基于机器视觉的条形光学玻璃自动计重切割

发布时间：2018-06-03 17:13

本文选题：机器视觉 + 自动计重切割　；参考：《激光与光电子学进展》2017年07期

【摘要】：基于人工经验对光学玻璃进行的计重切割存在误差较大、效率较低、安全性较差的问题。针对上述问题,利用机器视觉构建了一套针对条形光学玻璃的自动计重切割设备,并结合结构光为该设备设计了一套在线自动计重算法。在计重算法中,高速工业相机采集到光学玻璃的图像后,首先识别玻璃横截面的位置特征,并对轮廓进行拟合,得出当前横截面的面积;然后结合伺服电机对玻璃推进的进给量,对面积进行积分,计算出累计的体积与质量。当累计质量满足切割条件时,对玻璃进行切割。经实验及工厂实际应用证明,该系统具有高精度、高效率以及高安全性等特性,实际切割误差小于0.3g。该装置及算法能够高效、精确地进行条形光学玻璃的自动计重切割。
[Abstract]:On the basis of artificial experience, there are some problems such as large error, low efficiency and poor safety in the cutting of optical glass. Aiming at the above problems, a set of automatic weight measuring and cutting equipment for strip optical glass is constructed by using machine vision, and a set of on-line automatic weight counting algorithm is designed for the device combined with structural light. In the weighing algorithm, the image of optical glass is collected by high speed industrial camera. Firstly, the position characteristics of the cross section of the glass are identified, and the contour is fitted to get the area of the current cross section. Then the area is integrated with the feed of servo motor to the glass, and the accumulative volume and mass are calculated. When the cumulative quality meets the cutting condition, cut the glass. The experiment and practical application in the factory show that the system has the characteristics of high precision, high efficiency and high safety, and the actual cutting error is less than 0.3 g. The device and algorithm can efficiently and accurately cut the strip optical glass automatically.
【作者单位】：河北工业大学电子信息工程学院;北京市安视中电科技有限公司;
【基金】：中国博士后基金(2014M561053) 河北省自然科学基金(F2013202254) 教育部人文社会科学研究规划基金(15YJA630108)
【分类号】：TP391.41;TQ171.734

【相似文献】