双旁路耦合电弧GMAW熔池图像边缘提取算法  

Edge Extraction Algorithm for Dual Bypass GMAW Weld Pool

作　　者：薛诚[1] 石玗[2] 樊丁[2] 李卫东[1] 

机构地区：[1]兰州理工大学有色金属合金及加工教育部重点实验室,兰州730050 [2]兰州理工大学甘肃省有色金属新材料省部共建国家重点实验室,兰州730050

出　　处：《上海交通大学学报》2010年第S1期4-7,共4页Journal of Shanghai Jiaotong University

基　　金：国家自然科学基金资助项目(50805073);兰州理工大学优秀青年教师培养计划资助项目(Q200901);教育部科学技术研究重点资助项目(210229)

摘　　要：为了研究在双旁路耦合电弧气体保护电弧焊(DB-GMAW)方法下的铝合金焊接过程,通过被动视觉检测系统对焊接过程中的熔池图像进行了采集.介绍了该焊接方法的原理和系统组成,对所得焊接熔池图像进行了Roberts、Sobel、Prewitt、LOG、Canny、ZeroCross 6种微分算子的边缘提取和结果对比.结果表明:由于旁路电弧的分流作用使得通过母材的电流大幅减小,显著降低了熔池区电弧的亮度,从而降低了熔池图像采集和处理的难度;比较6种微分算子对熔池图像边缘提取的结果,Canny算子可以得到连续性、完整性和准确性均符合控制要求的熔池边缘结果,为实现该种焊接方法的过程控制奠定了基础.In order to study the process of aluminum alloy dual bypass gas metal arc welding(DB-GMAW),a series of weld pool images were acquired by a passive vision system.The principle and every part of its system were introduced.And differential operators,such as Roberts,Sobel,Prewitt,LOG,Canny and Zerocross,were used to extract the edge of weld pool from acquired images.The results show that the base metal current is decreased greatly because of the bypass arc,and the brightness of arc above the weld pool is decreased too.That makes getting and processing the weld pool images easier.In the six edge extraction results of differential operators,the Canny operator can get a continuous,whole and exact edge.This will be useful for DB-GMAW process control.

关 键 词：双旁路耦合电弧GMAW 焊接熔池 边缘提取算法 微分算子 

分 类 号：TG444[金属学及工艺—焊接]