长条状细薄带钩零件变形自动检测系统

doi:10.13475/j.fzxb.20200306006

纺织学报 ›› 2020, Vol. 41 ›› Issue (10): 158-163.doi: 10.13475/j.fzxb.20200306006

长条状细薄带钩零件变形自动检测系统

朱世根¹^,²(), 杨宏贤¹^,², 白云峰¹^,², 丁浩¹^,², 朱巧莲³

1.东华大学机械工程学院, 上海 201620
2.东华大学纺织装备教育部工程研究中心, 上海 201620
3.义乌云溪新材料科技有限公司, 浙江义乌 322000

收稿日期:2020-03-23 修回日期:2020-07-08 出版日期:2020-10-15 发布日期:2020-10-27
作者简介:朱世根(1963—),男,教授,博士。主要研究方向为成型制造与强化。E-mail:sgzhu@dhu.edu.cn。
基金资助:
中央高校改善基本办学条件专项资助(14X15)

Investigation on automatic deformation inspection system of long and thin parts with hooks

ZHU Shigen¹^,²(), YANG Hongxian¹^,², BAI Yunfeng¹^,², DING Hao¹^,², ZHU Qiaolian³

1. College of Mechanical Engineering, Donghua University, Shanghai 201620, China
2. Engineering Research Center of Advanced Textile Machinery, Ministry of Education, Donghua University, Shanghai 201620, China
3. Yiwu Yunxi New Material Technology Company, Yiwu, Zhejiang 322000,China

Received:2020-03-23 Revised:2020-07-08 Online:2020-10-15 Published:2020-10-27

摘要/Abstract

摘要：

现有的机器视觉变形自动检测系统主要局限于小尺寸精密零件或大尺寸非精密零件的检测,而对于一些大尺寸、高精密的大批量检测对象,在实际生产中主要依靠人工分拣,难以同时保证变形检测的高精准度与高效率。针对此问题,设计研发了一种基于视觉的变形自动检测方法和系统。通过设计模块化的高速检测硬件系统,利用虚实像联合检测方法量化变形检测指标;利用LabVIEW及IMAQ Vision视觉工具包作为开发环境,根据零件形状特点,设计了基于缝隙值的分区检测算法,避免直接检测整体变形的误差;在此基础上,针对针钩形态,确定最优化的检测方案;针对零件位姿偏差问题,使用基于多基准的改进定位策略。结果表明:该系统可避免弯钩的误检,提高针钩尺寸测量精度和检测结果可重复性,重复检出率可达91%~96%。最后,将机检零件与标准零件进行比较,机检零件一致性完全可满足装机使用需求。

关键词: 机器视觉, 变形检测, 虚拟仪器, LabVIEW, 织针, 零件变形测量算法

Abstract:

The existing machine vision automatic deformation inspection system is mainly limited to the detection of small size precision parts or large size non precision parts. For some large-scale, high-precision and large-quantity inspection objects, manual sorting is mainly used in actual production. It is difficult to guarantee high accuracy and efficiency at the same time. Therefore, an automatic deformation inspection method and system based on vision was proposed. First of all, a modular high-speed detection hardware system was designed, and the detection index was quantified by the virtual real image joint detection method. Secondly, using LabVIEW and IMAQ vision visual toolkit as the development environment, according to the shape characteristics of the parts, a partition detection algorithm based on the gap value was designed to avoid various errors of direct detection of the overall deformation. On this basis, the optimal detection scheme was determined according to the shape of the needle hook, and the improved positioning strategy based on multi-references was used to solve the problem of pose deviation. The results show that the system can avoid the false detection of the hook, improve the measurement accuracy of the hook size and the repeatability of the detection results, and the repeat detection rate can reach 91%-96%. Finally, comparing with standard parts, it is verified that the consistency of machine-checked parts meets the needs of installation.

Key words: machine vision, deformation inspection, virtual instrument, LabVIEW, needle, deformation detection algorithm of parts

中图分类号:

TH71

朱世根, 杨宏贤, 白云峰, 丁浩, 朱巧莲. 长条状细薄带钩零件变形自动检测系统[J]. 纺织学报, 2020, 41(10): 158-163.

ZHU Shigen, YANG Hongxian, BAI Yunfeng, DING Hao, ZHU Qiaolian. Investigation on automatic deformation inspection system of long and thin parts with hooks[J]. Journal of Textile Research, 2020, 41(10): 158-163.

