Spatter analysis of rotating arc image based on multi threshold and neural network
-
摘要: 为探究旋转电弧飞溅产生原因及规律，针对高速相机采集的旋转电弧平堆焊的焊接图像，提出了一种基于掩膜的多阈值与BP(back propagation)神经网络组合方法识别焊接飞溅．多阈值法获取飞溅位置及其轮廓，再通过建立5特征值的BP神经网络模型识别飞溅．结果表明，对于具有灰度分布范围大、背景复杂的旋转电弧飞溅图像，该组合方法的识别准确率可达95.76%．同时，通过飞溅与焊丝位置的相位分析，飞溅最大数量相位均值为241.4°，即焊丝末端进入熔池后约0.14周期位置，主要是由焊丝末端熔滴与熔池接触导致电流激增，电流抑制不充分造成，该研究结果为旋转电弧焊接飞溅控制提供了依据．Abstract: To exploring the causes and rules of rotary arc spatter, a combination method of multi threshold and BP neural network based on mask was proposed to identify welding spatter in accordance with the welding images of rotary arc flat surfacing collected by high-speed camera. The multi threshold method was used to obtain the spatter position and contour, and then the spatter was identified by establishing a BP neural network model with five characteristic values The recognition accuracy of this combined method can reach 95.76% for rotating arc spatter images with complex background. At the same time, through the phase analysis of spatter and welding wire position, the average phase of the maximum number of spatters is 241.4°, that is, about 0.14 cycle position after the end of welding wire enters the molten pool. This is mainly due to the current surge caused by the contact between the droplet at the end of welding wire and the molten pool, and the insufficient current suppression, The research results provide a basis for controlling spatter in rotating arc welding.
-
Keywords:
- rotating arc /
- welding spatter /
- multi threshold processing /
- BP neural network /
- image processing
-
-
![]()
图 5 焊接图像预处理
Figure 5. Welding image preprocessing. (a) original image enhancement processing results; (b) median and Gaussian filtering results
![]()
图 6 多阈值处理结果
Figure 6. Multi-threshold processing results. (a) processing results; (b) segmentation result
![]()
图 7 掩膜处理
Figure 7. Mask processing. (a) arc and molten pool mask; (b) mask and open operation results
![]()
图 8 飞溅分割和标记图
Figure 8. Segmentation and mark sheet of spatter. (a) segmentation; (b) mark sheet
![]()
![]()
图 14 飞溅数量、焊接电流与极值相位统计
Figure 14. Statistics of the number of spatter, welding current and extreme value phase
表 1 焊接工艺参数
Table 1 Welding process parameters
焊接电流
I/A电弧电压
U/V保护气体 气体流量
Q/(L·min−1)焊丝直径
d/mm焊丝伸出长度
l/mm焊接速度
v/(mm·s−1)旋转频率
f/Hz180 24 20%CO2 + 80%Ar 12 1.2 15 5 20 
下载: 导出CSV
-
[1] You D, Gao X, Katayama S. Monitoring of high-power laser welding using high-speed photographing and image processing[J]. Mechanical Systems and Signal Processing, 2014, 49(1/2): 39 − 52.
[2] 刘西洋, 徐锴, 杨淼森, 等. 基于表面张力的氧化物组分及含量对焊接飞溅的影响[J]. 焊接, 2020(8): 22 − 25. Liu Xiyang, Xu Kai, Yang Miaosen, et al. Effect of component and content of oxide based on surface tension on welding spatter[J]. Welding & Joining, 2020(8): 22 − 25.
[3] 张恒铭, 石玗, 李春凯, 等. 极性对细直径自保护药芯焊丝CMT下熔滴过渡及焊缝成形的影响[J]. 焊接学报, 2021, 42(8): 75 − 81. doi: 10.12073/j.hjxb.20210419001 Zhang Hengming, Shi Yu, Li Chunkai, et al. Effect of polarity on droplet transfer and weld formation of fine diameter self shielded flux cored wire under CMT[J]. Transactions of the China Welding Institution, 2021, 42(8): 75 − 81. doi: 10.12073/j.hjxb.20210419001
[4] Lü Xiaoqing, Cao Biao, Zeng Min, et al. Effects of current waveform parameters during droplet transfer on spatter in high speed waveform controlled Short-circuiting GMAW[J]. China Welding, 2005, 14(2): 121 − 124.
[5] Kang S, Kang M, Jang Y H, et al. Droplet transfer and spatter generation in DC-AC pulse tandem gas metal arc welding[J]. Science and Technology of Welding and Joining, 2020, 25(7): 589 − 599. doi: 10.1080/13621718.2020.1786262
[6] 孔海旺, 李科, 王金波, 等. CO2气体保护焊熔滴过渡与飞溅的研究[J]. 热加工工艺, 2017, 46(11): 235 − 237. Kong Haiwang, Li Ke, Wang Jinbo, et al. Study on droplet transfer and spatter in CO2 gas shielded arc welding[J]. Hot Working Technology, 2017, 46(11): 235 − 237.
