In high-power laser welding process, it is hard to detect weld penetration conditions and back of weld shape directly. The width of back of weld was predicted by the sensing characteristics information of weld face and side surface. Visual sensors are used to capture images which contain weld characteristics information in laser welding process. Weld characteristics are extracted accurately through image segmentation, image hierarchical, pattern recognition and space image process. The extracted characteristics variation trends are corresponding to weld route change obviously. Bayes neural network that contains two hidden layers is established for back of weld width prediction of weldment, and the characteristics extracted from images are used as inputs. The compare results between prediction value and real value verified that the established Bayes neural network has good predictive ability, and better predictive stability even the weld is not ideal.
CHEN Ziqin
,
GAO Xiangdong
,
WANG Yu
,
YOU Deyong
. Weldment back of weld width prediction based on neural network during high-power laser welding[J]. Transactions of The China Welding Institution, 2018
, 39(11)
: 48
-52
.
DOI: 10.12073/j.hjxb.2018390271
[1] Yang L, Ume I C. Measurement of weld penetration depths in thin structures using transmission coefficients of laser-generated Lamb waves and neural network[J]. Ultrasonics, 2017, 78:96-109.
[2] Ola O T, Doern F E. Factors controlling keyhole-induced porosity in cold wire laser welded aluminum[J]. Journal of Laser Applications, 2017, 29(1):012008-1-8.
[3] 赵琳, 塚本进, 荒金吾郎, 等. 10 kW光纤激光焊接缺陷的形成[J]. 焊接学报, 2015, 36(7):55-58 Zhao Lin, Tsukamoto S, Arakane G, et al. Formation of defects in 10 kW fiber laser welding[J]. Transactions of the China Welding Institution, 2015, 36(7):55-58
[4] Li S, Chen G, Zhou C. Effects of welding parameters on weld geometry during high-power laser welding of thick plate[J]. International Journal of Advanced Manufacturing Technology, 2015, 79(1-4):177-182.
[5] Li S, Chen G, 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(6):481-488.
[6] Zhang Y, Gao X. Analysis of characteristics of molten pool using cast shadow during high-power disk laser welding[J]. International Journal of Advanced Manufacturing Technology, 2014, 70(9-12):1979-1988.
[7] Pang S Y, Chena X, Zhou J X, et al. 3D transient multiphase model for keyhole, vapor plume, and weld pool dynamics in laser welding including the ambient pressure effect[J]. Optics and Lasers in Engineering, 2015, 74:47-58.
[8] 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.
[9] 高向东, 张勇, 游德勇, 等. 大功率光纤激光焊熔池形态及焊接稳定性分析[J]. 焊接学报, 2011, 32(9):13-16 Gao Xiangdong, Zhang Yong, You Deyong, et al. Analysis of molten pool configuration and welding stability during high-power fiber laser welding[J]. Transactions of the China Welding Institution, 2011, 32(9):13-16
[10] Pan Q, Mizutani M, Kawahito Y, et al. High power disk laser-metal active gas arc hybrid welding of thick high tensile strength steel plates[J]. Journal of Laser Applications, 2016, 28(1):012004.
