锻压技术

航空锻造柔性自动上料机视觉定位系统

英文标题：Visual positioning system of flexible automatic feeder for aviation forging

作者：彭宇升孙勇徐超凌云汉

分类号：TP23;TP31

出版年,卷(期):页码：2021,46(12):174-182

摘要：

航空锻造属于典型的小批量、多品种生产模式，在生产中需要频繁更换不同材质和规格的原料，对自动上料机的柔性要求很高。针对航空锻造中常用的圆棒料，在已有自动上料机的基础上，设计了一种适用于多规格、多材质圆棒料的柔性视觉定位系统。以工业视觉相机和镜头组成的成像系统为主体，搭配外部光源等辅助设备构成定位系统的硬件部分。在此基础上，为了满足各种工况下的上料需求，设计了不同光照条件下的自动曝光算法，研究了适用于不同规格和不同材质的圆棒料的视觉定位算法，实现了在不同光照条件下的棒料精准定位。实验结果表明，该视觉定位系统能够在不同工况下实现对不同材料和规格的圆棒料的快速、准确定位，满足了航空锻造圆棒料自动上料机的柔性化需求。

forging is a typical production mode of small batch and many varieties, and in the production, different materials and specifications of raw materials need to be changed frequently, which requires high flexibility of automatic feeder. Therefore, for the round bar commonly used in aviation forging, based on the existing automatic feeder, a flexible visual positioning system for round bar with multiple specifications and materials was designed, and the hardware of the positioning system was constituted by the imaging system composed of industrial visual camera and lenses, as well as the auxiliary equipment such as an external light source. On this basis, in order to meet the feeding requirements under various working conditions, the automatic exposure algorithm under different lighting conditions was designed, and the visual positioning algorithm suitable for round bar with different specifications and materials was studied to realize the accurate positioning of bar under different lighting conditions. The experimental results show that the vision positioning system can quickly and accurately locate the round bar with different materials and specifications under different working conditions, which meets the flexible requirements of the automatic feeder for round bar in aviation forging.

基金项目：

国家科技重大专项（2018ZX04024-001）

作者简介：彭宇升（1997-），男，硕士研究生 E-mail：bitys@qq.com 通信作者：孙勇 (1971-), 男, 博士, 研究员 E-mail：sun_yong_89@163.com

参考文献：

[1] Hou B, Zhang C P, Yang S B. Computer vision toolsetting system of numerical control machine tool[J]. Sensors, 2020, 20(18): 5302.

[2] 朱云, 凌志刚, 张雨强. 机器视觉技术研究进展及展望[J]. 图学学报, 2020, 41(6): 871-890.

Zhu Y, Ling Z G, Zhang Y Q. Research progress and prospect of machine vision technology[J]. Journal of Graphics, 2020, 41(6): 871-890.

[3] Lins Romulo Gonalves, De Araujo Paulo Ricardo Marques, Corazzim Marcio. Inprocess machine vision monitoring of tool wear for CyberPhysical Production Systems[J]. Robotics and ComputerIntegrated Manufacturing, 2020, 61: 101859.

[4] Ong Pauline, Lee Woon Kiow, Lau Raymond Jit Hoo. Tool condition monitoring in CNC end milling using wavelet neural network based on machine vision[J]. The International Journal of Advanced Manufacturing Technology, 2019, 104(1): 1369-1379.

[5] Hou Q L, Sun J, Huang P L. A novel algorithm for tool wear online inspection based on machine vision[J]. The International Journal of Advanced Manufacturing Technology, 2019, 101(9): 2415-2423.

[6] Galata Dorián László, Mészáros Lilla Alexandra, KállaiSzabó Nikolett, et al. Applications of machine vision in pharmaceutical technology: A review[J]. European Journal of Pharmaceutical Sciences, 2021, 159: 105717.

[7] Zhu L L, Spachos Petros, Pensini Erica, et al. Deep learning and machine vision for food processing: A survey[J]. Current Research in Food Science, 2021, 4: 233-249.

[8] Tripathi Mukesh Kumar, Maktedar Dhananjay D. A role of computer vision in fruits and vegetables among various horticulture products of agriculture fields: A survey[J]. Information Processing in Agriculture, 2020, 7(2): 183-203.

