基于机器视觉的条形光学玻璃自动计重切割  被引量:2

Automatic Weighing and Cutting Method of Strip Optical Glass Based on Machine Vision

在线阅读下载全文

作  者:何峰[1] 周亚同[1] 赵翔宇[1] 王帅 张忠伟 

机构地区:[1]河北工业大学电子信息工程学院,天津300401 [2]北京市安视中电科技有限公司,北京100871

出  处:《激光与光电子学进展》2017年第7期249-257,共9页Laser & Optoelectronics Progress

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)

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。There are many problems of using weighing and cutting method for optical glass based on artificial experience, such as large errors, low efficiency and poor security. In order to solve the above problems, an automatic weighing and cutting equipment for strip optical glass is built based on machine vision, and an automatic weighing algorithm is designed for the equipment combined with structured light. The position feature of the glass cross section is identified after the optical glass image is collected by the high speed industrial camera. The cross sectional area is calculated by using the location information. Then the area is integrated with the help of the glass propulsion feed of the servo motor. And the cumulative volume and the mass size are calculated. When the cutting conditions are satisfied, the glass will be cut. Experimental results 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. Therefore, The automatic weighing and cutting method can cut the strip optical glass efficiently and accurately.

关 键 词:机器视觉 自动计重切割 高速工业相机 光学玻璃 

分 类 号:TP391.4[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象