图/表 15

图1

图2

图3

图4

图5

图6

图7

表1

图8

图9

表2

表3

表4

图10

图11

参考文献 12

[1]	余文咏. 基于图像处理技术检测织针轮廓的研究[D]. 上海: 东华大学, 2015: 1-5.
	YU Wenyong. Study on the detection system for kitting needle contour based on digital image process[D]. Shanghai: Donghua University, 2015: 1-5.
[2]	LIU L, LIAO X, ZHU Y, et al. International symposium on photoelectronic detection and imaging 2013: laser sensing and imaging and applications[C]// International Society for Optics and Photonics. Bellingham: Spie-int Soc Optical Engineering, 2013: 1-7.
[3]	颜幸尧, 陈栋. 非接触式针钩变形实时在线监测系统研究[J]. 针织工业, 2016(3):1-3.
	YAN Xingyao, CHEN Dong. Non-contact real-time needle deformation monitor system[J]. Knitting Industries, 2016(3):1-3.
[4]	杨泉海, 李文乐, 陈晓升, 等. 织针筛选机构: 106076866B[P]. 2019-01-08.
	YANG Quanhai, LI Wenle, CHEN Xiaosheng, et al. Screening mechanism for knitting needles: 106076866B[J]. 2019-01-08.
[5]	MIYASHITA K. Needle automatic inspection device, JP33570594A[P]. 1994-12-20.
[6]	MAIRESSE F, SLIWA T M, ROY M, et al. Needle-shape quality control by shadowgraphic image processing[J]. Optical Engineering, 2011,50(2):1-16.
[7]	孙卫红, 阮棉奖, 邵铁锋, 等. 基于机器视觉的生丝抱合性能检测方法[J]. 纺织学报, 2019,40(8):164-168.
	SUN Weihong, RUAN Mianjiang, SHAO Tiefeng, et al. Detection method of cohesive performance of raw silk based on machine vision[J]. Journal of Textile Research, 2019,40(8):164-168.
[8]	景军锋, 张星星. 基于机器视觉的玻璃纤维管纱毛羽检测[J]. 纺织学报, 2019,40(5):157-162.
	JING Junfeng, ZHANG Xingxing. Fiber glass bobbin yarn hairiness detection based on machine vision[J]. Journal of Textile Research, 2019,40(5):157-162.
[9]	张喜民, 余奇颖, 张金博, 等. 基于机器视觉的手机尾插件精密测量方法研究[J]. 仪器仪表学报, 2019,40(10):47-54.
	ZHANG Ximin, YU Qiying, ZHANG Jinbo, et al. Research on precision measurement method for mobile phone tail plug part based on machine vision[J]. Chinese Journal of Scientific Instrument, 2019,40(10):47-54.
[10]	黄晓. 基于LabVIEW和IMAQ Vision的几何尺寸非接触测量系统的研究[D]. 武汉: 武汉理工大学, 2007: 20-22.
	HUANG Xiao. Recearch on non-contact visual inspection system of geometric dimension based on LabVIEW and IMAQ vision[D]. Wuhan: Wuhan University of Technology, 2007: 20-22.
[11]	张文勇, 陈乐柱. 基于LabVIEW机器视觉的餐具分拣系统[J]. 计算机科学, 2008,45(1):595-597.
	ZHANG Wenyong, CHEN Lezhu. Tableware sorting system based on LabVIEW machine vision[J]. Computer Science, 2008,45(1):595-597.
[12]	DERGANC J, LIKAR B, PERNUS F. A machine vision system for measuring the eccentricity of bearings[J]. Computers in Industry, 2003,50(1):103-111. doi: 10.1016/S0166-3615(02)00141-0

