层操作技巧分析[J].科技资讯,2020,18(10):38-39. LI J,ZUO Y Q.Analysis on the operation skill of the bottom layer in CO₂ gas shielded welding of flux-cored wire[J].Science & Technology Information,2020,18(10):38-39.
[10]	张圆圆,冯志强,陈海峰,等.一种模糊推理的CO₂焊接质量预测方法[J].武汉理工大学学报,2021,43(3):73-78. ZHANG Y Y,FENG Z Q,CHEN H F,et al.A fuzzy reasoning method for predicting CO₂ welding quality[J].Journal of Wuhan University of Technology,2021,43(3):73-78.
[11]	林惠乐.基于遗传神经网络的CO₂弧焊机器人工艺参数优化研究[D].南宁:广西大学,2015. LIN H L.Optimization of process parameters of CO₂ arc welding robot based on genetic neural network[D].Nanning:Guangxi University,2015.
[12]	覃科,刘晓刚,丁立新.基于卷积神经网络的CO₂焊接熔池图像状态识别方法[J].焊接,2017(6):21-26. QIN K,LIU X G,DING L X.Recognition of molten pool morphology in CO₂ welding based on convolution neural network[J].Welding & Joining,2017(6):21-26.
[13]	张立斌.CO₂自动焊工艺参数模型建立[J].广东石油化工学院学报,2015,25(6):54-58. ZHANG L B.The model building of CO₂ automatic welding process parameters[J].Journal of Guangdong University of Petrochemical Technology,2015,25(6):54-58.
[14]	VENKATA RAO K,PARIMI S,SUVARNA RAJU L,et al.Modelling and optimization of weld bead geometry in robotic gas metal arc-based additive manufacturing using machine learning,finite-element modelling and graph theory and matrix approach[J].Soft Computing,2022,26(7):3385-3399.
[15]	SHIN S,JIN C N,YU J,et al.Real-time detection of weld defects for automated welding process base on deep neural network[J].Metals,2020,10(3):389.
[16]	吴月玉,张弓,林群煦,等.机器人TIG焊接的焊缝形貌遗传神经网络预测[J].制造业自动化,2022,44(7):86-90. WU Y Y,ZHANG G,LIN Q X,et al.Genetic neural network prediction of weld morphology in robot TIG welding[J].Manufacturing Automation,2022,44(7):86-90.
[17]	LI R,DONG M S,GAO H M.Prediction of bead geometry with changing welding speed using artificial neural network[J].Materials,2021,14(6):1494.
[18]	刘理想.电弧增材制造堆积形貌研究及堆积过程数字孪生模拟[D].衡阳:南华大学,2020. LIU L X.Study on accumulation morphology and digital twin simulation of accumulation process in arc additive manufacturing[D].Hengyang:University of South China,2020.