基于机器视觉的热轧中间坯镰刀弯在线检测系统

来源期刊:中南大学学报(自然科学版)2018年第7期

论文作者:徐冬 杨荃 王晓晨 孙友昭 刘克东 代振洋

文章页码:1657 - 1667

关键词:热轧粗轧;镰刀弯;机器视觉;测量系统

Key words:hot rough rolling; camber; machine vision; measurement system

摘    要:为了能够实现对中间坯镰刀弯的非接触在线测量,提出通过基于机器视觉技术的镰刀弯在线测量方案。将面阵CCD相机布置在粗轧机出口倾斜拍摄中间坯表面形状:首先通过亚像素角点定位完成相机标定;再次,通过引入中间坯厚度变量实现对不同厚度的中间坯平面形状由图像坐标向世界坐标转化;最后通过中间坯边缘轮廓连续变化的原理,计算具有重叠区域的连续中间坯图像沿宽度方向的平移量和整体的旋转量,完成中间坯平面图像的拼接。研究结果表明:通过所提出的测量系统及算法可以获得完整的中间坯平面图像及镰刀弯值,通过与工业现场测宽仪的测量结果对比,可知系统测量结果能够反映中间坯弯曲的趋势及细节特征,为热连轧粗轧过程中间坯镰刀弯的控制提供了有效测量手段。

Abstract: To achieve non-contact and on-line measurement of camber in a hot rolling, the design and implementation of an image-based computer vision measurement system was proposed. In order to capture the plane images of intermediate slab, the area-scan charge-coupled device (CCD) camera was installed at the exit of the rough mill. The camber-detection algorithm consists of three parts. Firstly, the camera was calibrated by subpixel corner detection. Secondly, by introducing the thickness variable, the relationship between the physical positions on the intermediate slab and their relative image positions was formulated. Finally, the translation along the width direction and the rotation were calculated using the continuity of the intermediate slab edge shape, and then each frame capture with overlapped regions from the CCD camera was stitched. The results show that the propose camber measurement system and camber-detection algorithm can achieve the overall slab shape and camber values from the obtained image. The equipment and technique are validated through comparison with center-line deviation measured by width gauge. The accuracy of the system reflects that it can reflect the detailed character of the shape of intermediate slab, which provides a potential measurement tool for camber control.

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号