Weld pool image recognition of humping formation process in high speed GMAW
-
摘要: 针对高速驼峰焊道形成过程中熔池的变化规律，采用CCD视觉传感系统跟踪采集. 提出了一种基于模糊C-均值聚类(fuzzy C-means，FCM)协作主动轮廓(chan-vese，CV)模型的熔池图像分割方法，对高速焊接过程中的熔池图像进行图像分割. 结果表明，驼峰的形成过程中，熔池长度的阶跃变化是反映驼峰形成的主要图像特征. 将熔池长度序列拟合成波形，采用Symlets2号小波进行分解，发现d2级小波分解能更好地识别熔池长度的阶跃变化. 对d2级小波细节能量设定阈值，获取反映熔池长度阶跃变化的尖峰突起特征信号，能很好地识别驼峰缺陷的形成，初步实现了驼峰焊道的监测控制.Abstract: Aiming at the change rule of weld pool during the humping formation process in high speed GTAW, CCD vision system was used to track and collect. A segmentation method based on Fuzzy C-Means collaborative active contour model was proposed to segment the weld pool image. The results show that the step change of the weld length was the main image feature reflecting the humping formation. The weld length sequence was fitted into waveform and decomposed by Symlets2 wavelet. It was found that d2 wavelet decomposition can identify the step change of weld length. Threshold was set on the d2 wavelet to obtain the spike characteristic signal which reflected the step change of the well weld length. The formation of the hump defect can be recognized well and the monitoring and control of the humping bead can be realized preliminarily.
-
Keywords:
- humping bead /
- active contour /
- wavelet transform /
- feature extraction
-
-
[1] 陈 姬, 武传松. 高速GMAW驼峰焊道形成过程的数值分析[J]. 金属学报, 2009, 45(9): 1070 − 1076 [2] Chen Ji, Wu Chuansong. Numerical simulation of forming process of humping bead in high speed GMAW[J]. Acta Metallurgica Sinica, 2009, 45(9): 1070 − 1076
[3] Gratzke U, Kapadia P D, Dowden J. Heat conduction in high-speed laser welding[J]. Journal of Physics D Applied Physics, 1991, 24(12): 2125.
[4] Yang Zhanli, Zhang Shanbao, Yang Yongbo, et al. Study on humping bead formation mechanism in thick-wire high-speed MAG welding[J]. Transactions of the China Welding Institution, 2013, 34(1): 61 − 64
[5] Wu Dongsheng, Hua Xueming, Ye Dingjian, et al. Numerical analysis of humping formation in high speed GMAW process[J]. Transactions of the China Welding Institution, 2016, 37(10): 5 − 8
[6] Nguyen T C, Weckman D C, Johnson D A, et al. The humping phenomenon during high speed gas metal arc welding[J]. Science & Technology of Welding & Joining, 2005, 10(4): 447 − 459.
[7] 杨战利, 张善保, 杨永波, 等. 粗丝高速MAG焊驼峰焊道形成机理分析[J]. 焊接学报, 2013, 34(1): 61 − 64 [8] Gao Fei, Wang Kehong, Liang Yongshun, et al. A multi-scale fractal image segmentation method for arc welding pool[J]. Transactions of the China Welding Institution, 2011, 32(11): 33 − 36
[9] 吴东升, 华学明, 叶定剑, 等. 高速GMAW驼峰形成过程的数值分析[J]. 焊接学报, 2016, 37(10): 5 − 8 [10] Chen Xizhang, Chen Huabin, Chen Shanben, et al. Recognition of welding image based on improved C-V method[J]. Transactions of the China Welding Institution, 2007, 28(9): 9 − 12
[11] Li Jing, Qin Xiaolin, Li Fang, et al. New method based on region coarse localization and chan-vese model for weld pool edge extraction in MAG welding[J]. Chinese Journal of Mechanical Engineering, 2011, 47(12): 74 − 78
[12] 高 飞, 王克鸿, 梁永顺, 等. 一种多尺度分形的弧焊熔池图像分割方法[J]. 焊接学报, 2011, 32(11): 33 − 36 [13] Zhang K, Zhang L, Lam K M, et al. A level set approach to image segmentation with intensity inhomogeneity[J]. IEEE Transactions on Cybernetics, 2016, 46(2): 546 − 557.
[14] Hong Bo, Yuan Can, Pan Jiluan, et al. Wavelet signal processing system about arc sensor[J]. Transactions of the China Welding Institution, 2005, 26(1): 61 − 63.
[15] 陈希章, 陈华斌, 陈善本, 等. 基于改进C-V方法的焊接图像识别[J]. 焊接学报, 2007, 28(9): 9 − 12 [16] 李 静, 秦小麟, 李 芳, 等. 基于区域粗定位与Chan-Vese主动轮廓模型的MAG焊视觉图像熔池边缘提取[J]. 机械工程学报, 2011, 47(12): 74 − 78 [17] Bezdek J C, Dunn J C. Optimal fuzzy partitions: a heuristic for estimating the parameters in a mixture of normal distributions[J]. IEEE Transactions on Computers , 1975, C−24(8): 835 − 838.
[18] 洪 波, 袁 灿, 潘际銮, 等. 电弧传感器小波信号处理系统[J]. 焊接学报, 2005, 26(1): 61 − 63 -
期刊类型引用(0)
其他类型引用(1)
计量
- 文章访问数: 169
- HTML全文浏览量: 4
- PDF下载量: 9
- 被引次数: 1
下载:
