【作者】 刘宇； 王旭东； 杜凤鸣； 孔令伟； 李天衣； 姚曼； 张晓兵；

【Author】 LIU Yu;WANG Xu-dong;DU Feng-ming;KONG Ling-wei;LI Tian-yi;YAO Man;ZHANG Xiaobing;School of Materials Science and Engineering,Dalian University of Technology;Jiangsu Shagang Group;

【机构】 大连理工大学材料科学与工程学院； 江苏沙钢集团；

【摘要】 基于板坯连铸结晶器温度在线监控系统,实现了结晶器温度及其变化速率"热成像",借助阈值分割算法对温度变化的可疑区域进行分割,以此为基础,从异常区域的温度速率、几何以及移动特征等方面提取结晶器黏结的共性特征。结果表明,基于计算机视觉的黏结漏钢预报方法,能够直观呈现异常发生和传播的全部过程及其典型特征,为异常在线诊断和准确预报提供先进手段,对于促进连铸生产的智能化、可视化控制水平具有积极意义。更多还原

【Abstract】 Based on the mould temperature on-line monitoring system for slab continuous casting,mould temperature and its velocity thermographs are realized.The suspicious temperature regions in the thermograph are divided by virtue of threshold segmentation.Then based on it,the common characteristics of sticker breakout are extracted,such as the abnormal zone temperature velocity,geometry and propagation velocity.The research results show that the sticker breakout prediction method based on computer vision can present the classical formation and propagation characteristics of sticker breakout.It also provides an advanced means to detect and predict the abnormity,and has a positive meaning to the intelligent and visual monitoring system for continuous casting production.更多还原