盘型激光焊熔池红外特征支持向量机分类  

Classification of molten pool infrared characteristics based on support vector machine during disk laser welding

作　　者：刘英英[1] 高向东[1] 

机构地区：[1]广东工业大学机电工程学院,广东广州510006

出　　处：《焊接技术》2013年第12期21-24,8,共4页Welding Technology

基　　金：国家自然科学基金(51175095);广东省自然科学基金(10251009001000001;9151009001000020);高等学校博士学科点专项科研基金(20104420110001)资助的课题

摘　　要：在大功率盘型激光焊接过程中,熔池红外热像蕴含着丰富的焊接质量信息。以大功率盘型激光焊接304不锈钢板为试验对象,用近红外高速摄像机获取熔池区域图像。定义并提取熔池宽度、匙孔面积、匙孔周长和匙孔质心为熔池特征参数,以焊缝宽度作为衡量焊接质量的参数,研究支持向量机对熔池红外特征参数进行分类的方法。通过网格搜索和粒子群算法优化支持向量机参数,探索熔池特征与焊接质量之间的关系和规律。试验表明,通过支持向量机对熔池特征参数进行分类可有效判别大功率盘型激光焊缝宽度的变化。During high-power disk laser welding, molten pool infrared radiation contained a great deal of information for reflecting the welding quality. In the high-power disk laser welding of 304 austenitic stainless plate a continue laser power 10 kW, an infrared sensitive high speed video camera was used to capture molten pool dynamic images. Molten pool width, keyhole area, keyhole perimeter and keyhole centroid were defined and extracted as molten pool characteristic parameters. Weld width was used as a parameter to evaluate welding quality. A support vector machine classification model of molten pool characteristic parameters was set up, and the grid search method and particle swarm optimization were used to optimize the experimental parameter c and g. Experimental results showed that the classification of molten pool infrared characteristics based on support vector machine could effectively monitor the changes of weld width during high-power disk laser welding.

关 键 词：大功率盘型激光焊 熔池热像 支持向量机 分类 

分 类 号：TG456.7[金属学及工艺—焊接]