相关文章 15

[1]	戴宁, 彭来湖, 胡旭东, 崔英, 钟垚森, 王越锋. 基于Euler-Bernoulli 梁理论的无缝内衣机织针编织过程固有频率特性研究[J]. 纺织学报, 2020, 41(12): 144-150.
[2]	戴宁, 彭来湖, 胡旭东, 崔英, 钟垚森, 王越峰. 纬编针织机织针自由状态下固有频率测试方法[J]. 纺织学报, 2020, 41(11): 150-155.
[3]	李冬冬, 张成俊, 左小艳, 张弛, 李红军, 周向阳. 混合磁悬浮织针驱动的永磁织针磁场分布规律[J]. 纺织学报, 2020, 41(09): 136-142.
[4]	张建新, 李琦. 基于机器视觉的筒子纱密度在线检测系统[J]. 纺织学报, 2020, 41(06): 141-146.
[5]	路浩, 陈原. 基于机器视觉的碳纤维预浸料表面缺陷检测方法[J]. 纺织学报, 2020, 41(04): 51-57.
[6]	王文胜, 李天剑, 冉宇辰, 卢影, 黄民. 筒子纱纱笼纱杆的定位检测方法[J]. 纺织学报, 2020, 41(03): 160-167.
[7]	金守峰, 林强强, 马秋瑞, 张浩. 基于BP 神经网络的织物表面绒毛质量的检测方法[J]. 纺织学报, 2020, 41(02): 69-76.
[8]	景军锋, 张君扬, 张缓缓, 苏泽斌. 梯度空间下的丝饼表面缺陷检测[J]. 纺织学报, 2020, 41(02): 44-51.
[9]	张成俊, 游良风, 左小艳, 张弛, 朱里. 电脑横机织针的磁驱动设计与建模[J]. 纺织学报, 2019, 40(09): 180-185.
[10]	孙卫红, 阮棉奖, 邵铁锋, 梁曼. 基于机器视觉的生丝抱合性能检测方法[J]. 纺织学报, 2019, 40(08): 164-168.
[11]	景军锋, 张星星. 基于机器视觉的玻璃纤维管纱毛羽检测[J]. 纺织学报, 2019, 40(05): 157-162.
[12]	徐洋, 朱治潮, 盛晓伟, 余智祺, 孙以泽. 基于机器视觉的鞋面特征点自动识别改进方法[J]. 纺织学报, 2019, 40(03): 168-174.
[13]	景军锋, 郭根. 基于机器视觉的丝饼毛羽检测[J]. 纺织学报, 2019, 40(01): 147-152.
[14]	牟新刚蔡逸超周晓陈国良. 基于机器视觉的筒子纱缺陷在线检测系统[J]. 纺织学报, 2018, 39(01): 139-145.
[15]	杨松林马帅丁朝鹏范红丽薛欢欢. 应用机器视觉的织物表面绒毛率测试系统[J]. 纺织学报, 2017, 38(06): 118-123.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

方案	机器检测			合格品误检数		合格品误检率/%
方案	合格品	不合格品		合格品误检数		合格品误检率/%
一	60	240	7		6.6
二	52	248	0		0

次数	1	2	3	4	5
1	0.055	0.055	0.055	0.055	0.252
2	0.055	0.053	0.055	0.055	0.266
3	0.051	0.043	0.055	0.055	0.266
4	0.047	0.055	0.055	0.055	0.252
5	0.055	0.055	0.055	0.054	0.262
6	0.042	0.048	0.055	0.055	0.270
7	0.055	0.054	0.055	0.051	0.277
8	0.055	0.055	0.055	0.044	0.253
9	0.048	0.045	0.057	0.056	0.252
10	0.054	0.043	0.055	0.054	0.269
测量误差	0.013	0.012	0.002	0.012	0.025

次数	1	2	3	4	5
1	0.048	0.055	0.055	0.052	0.279
2	0.055	0.055	0.055	0.045	0.279
3	0.055	0.055	0.055	0.055	0.266
4	0.047	0.055	0.055	0.054	0.279
5	0.055	0.055	0.068	0.055	0.279
6	0.055	0.055	0.069	0.055	0.273
7	0.046	0.055	0.055	0.054	0.279
8	0.050	0.042	0.055	0.055	0.279
9	0.042	0.042	0.055	0.044	0.273
10	0.055	0.055	0.055	0.055	0.279
测量误差	0.013	0.013	0.014	0.011	0.013

类型	实验次数	初检合格数	初检合格品再检
类型	实验次数	初检合格数	个数	重复检出率/%
改进前	1	106	79	75
	2	98	78	80
	3	100	83	83
	4	106	83	78
改进后	1	99	90	91
	2	101	97	96
	3	96	87	91
	4	96	89	93

长条状细薄带钩零件变形自动检测系统

Investigation on automatic deformation inspection system of long and thin parts with hooks

RichHTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

图/表 15

参考文献 12

相关文章 15

Metrics

本文评价

推荐阅读 0