Advanced Search
XIE Fei, ZHU Tengfei, YANG Jiquan, YU Shengfu, SHI Jianjun, LIU Yijian. Detection method of molten pool shape based on additional loss function of edge included angle[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2021, 42(7): 82-90. DOI: 10.12073/j.hjxb.20201106001
Citation: XIE Fei, ZHU Tengfei, YANG Jiquan, YU Shengfu, SHI Jianjun, LIU Yijian. Detection method of molten pool shape based on additional loss function of edge included angle[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2021, 42(7): 82-90. DOI: 10.12073/j.hjxb.20201106001

Detection method of molten pool shape based on additional loss function of edge included angle

More Information
  • Received Date: November 05, 2020
  • Available Online: August 30, 2021
  • Aiming at the problems of traditional molten pool detection methods in arc welding additive manufacturing process, such as relying on empirical parameters, low accuracy and long recognition time, a molten pool shape detection method based on additional loss function of edge included angle is proposed to realize rapid and accurate detection and recognition of molten pool. Firstly, the molten pool is represented on multiple scales by integrating multiple features with feature pyramid network, and the dependence on empirical parameters is avoided. Secondly, PointRend neural network module is used to optimize the sampling points based on fine-grained features and coarse prediction mask to reduce the time required for molten pool target detection and recognition. Thirdly, the additional loss function of edge included angle is studied to maximize the classification interval in the angle space, which makes the features extracted by the network more separable and improves the recognition accuracy of model. Finally, tests are carried out using the actual molten pool monitoring data, and the results show that the proposed method has a high recognition accuracy, the accuracy rate is 97.85%. In the presence of molten droplet coverage interference, it can also achieve an accurate detection and recognition performance. Compared with the detection width and measured width of molten pool, the absolute error is less than 0.36 mm. The experimental results have demonstrated that the method is effective and reliable.
  • Zhu K, Yang D, Yu Z, et al. Additive manufacturing of SiO2–Al2O3 refractory products via direct ink writing[J]. Ceramics International, 2020, 46(17): 27254 − 27261. doi: 10.1016/j.ceramint.2020.07.210
    Haleem A, Javaid D M, Vaishya R. 3D printing applications for the treatment of cancer[J]. Clinical Epidemiology and Global Health, 2020, 8(4): 1072 − 1076. doi: 10.1016/j.cegh.2020.03.022
    Yang Z, Liu Q, Wang Y, et al. Fabrication of multi-element alloys by twin wire arc additive manufacturing combined with in-situ alloying[J]. Materials Research Letters, 2020, 8(12): 477 − 482. doi: 10.1080/21663831.2020.1809543
    郭政亚, 熊振华. 金属增材制造缺陷检测技术[J]. 哈尔滨工业大学学报, 2020, 52(5): 49 − 57. doi: 10.11918/201905012

    Guo Zhengya, Xiong Zhenhua. Defect detection technology in metal additive manufacturing[J]. Journal of Harbin Institute of Technology, 2020, 52(5): 49 − 57. doi: 10.11918/201905012
    任永明, 林鑫, 黄卫东. 增材制造Ti-6Al-4V合金组织及疲劳性能研究进展[J]. 稀有金属材料与工程, 2017, 46(10): 3160 − 3168.

    Ren Yongming, Lin Xin, Huang Weidong. Progress in research on microstructure and fatigue properties of Ti-6Al-4V alloy by additive manufacturing[J]. Rare Metal Materials and Engineering, 2017, 46(10): 3160 − 3168.
    Wang Y, Zhang C, Lu J, et al. Weld reinforcement analysis based on long-term prediction of molten pool image in additive manufacturing[J]. IEEE Access, 2020, 99(8): 69908 − 69918.
    Huang Yong, Ren Cao, Ren Qinglong. The element transfer behavior of gas pool coupled activating TIG welding[J]. China Welding, 2018, 27(4): 1 − 9.
    段凯扬, 戈兆文. 焊接工艺评定国际新趋势—焊接经验评定与标准焊接工艺规程[J]. 压力容器, 2020, 37(5): 52 − 57. doi: 10.3969/j.issn.1001-4837.2020.05.009

    Duan Kaiyang, Ge Zhaowen. New international tendency in welding procedure qualification: previous welding experience and standard welding procedure specification[J]. Pressure Vessel Technology, 2020, 37(5): 52 − 57. doi: 10.3969/j.issn.1001-4837.2020.05.009
    方吉米, 王克鸿, 黄勇. 高速GMAW驼峰焊道形成过程熔池图像识别[J]. 焊接学报, 2019, 40(2): 42 − 46.

    Fang Jimi, Wang Kehong, Huang Yong. Weld pool image recognition of humping formation process in high speed GMAW[J]. Transactions of the China Welding Institution, 2019, 40(2): 42 − 46.
    张阳, 吕小青, 徐连勇, 等. 工件倾角对脉冲MAG焊接熔池形态和焊缝尺寸的影响[J]. 焊接学报, 2019, 40(10): 36 − 42.

    Zhang Yang, Lü Xiaoqing, Xu Lianyong, et al. Effect of workpiece inclination on weld pool shape and weld forming in pulsed MAG welding[J]. Transactions of the China Welding Institution, 2019, 40(10): 36 − 42.
    冯宝, 覃科, 蒋志勇. 基于L1/L2极限学习机的熔池熔透状态识别[J]. 焊接学报, 2018, 39(9): 31 − 35.

    Feng Bao, Qin Ke, Jiang Zhiyong. ELM with L1/L2 regularization constraints[J]. Transactions of the China Welding Institution, 2018, 39(9): 31 − 35.
    郑佳美. 基于深度学习的焊缝缺陷检测方法研究[D]. 杭州: 浙江工业大学, 2020.

    Zheng Jiamei. Study on the method of weld defects detection based on deep learning[D]. Hangzhou: Zhejiang University of Technology, 2020.
    李欣. 基于机器视觉的激光3D打印熔池监测技术研究[D]. 哈尔滨: 哈尔滨工业大学, 2020.

    Li Xin. Research on laser 3D printing molten pool monitoring technology based on machine vision[D]. Harbin: Harbin Institute of Technology, 2020.
    Caprio Leonardo, Demir Ali Gökhan, Previtali Barbara. Observing molten pool surface oscillations during keyhole processing in laser powder bed fusion as a novel method to estimate the penetration depth[J]. Additive Manufacturing, 2020, 36(5): 101470.
    Gao Xuesong, Guilherme Abreu Faria, Zhang Wei, et al. Numerical analysis of non-spherical particle effect on molten pool dynamics in laser-powder bed fusion additive manufacturing[J]. Computational Materials Science, 2020, 179(5): 109648.

Catalog

    Article views (512) PDF downloads (57) Cited by()

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return