| 摘要: |
| 焊缝成形参数的自动检测技术的开发对焊接质量的提高和自动化生产的实现具有重要意义。文中建立了背面视觉传感焊缝成形参数自动检测系统,通过分析背面焊缝特征,其灰度直方图呈三峰结构,采用迭代法进行二次区域阈值自动的提取,再进行三值化处理,内部噪声点的剔除等图像处理流程,快速准确地分割出熔池和热影响区,并提取出熔池和热影响区的几何尺寸等成形参数。结果表明,该方法可避免强弧光、飞溅、电磁等信号的干扰,能保证焊接的稳定性,从而满足工业生产的需要。 |
| 关键词: 背面视觉 焊缝成形 迭代法 多次区域阈值 图像处理 |
| DOI： |
| 分类号: |
| 基金项目: |
|
| Automatic extraction of weld formation parameters by back CCD visual sensor |
|
ZHANG Huajun1,2, CAI Chunbo1, ZHANG Guangjun2, GAO Hongming2
|
|
1.Material Science and Engineering Institute, Harbin University of Science and Technology, Harbin 150040, China;2.State Key Laboratory of Advanced Welding Production Technology, Harbin Institute of Technology, Harbin 150001, China
|
| Abstract: |
| It is necessary for the improvement of weld quality and the realization of automatic production to detect weld formation parameters automatically.Automatic detective system of weld formation parameters by back CCD visual sensor is developed.The grey histogram of back seam image shows three peaks.The procedure of image process is as follows:twice automatic extractions of region threshold by iteration method, three thresholds processing, and inner noise elimination and so on.The system can detect the dimension parameters of molten and heat effect zone accurately.The experiment shows that this method is to improve the stability of weld production and to meet the demands of industry without the interferences of arc, spatter and electromagnetism, etc. |
| Key words: back visual sensor weld formation iteration method multiple region threshold image process |