[7] Shareef I, Martin C. Effect of process parameters on weld spatter in robotic welding[C]//Procedia Manufacturing. 48th SME North American Manufacturing Research Conference. Cincinnati, Ohio, USA, 2020, 48: 358 − 371.
[8] Haubold M W, Zäh M F. Real-time spatter detection in laser welding with beam oscillation[C]//Procedia CIRP. 12th CIRP Conference on Intelligent Computation in Manufacturing Engineering. Gulf of Naples, Italy, 2019, 79: 159 − 164.
[9] Yang D, Li H, Liu S, et al. In situ capture of spatter signature of SLM process using maximum entropy double threshold image processing method based on genetic algorithm[J]. Optics & Laser Technology, 2020, 131(6): 106371.
[10] Huang Y, Hua X, Li F, et al. Spatter feature analysis in laser welding based on motion tracking method[J]. Journal of Manufacturing Processes, 2020, 55(4): 220 − 229.
[11] Tan Z, Fang Q, Li H, et al. Neural network based image segmentation for spatter extraction during laser-based powder bed fusion processing[J]. Optics & Laser Technology, 2020, 130(3): 106347.
[12] Xia X, Jiang Z, Xu P. A detection algorithm of spatter on welding plate surface based on machine vision[J]. Optoelectronics Letters, 2019, 15(1): 52 − 56. doi: 10.1007/s11801-019-8104-7
[13] Zhao Z, Deng L, Bai L, et al. Optimal imaging band selection mechanism of weld pool vision based on spectrum analysis[J]. Optics & Laser Technology, 2019, 110(9): 145 − 151.
[14] 陈明. MATLAB神经网络原理与实例精解[M]. 北京: 清华大学出版社, 2013. Chen Ming. The principle of MATLAB neural network and the detailed explanation of examples[M]. Beijing: Tsinghua University Press, 2013.
-
期刊类型引用(13)
1. 何阳阳，吴新伟，汪超. 10Cr9MoW2VNbBN的焊接工艺研究. 机械制造文摘(焊接分册). 2024(06): 13-16 . 
百度学术
2. 路学成，韩玉茹，张志强，白玉洁，张天刚，郭志永. 添加N_2保护对CMT-P复合电弧焊接头组织与性能的影响. 焊接学报. 2023(04): 63-70+133 . 本站查看
3. 雷小伟，余巍，符成学. TA5钛合金CMT+P混合过渡焊接工艺研究. 热加工工艺. 2023(09): 51-55 . 百度学术
4. 徐连勇，王成，杨连河，赵雷，荆洪阳，韩永典. P110套管内壁CMT/P堆焊Inconel 625合金的组织及性能研究. 机械工程学报. 2023(14): 159-168 . 百度学术
5. 王宇冬，尚建路，孙斌，杨佳，王妍. 不同焊接工艺对P92钢焊接接头组织性能的影响. 钢铁研究学报. 2023(09): 1152-1160 . 百度学术
6. 张志强，李涵茜，贺世伟，路学成，王浩，张天刚. 激光与CMT-P电弧复合增材构件的微观组织特征研究. 材料保护. 2023(10): 74-82 . 百度学术
7. 殷亚运，雷小伟，崔永杰，杜志博，付占波，鄂楠. 基于CMT技术的薄壁不锈钢框架焊接工艺研究. 热加工工艺. 2022(03): 127-130 . 百度学术
8. 徐连勇，白玉洁，韩永典，荆洪阳，张志强. 双相不锈钢CMT-P复合焊接微区组织特征. 焊接学报. 2022(03): 1-6+113 . 本站查看
9. 张忠科，刘旭峰，李昭，雄健强. P92钢等离子弧焊接接头原位拉伸的SEM观察研究. 材料导报. 2021(24): 24128-24133 . 百度学术
10. 万夫伟，郭新芳，马志宝，张汝潺，周海涛. G115大壁厚管道GTAW+TIP TIG焊接工艺. 焊接技术. 2021(12): 71-74 . 百度学术
11. 卜凡辉，徐连勇，荆洪阳，庞红宁，韩永典，赵雷. Influence of the repair length on the residual stress in P92 steel repair welds. China Welding. 2020(02): 17-22 . 百度学术
12. 徐连勇，庞红宁，赵雷，韩永典，迟大钊. G115钢CMT+P焊接工艺及组织和性能. 焊接学报. 2020(08): 1-5+97 . 本站查看
13. 卜凡辉，徐连勇，韩永典，赵雷. 补焊长度对P92补焊残余应力的影响. 焊接学报. 2019(09): 19-24+161-162 . 本站查看
其他类型引用(7)
计量
- 文章访问数: 306
- HTML全文浏览量: 81
- PDF下载量: 72
- 被引次数: 20
