Weld width prediction of weldment bottom surface in high-power disk laser welding

Zi-qin CHEN; Xiang-dong GAO; Lin WANG

doi:10.3788/OPE.20172509.2524

您当前的位置：

首页 >

文章列表页 >

Weld width prediction of weldment bottom surface in high-power disk laser welding

Information Sciences | 更新时间：2020-08-13

- Weld width prediction of weldment bottom surface in high-power disk laser welding
- Optics and Precision Engineering Vol. 25, Issue 9, Pages: 2524-2531(2017)
- 作者机构：
  
  广东工业大学机电工程学院, 广东广州 510006
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20172509.2524
  CLC： TG441.3
- Received：06 March 2017，
  
  Accepted：17 May 2017，
  
  Published：25 September 2017
- 稿件说明：
移动端阅览
Zi-qin CHEN, Xiang-dong GAO, Lin WANG. Weld width prediction of weldment bottom surface in high-power disk laser welding[J]. Optics and precision engineering, 2017, 25(9): 2524-2531.
DOI：

Zi-qin CHEN, Xiang-dong GAO, Lin WANG. Weld width prediction of weldment bottom surface in high-power disk laser welding[J]. Optics and precision engineering, 2017, 25(9): 2524-2531. DOI： 10.3788/OPE.20172509.2524.

摘要

提出了通过视觉传感获取焊接过程中的焊接特征信息并利用神经网络模型预测焊缝背面宽度的方法。利用大功率盘形激光器焊接了低碳钢SS400焊件，在焊接过程中改变焊接功率、焊接速度和焊接路径，并利用两台高速摄像机同步获取焊件正面和侧面出现的焊接特征信息。对获取的图像进行色彩空间转换、分层、滤波去噪和空域图像处理，提取飞溅、熔池和金属蒸气等焊接特征信息，观察焊接路径对各个特征的影响。最后，建立了一个三层的LMBP（Levenberg-Marquardt Back Propagation）神经网络模型，将提取的特征信息作为输入量，预测焊缝的背面宽度。结果显示：当熔透不稳定或出现未熔透状态时，LMBP神经网络拟合度大于0.83，最大训练误差均值为0.0028 mm，最大实际误差均值为0.2256 mm。试验结果表明所建立的预测模型具有良好的准确性和稳定性。

Abstract

A method was proposed to obtain characteristic information in a welding process by visual sensing and to predict the weld width of weldment bottom surface by using a neural network model. A workpiece made from mild steel SS400 was welded by a high power disk laser. In welding processing

the weld conditions were changed

including laser welding power

welding speed and welding route and two high speed cameras were used to capture images containing characteristic information on both top surface and side surface of weldment simultaneously. In order to get a better characteristics extraction

the colour space of a RGB image was changed into NTSC (National Television Standards Committee) colour space

then both RGB image and YIQ image were separated into their colour components

filtered to denoising and processed in space domain. The weld characteristic information was extracted

including spatter

weld pool and metal vapour and the effect of weld route on characteristic information was researched. Finally

a LMBP (Levenberg-Marquardt Back Propagation) neural network model including three layers and one hidden layer was established. The obtained characteristic information was taken as input

and the weld width of weldment bottom surface was predicted. The results show that when the welding penetration is unstable or lack of penetration

the fitting degree of LMBP neural network is greater than 0.83

the maximum training error mean is 0.002 8 mm

and maximum actual error mean is 0.225 6 mm. It concludes that the prediction model has good accuracy and stability.

关键词

Keywords

references

KATAYAMA S, KAWAHITO Y, MIZUTANI M. Elucidation of laser welding phenomena and factors affecting weld penetration and welding defects [J]. Physics Procedia, 2010, 5:9-17.

YOU D Y, GAO X D, KATAYAMA S. Multiple-optics sensing of high-brightness disk laser welding process [J]. NDT & E International, 2013, 60: 32-39.

高向东, 李竹曼, 游德勇, 等.激光焊匙孔特征的近红外与X射线传感分析[J].光学精密工程, 2016, 24(10):2400-2407.

GAO X D, LI ZH M, YOU D Y, et al.. Analysis of laser welding keyhole characteristics based on near-infrared high speed camera and X-ray sensing [J]. Opt. Precision Eng., 2016, 24(10):2400-2407. (in Chinese)

KIM J, KI H. Scaling law for penetration depth in laser welding [J]. Journal of Materials Processing Technology, 2014, 214(12):2908-2914.

ZOU J L, WU S K, YANG W X, et al.. A novel method for observing the micro-morphology of keyhole wall during high-power fiber laser welding [J]. Materials & Design, 2016, 89:785-790.

LI S C, CHEN G Y, ZHOU C. Effects of welding parameters on weld geometry during high-power laser welding of thick plate [J]. The International Journal of Advanced Manufacturing Technology, 2015, 79(1-4):177-182.

LI S C, CHEN G Y, KATAYAMA S, et al.. Relationship between spatter formation and dynamic molten pool during high-power deep-penetration laser welding [J]. Applied Surface Science, 2014, 303:481-488.

ZHANG Y X, GAO X D. Analysis of characteristics of molten pool using cast shadow during high-power disk laser welding [J]. The International Journal of Advanced Manufacturing Technology, 2014, 70(9-12):1979-1988.

MIRAPEIX J, COBO A, CONDE O M, et al.. Real-time arc welding defect detection technique by means of plasma spectrum optical analysis [J]. NDT & E International, 2006, 39(5):356-360.

HAO K D, LI G, GAO M, et al.. Weld formation mechanism of fiber laser oscillating welding of austenitic stainless steel [J]. Journal of Materials Processing Technology, 2015, 225:77-83.

MUNGLE T, TEWARY S, ARUN I, et al.. Automated characterization and counting of Ki-67 protein for breast cancer prognosis:A quantitative immunohistochemistry approach [J]. Computer Methods and Programs in Biomedicine, 2017, 139:149-161.

Views

352

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Full-stokes photodetector based on neural networks

Research of 3D reconstruction and position estimation of 3D pieces based on binocular structured light peripheral scanning

Design of partial overlap point cloud registration network driven by overlap score and matching matrix

A method for underwater vehicle attitude measurement based on Snell’s window and its polarization mode

Detection of conductive multi-particles based on circular convolutional neural network

Related Author

WANG Shoutong

ZHANG Ran

CHU Jinkui

MENG Hailong

CAI Dehao

CHENG Yao

WU Zhetao

SHI Xiaoyi

Related Institution

Liaoning Provincial Key Laboratory of Micro Nanosystems， Dalian University of Technology

Ningbo Research Institute， Dalian University of Technology

College of Mechanical Engineering， Chongqing University of Technology

School of Information Engineering， Jiangxi University of Science and Technology

Jiangxi Province Key Laboratory of Multidimensional Intelligent Perception and Control

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