[9] 苗猛. 双目视觉系统在盘类零件上料机器人中的应用研究[D]. 重庆:重庆大学, 2018.

Miao M. Research on the Application of Binocular Vision System in Disc Parts Loading Robot[D]. Chongqing: Chongqing University, 2018.

[10]任勇峰, 王国忠, 储成群, 等. 基于CMOS传感器的高性能图像采集系统设计[J]. 仪表技术与传感器, 2019,(1): 64-67.

Ren Y F, Wang G Z, Chu C Q, et al. Design of high performance image acquisition system based on cmos sensor[J]. Instrument Technique and Sensor, 2019,(1): 64-67.

[11]高润, 牛春晖, 李晓英. 632 nm激光对CCD和CMOS的干扰实验及机理分析[J]. 激光杂志, 2016, 37(9): 5-9.

Gao R, Niu C H, Li X Y. Experiment and mechanism analysis of 632 nm laser jamming CCD and CMOS[J]. Laser Journal, 2016, 37(9): 5-9.

[12]阎文舟. 柔性上料机与视觉辅助抓取系统的开发[D]. 杭州：浙江大学, 2016.

Yan W Z. Developing of FlexFeeder and Picking Up System with Vision Assistant[D]. Hangzhou: Zhejiang University, 2016.

[13]行长印, 毛亚杰, 杨立宏. 基于图像熵的自动曝光设计[J]. 长春理工大学学报:自然科学版, 2009, 32(1): 28-30,10.

Xing C Y, Mao Y J, Yang L H. Design of automatic exposure based on image entropy[J]. Journal of Changchun University of Science and Technology: Natural Science Edition, 2009, 32(1): 28-30,10.

[14]Wu X, Liu X Y, Yuan F. Fast dehazing method for improving the image quality in pellet size measurement[J]. Computers in Industry, 2021, 128: 103438.

[15]赵海士, 路来君, 杨晨. 一种基于图像熵的密度峰值聚类波段选择方法[J]. 吉林大学学报:理学版, 2017, 55(2): 376-378.

Zhao H S, Lu L J, Yang C. A method for density peaks clustering band selection based on image entropy[J]. Journal of Jilin University: Science Edition, 2017, 55(2): 376-378.

[16]刘峰, 霍文甲, 王向军. 嵌入式平台下的两级自适应动态调光方法[J]. 弹箭与制导学报, 2019, 39(2): 83-87,91.

Liu F, Huo W J, Wang X J. Two stage adaptive dynamic dimming method in embedded platform[J]. Journal of Projectiles,Rockets,Missiles and Guidance, 2019, 39(2): 83-87,91.

[17]Zhang Z Y.A flexible new technique for camera calibration[J].IEEE Transactions on Pattern Analysisand Machine Intelligence,2000,22(11):1330-1334.

[18]张墨逸, 张秋余, 段宏湘, 等. 基于运动轨迹的单目相机位姿自标定方法[J]. 华中科技大学学报: 自然科学版, 2019, 47(2): 64-69.

Zhang M Y, Zhang Y Q, Duan H X, et al. Trajectory based monocular camera pose selfcalibration method[J]. Journal of Huazhong University of Science and Technology: Natural Science Edition, 2019, 47(2): 64-69.

[19]李海彦, 徐汀荣, 张立晓, 等. 基于仿射变换的多姿态人脸矫正和识别[J]. 计算机应用研究, 2014,31(4):1215-1219，1228.

Li H Y, Xu T R, Zhang L X, et al. Multipose face correction and recogniton based on affine transformation[J]. Application Research of Computers, 2014,31(4):1215-1219，1228.

[20]周丽莎. 基于模板匹配的视觉定位技术研究与应用[D]. 大连：大连理工大学, 2012.

Zhou L S. Research and Application of Vision Positioning Technology Based on Template Matching[D]. Dalian：Dalian University of Technology, 2012.

[21]李向东. 基于机器视觉的气门组件装配质量在线检测[D]. 广州：华南理工大学, 2013.

Li X D. The Realtime Detection of Valve Components Assembly Quality Based on Machine Vision[D]. Guangzhou: South China University of Technology, 2013.

服务与反馈：

【本网站尚未开通全文下载服务】【加入收藏】